{"task":"Use exploratory-autoresearch","agent":"codex","constraints":{"max_risk":"medium","needs_install_command":true,"min_stars":0},"feedback":{"event_id":"resolve_4cb6fd18-b126-4411-8624-ece5adc79777","outcome_api":"https://www.openagentskill.com/api/agent/outcome","method":"POST","selected_skill_slug":"gaasher-exploratory-autoresearch","selected_skill_name":"exploratory-autoresearch","alternative_skill_slugs":["uditgoenka-autoresearch","alvinreal-awesome-autoresearch","leo-lilinxiao-codex-autoresearch","rlaope-omh-autoresearch-goal"],"expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"report_after":["After trying the selected skill, report whether it solved the task.","Mark blocked_by_risk when audit, license, credentials, shell, or network risk prevents safe use.","Mark setup_required when the skill looks relevant but needs missing keys, data, or manual configuration.","Mark not_relevant when the selected skill does not match the task after inspection.","Include output_quality, error_type, workspace, human_review_required, evidence_url, and time_to_useful_ms when available."],"json_example":{"event_id":"resolve_4cb6fd18-b126-4411-8624-ece5adc79777","skill_slug":"gaasher-exploratory-autoresearch","task":"Use exploratory-autoresearch","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":"f1169e6db0b0f8a83ced3a18562b7c57e14a748a","content_hash":"94f2fbf5cad3f6036dfa20764ca1f13622b620e88dc43e2bf35e9c9424149d77","ref":"main","path":"loops/exploratory-autoresearch/SKILL.md","sync_status":"current"}},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_4cb6fd18-b126-4411-8624-ece5adc79777\" --skill \"gaasher-exploratory-autoresearch\" --task \"Use exploratory-autoresearch\" --agent \"codex\" --outcome success"},"agent_feedback_loop":{"version":"openagentskill-agent-feedback-loop-v3","status":"active","purpose":"Report the result of one resolved skill run so Trust Score v5 and future Resolve rankings learn from real use.","event_id":"resolve_4cb6fd18-b126-4411-8624-ece5adc79777","selected_skill_slug":"gaasher-exploratory-autoresearch","selected_skill_name":"exploratory-autoresearch","endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","idempotency":"Retrying the same event_id updates the previous outcome.","dry_run":{"supported":true,"instruction":"Set dry_run=true to validate a payload before wiring a new agent integration."},"expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"error_types":["install_failed","runtime_error","not_relevant","permission_blocked","risk_blocked","setup_required","low_quality_output","missing_dependency","timeout","other"],"workspaces":["sandbox","local","ci","production","unknown"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url"],"payload_template":{"event_id":"resolve_4cb6fd18-b126-4411-8624-ece5adc79777","skill_slug":"gaasher-exploratory-autoresearch","task":"Use exploratory-autoresearch","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":"f1169e6db0b0f8a83ced3a18562b7c57e14a748a","content_hash":"94f2fbf5cad3f6036dfa20764ca1f13622b620e88dc43e2bf35e9c9424149d77","ref":"main","path":"loops/exploratory-autoresearch/SKILL.md","sync_status":"current"}},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_4cb6fd18-b126-4411-8624-ece5adc79777\" --skill \"gaasher-exploratory-autoresearch\" --task \"Use exploratory-autoresearch\" --agent \"codex\" --outcome success","ranking_inputs_updated":["Trust Score v5 outcome confidence","Resolve ranking outcome evidence","Skill detail outcome signal block","Outcome leaderboard"]},"install_receipt":{"version":"openagentskill-install-receipt-v2","receipt_id":"receipt_4cb6fd18-b126-4411-8624-ece5adc79777","resolve_event_id":"resolve_4cb6fd18-b126-4411-8624-ece5adc79777","generated_at":"2026-09-06T22:35:03.259Z","task":"Use exploratory-autoresearch","agent":"codex","constraints":{"max_risk":"medium","needs_install_command":true,"min_stars":0},"urls":{"web":"https://www.openagentskill.com/resolve?task=Use+exploratory-autoresearch&agent=codex&max_risk=medium","json":"https://www.openagentskill.com/api/agent/receipt?task=Use+exploratory-autoresearch&agent=codex&max_risk=medium","text":"https://www.openagentskill.com/api/agent/receipt?task=Use+exploratory-autoresearch&agent=codex&max_risk=medium&format=text","resolve_json":"https://www.openagentskill.com/api/agent/resolve?task=Use+exploratory-autoresearch&agent=codex&max_risk=medium","resolve_text":"https://www.openagentskill.com/api/agent/resolve?task=Use+exploratory-autoresearch&agent=codex&max_risk=medium&format=text"},"selected_skill":{"slug":"gaasher-exploratory-autoresearch","name":"exploratory-autoresearch","description":"Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps.","category":"research","url":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch","api_url":"https://www.openagentskill.com/api/agent/skills/gaasher-exploratory-autoresearch","audit_url":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=gaasher-exploratory-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium","install_api_url":"https://www.openagentskill.com/api/skills/gaasher-exploratory-autoresearch/install","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","source_version":{"version":"1.0.0","commit_sha":"f1169e6db0b0f8a83ced3a18562b7c57e14a748a","content_hash":"94f2fbf5cad3f6036dfa20764ca1f13622b620e88dc43e2bf35e9c9424149d77","ref":"main","path":"loops/exploratory-autoresearch/SKILL.md","sync_status":"current"}},"install":{"command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","target":"codex","label":"Codex install prompt","kind":"agent-prompt","value":"Install the \"exploratory-autoresearch\" agent skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","ready":true,"policy":"review","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"blocked":false},"decision":{"recommendation":"Require human approval before installing into a real workspace.","why_selected":["Matches task terms: exploratory, autoresearch","Install handoff is available","Repository freshness signal is available","Registry match score 42","Fallback candidate for Research agents","68/100 Trust Score","0/100 Agent Proven Score","78/100 audit score"],"suited_tasks":["Research agents workflows","Claude Code teams","builders willing to evaluate younger projects","Search sources","Extract claims","Synthesize findings","Chunk documents","Create embeddings"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"]},"trust":{"score":68,"label":"Sandbox only","version":"trust-score-v5","base_score":76,"outcome_confidence":0,"outcome_signal":"No agent outcome data yet","outcome_total":0,"outcome_success_rate":null,"decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["68/100 Trust Score v5","76/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]}},"agent_proven":{"score":0,"label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"installAttempts":0,"installSuccessRate":null,"riskBlocked":0,"setupRequired":0,"avgOutputQuality":null,"productionOutcomes":0}},"risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety_score":66,"audit_score":78,"notes":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","66/100 agent safety score"],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"minimum_review_before_use":["Trust: 76/100 Strong shortlist","Audit: 78/100 Needs review","Safety: 66/100 Review before install","Review repository, license, install command, and permission surface before production use."]},"alternatives":[{"slug":"uditgoenka-autoresearch","name":"Autoresearch","url":"https://www.openagentskill.com/skills/uditgoenka-autoresearch","audit_url":"https://www.openagentskill.com/skills/uditgoenka-autoresearch/audit","install_command":"npx skills add uditgoenka/autoresearch","trust_score":90,"audit_score":94,"safety_score":82,"reason":"Matches task terms: autoresearch","policy":"review"},{"slug":"alvinreal-awesome-autoresearch","name":"Awesome Autoresearch","url":"https://www.openagentskill.com/skills/alvinreal-awesome-autoresearch","audit_url":"https://www.openagentskill.com/skills/alvinreal-awesome-autoresearch/audit","install_command":"npx skills add alvinreal/awesome-autoresearch","trust_score":85,"audit_score":90,"safety_score":78,"reason":"Matches task terms: autoresearch","policy":"review"},{"slug":"leo-lilinxiao-codex-autoresearch","name":"Codex Autoresearch","url":"https://www.openagentskill.com/skills/leo-lilinxiao-codex-autoresearch","audit_url":"https://www.openagentskill.com/skills/leo-lilinxiao-codex-autoresearch/audit","install_command":"npx skills add leo-lilinxiao/codex-autoresearch","trust_score":84,"audit_score":88,"safety_score":64,"reason":"Matches task terms: autoresearch","policy":"review"},{"slug":"rlaope-omh-autoresearch-goal","name":"omh-autoresearch-goal","url":"https://www.openagentskill.com/skills/rlaope-omh-autoresearch-goal","audit_url":"https://www.openagentskill.com/skills/rlaope-omh-autoresearch-goal/audit","install_command":"npx skills add rlaope/oh-my-hermes --skill omh-autoresearch-goal","trust_score":82,"audit_score":84,"safety_score":72,"reason":"Matches task terms: autoresearch","policy":"review"}],"outcome_feedback":{"event_id":"resolve_4cb6fd18-b126-4411-8624-ece5adc79777","endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"resolve_4cb6fd18-b126-4411-8624-ece5adc79777","skill_slug":"gaasher-exploratory-autoresearch","task":"Use exploratory-autoresearch","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":"f1169e6db0b0f8a83ced3a18562b7c57e14a748a","content_hash":"94f2fbf5cad3f6036dfa20764ca1f13622b620e88dc43e2bf35e9c9424149d77","ref":"main","path":"loops/exploratory-autoresearch/SKILL.md","sync_status":"current"}},"dry_run_payload":{"event_id":"resolve_4cb6fd18-b126-4411-8624-ece5adc79777","skill_slug":"gaasher-exploratory-autoresearch","task":"Use exploratory-autoresearch","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":"f1169e6db0b0f8a83ced3a18562b7c57e14a748a","content_hash":"94f2fbf5cad3f6036dfa20764ca1f13622b620e88dc43e2bf35e9c9424149d77","ref":"main","path":"loops/exploratory-autoresearch/SKILL.md","sync_status":"current"},"dry_run":true},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_4cb6fd18-b126-4411-8624-ece5adc79777\" --skill \"gaasher-exploratory-autoresearch\" --task \"Use exploratory-autoresearch\" --agent \"codex\" --outcome success","instruction":"After one narrow sandbox run, report success, failed, not_relevant, blocked_by_risk, or setup_required so Trust Score v5 and future agent rankings learn from real usage."},"next_steps":["Read the audit page: https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch/audit","Fetch the pre-install eval: https://www.openagentskill.com/api/agent/evals?slug=gaasher-exploratory-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium","Do not auto-install yet. Ask for human review before running: npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","Run one narrow task with no production secrets or irreversible side effects.","Report the result to https://www.openagentskill.com/api/agent/outcome using event_id resolve_4cb6fd18-b126-4411-8624-ece5adc79777."],"stable_fields":["receipt_id","selected_skill","install","trust","risk","alternatives","outcome_feedback","next_steps"],"freshness_policy":"Re-resolve before production use or after 24 hours to refresh trust, audit, and outcome signals."},"recommendation":{"task":"Use exploratory-autoresearch","agent":"codex","best_skill":{"slug":"gaasher-exploratory-autoresearch","name":"exploratory-autoresearch","description":"Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps.","category":"research","url":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch","api_url":"https://www.openagentskill.com/api/agent/skills/gaasher-exploratory-autoresearch","audit_url":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=gaasher-exploratory-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","source_version":{"version":"1.0.0","commit_sha":"f1169e6db0b0f8a83ced3a18562b7c57e14a748a","content_hash":"94f2fbf5cad3f6036dfa20764ca1f13622b620e88dc43e2bf35e9c9424149d77","ref":"main","path":"loops/exploratory-autoresearch/SKILL.md","sync_status":"current"}},"install":{"command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","target":"codex","label":"Codex install prompt","kind":"agent-prompt","value":"Install the \"exploratory-autoresearch\" agent skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","install_api":"https://www.openagentskill.com/api/skills/gaasher-exploratory-autoresearch/install","ready":true,"review_required":true,"auto_install_allowed":false,"policy":"review"},"why_recommended":["Matches task terms: exploratory, autoresearch","Install handoff is available","Repository freshness signal is available","Registry match score 42","Fallback candidate for Research agents","68/100 OpenAgentSkill Trust Score v5","78/100 audit score","66/100 safety score"],"trust_score_v5":{"score":68,"base_score":76,"outcome_confidence":0,"tier":"review","label":"Sandbox only","version":"trust-score-v5","install_policy":"human_review_before_install","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["68/100 Trust Score v5","76/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","install":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"agent_compatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"risk":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomes":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["research","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","trust_score":68,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"best_for":["research","agent-skill"],"do_not_use_for":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"known_risks":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":76,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"trust_score_v4":{"score":76,"tier":"strong","label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","install":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"agent_compatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"risk":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomes":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","agent-skill"],"do_not_use_for":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"known_risks":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_score_v3":{"score":76,"tier":"strong","label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","install":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"agent_compatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"risk":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},"trust_score_v2":{"score":76,"tier":"strong","label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","install":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"agent_compatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"risk":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},"risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"66/100 Review before install","trust":"76/100 Strong shortlist","notes":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Quality score needs review","66/100 agent safety score"]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"gaasher-exploratory-autoresearch","name":"exploratory-autoresearch","description":"Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps.","category":"research","url":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","github_repo":"gaasher/Agent-Loop-Skills"},"suited_tasks":["Research agents workflows","Claude Code teams","builders willing to evaluate younger projects","Search sources","Extract claims","Synthesize findings","Chunk documents","Create embeddings"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add gaasher-exploratory-autoresearch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"exploratory-autoresearch\" agent skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"exploratory-autoresearch\" as a Claude Code skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"exploratory-autoresearch\" from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/gaasher-exploratory-autoresearch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/gaasher-exploratory-autoresearch"},"trust":{"score":76,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","install":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","agent-skill"],"known_risks":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":63,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use exploratory-autoresearch","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 76/100 Strong shortlist","Audit: 78/100 Needs review","Safety: 66/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"gaasher-exploratory-autoresearch (exploratory-autoresearch)","install_command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"gaasher-exploratory-autoresearch","task":"Use exploratory-autoresearch","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch","api":"https://www.openagentskill.com/api/agent/skills/gaasher-exploratory-autoresearch","audit":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=gaasher-exploratory-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20exploratory-autoresearch&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20exploratory-autoresearch&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/gaasher-exploratory-autoresearch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/gaasher-exploratory-autoresearch"}},"agent_contract":{"version":"openagentskill-resolve-contract-v2","input_task":"Use exploratory-autoresearch","recommended_skill_slug":"gaasher-exploratory-autoresearch","recommended_skill_name":"exploratory-autoresearch","install_command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","install_policy":"review","auto_install_allowed":false,"human_review_required":true,"audit_url":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=gaasher-exploratory-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium","skill_api_url":"https://www.openagentskill.com/api/agent/skills/gaasher-exploratory-autoresearch","do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"minimum_review_before_use":["Trust: 76/100 Strong shortlist","Audit: 78/100 Needs review","Safety: 66/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"gaasher-exploratory-autoresearch (exploratory-autoresearch)","install_command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"supply_asset":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"Research agents","description":"I need my agent to research a topic, compare sources, and produce a concise report.","useCases":[{"slug":"research-agents","title":"Research agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"workflow-automation","title":"Workflow automation"}]},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":68,"lastPushedAt":"2026-06-30T04:03:49+00:00"},"github_quality":{"stars":163,"starsLabel":"163","forks":19,"license":"MIT","qualityScore":63,"trustScore":76,"auditScore":78},"coverage_tags":["Research","Research agents","agent-skill"]},"alternatives":[{"slug":"uditgoenka-autoresearch","name":"Autoresearch","url":"https://www.openagentskill.com/skills/uditgoenka-autoresearch","install_command":"npx skills add uditgoenka/autoresearch","trust_score":90,"audit_score":94,"safety_score":82,"why_consider":"Matches task terms: autoresearch","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"82/100 Review before install","trust":"90/100 Production candidate","notes":["Documentation summary is thin"]}},{"slug":"alvinreal-awesome-autoresearch","name":"Awesome Autoresearch","url":"https://www.openagentskill.com/skills/alvinreal-awesome-autoresearch","install_command":"npx skills add alvinreal/awesome-autoresearch","trust_score":85,"audit_score":90,"safety_score":78,"why_consider":"Matches task terms: autoresearch","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"78/100 Review before install","trust":"85/100 Strong shortlist","notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"]}},{"slug":"leo-lilinxiao-codex-autoresearch","name":"Codex Autoresearch","url":"https://www.openagentskill.com/skills/leo-lilinxiao-codex-autoresearch","install_command":"npx skills add leo-lilinxiao/codex-autoresearch","trust_score":84,"audit_score":88,"safety_score":64,"why_consider":"Matches task terms: autoresearch","risk":{"level":"Safe to try","safety_tier":"Reviewed with permission notes","safety":"64/100 Review before install","trust":"84/100 Strong shortlist","notes":["High-risk permission hints: Shell or command execution","Documentation summary is thin"]}},{"slug":"rlaope-omh-autoresearch-goal","name":"omh-autoresearch-goal","url":"https://www.openagentskill.com/skills/rlaope-omh-autoresearch-goal","install_command":"npx skills add rlaope/oh-my-hermes --skill omh-autoresearch-goal","trust_score":82,"audit_score":84,"safety_score":72,"why_consider":"Matches task terms: autoresearch","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"72/100 Review before install","trust":"82/100 Strong shortlist","notes":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}}],"decision_packet":{"version":"openagentskill-agent-decision-packet-v1","task":"Use exploratory-autoresearch","agent":"codex","selected_skill":{"slug":"gaasher-exploratory-autoresearch","name":"exploratory-autoresearch","url":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch","api_url":"https://www.openagentskill.com/api/agent/skills/gaasher-exploratory-autoresearch","audit_url":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch/audit","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","source_version":{"version":"1.0.0","commit_sha":"f1169e6db0b0f8a83ced3a18562b7c57e14a748a","content_hash":"94f2fbf5cad3f6036dfa20764ca1f13622b620e88dc43e2bf35e9c9424149d77","ref":"main","path":"loops/exploratory-autoresearch/SKILL.md","sync_status":"current"}},"suited_tasks":["Research agents workflows","Claude Code teams","builders willing to evaluate younger projects","Search sources","Extract claims","Synthesize findings","Chunk documents","Create embeddings"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","target":"codex","label":"Codex install prompt","policy":"review","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true},"trust":{"score":68,"label":"Sandbox only","version":"trust-score-v5","base_score":76,"outcome_confidence":0,"decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["68/100 Trust Score v5","76/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"status":"info","detail":"163 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"status":"warn","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"status":"pass","detail":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch"},{"id":"install_safety","label":"Install command safety","score":92,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"status":"pass","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch"},{"id":"review_status","label":"Review status","score":88,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"status":"info","detail":"No agent outcome data yet"}]},"risk":{"level":"Needs review","audit_label":"Needs review","safety":"66/100 Review before install","trust":"76/100 Strong shortlist","safety_tier":"Reviewed with permission notes","notes":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"minimum_review_before_use":["Trust: 76/100 Strong shortlist","Audit: 78/100 Needs review","Safety: 66/100 Review before install","Review repository, license, install command, and permission surface before production use."]},"alternatives":[{"slug":"uditgoenka-autoresearch","name":"Autoresearch","url":"https://www.openagentskill.com/skills/uditgoenka-autoresearch","install_command":"npx skills add uditgoenka/autoresearch","trust_score":90,"audit_score":94,"safety_score":82,"why_consider":"Matches task terms: autoresearch","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"82/100 Review before install","trust":"90/100 Production candidate","notes":["Documentation summary is thin"]}},{"slug":"alvinreal-awesome-autoresearch","name":"Awesome Autoresearch","url":"https://www.openagentskill.com/skills/alvinreal-awesome-autoresearch","install_command":"npx skills add alvinreal/awesome-autoresearch","trust_score":85,"audit_score":90,"safety_score":78,"why_consider":"Matches task terms: autoresearch","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"78/100 Review before install","trust":"85/100 Strong shortlist","notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"]}},{"slug":"leo-lilinxiao-codex-autoresearch","name":"Codex Autoresearch","url":"https://www.openagentskill.com/skills/leo-lilinxiao-codex-autoresearch","install_command":"npx skills add leo-lilinxiao/codex-autoresearch","trust_score":84,"audit_score":88,"safety_score":64,"why_consider":"Matches task terms: autoresearch","risk":{"level":"Safe to try","safety_tier":"Reviewed with permission notes","safety":"64/100 Review before install","trust":"84/100 Strong shortlist","notes":["High-risk permission hints: Shell or command execution","Documentation summary is thin"]}},{"slug":"rlaope-omh-autoresearch-goal","name":"omh-autoresearch-goal","url":"https://www.openagentskill.com/skills/rlaope-omh-autoresearch-goal","install_command":"npx skills add rlaope/oh-my-hermes --skill omh-autoresearch-goal","trust_score":82,"audit_score":84,"safety_score":72,"why_consider":"Matches task terms: autoresearch","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"72/100 Review before install","trust":"82/100 Strong shortlist","notes":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}}],"outcome_feedback":{"event_id":"resolve_4cb6fd18-b126-4411-8624-ece5adc79777","endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"resolve_4cb6fd18-b126-4411-8624-ece5adc79777","skill_slug":"gaasher-exploratory-autoresearch","task":"Use exploratory-autoresearch","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":"f1169e6db0b0f8a83ced3a18562b7c57e14a748a","content_hash":"94f2fbf5cad3f6036dfa20764ca1f13622b620e88dc43e2bf35e9c9424149d77","ref":"main","path":"loops/exploratory-autoresearch/SKILL.md","sync_status":"current"}},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_4cb6fd18-b126-4411-8624-ece5adc79777\" --skill \"gaasher-exploratory-autoresearch\" --task \"Use exploratory-autoresearch\" --agent \"codex\" --outcome success"},"next_agent_action":"Ask for human approval or choose a safer alternative before installing.","stable_fields":["decision_packet.selected_skill","decision_packet.install","decision_packet.risk.do_not_use_when","decision_packet.alternatives","decision_packet.outcome_feedback","decision_packet.trust.decision"]},"agent_instruction":"Use exploratory-autoresearch for: Use exploratory-autoresearch\nReview audit: https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch/audit\nAsk for human approval before installing: npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch\nIf the audit or policy warnings are unacceptable, choose one of the alternatives."},"recommendation_lanes":{"best_match":{"rank":1,"match_score":42,"raw_match_score":229.8,"semantic_relevance":42,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"gaasher-exploratory-autoresearch","name":"exploratory-autoresearch","description":"Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps.","category":"research","github_stars":163,"created_at":"2026-09-04T05:11:21.841977+00:00","updated_at":"2026-06-30T04:03:49+00:00","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","github_repo":"gaasher/Agent-Loop-Skills","source_version":{"version":"1.0.0","commit_sha":"f1169e6db0b0f8a83ced3a18562b7c57e14a748a","content_hash":"94f2fbf5cad3f6036dfa20764ca1f13622b620e88dc43e2bf35e9c9424149d77","ref":"main","path":"loops/exploratory-autoresearch/SKILL.md","sync_status":"current"}},"recommendation_reasons":["Matches task terms: exploratory, autoresearch","Install handoff is available","Repository freshness signal is available","Registry match score 42"],"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"Research agents","description":"I need my agent to research a topic, compare sources, and produce a concise report.","useCases":[{"slug":"research-agents","title":"Research agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"workflow-automation","title":"Workflow automation"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":163,"starsLabel":"163","forks":19,"license":"MIT","qualityScore":63,"trustScore":76,"auditScore":78},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":68,"lastPushedAt":"2026-06-30T04:03:49+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Needs review"]},"coverageTags":["Research","Research agents","agent-skill"]},"quality":{"score":63,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"163","tone":"neutral"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":76,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"163 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"info","label":"GitHub adoption","detail":"163 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","install":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":68,"base_score":76,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["68/100 Trust Score v5","76/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"163 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"info","label":"GitHub adoption","detail":"163 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","install":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["research","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","trust_score":68,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":76,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":66,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Quality score needs review","66/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Quality score needs review"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Quality score needs review","66/100 agent safety score"]},"decision":{"readiness_score":62,"readiness_label":"Prototype first","headline":"Fallback candidate for Research agents","role":"Fallback candidate","best_for":["Research agents workflows","Claude Code teams","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Research agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","value":"Install the \"exploratory-autoresearch\" agent skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review exploratory-autoresearch trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add gaasher-exploratory-autoresearch","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"exploratory-autoresearch\" agent skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"exploratory-autoresearch\" as a Claude Code skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"exploratory-autoresearch\" from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"gaasher-exploratory-autoresearch","name":"exploratory-autoresearch","description":"Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps.","category":"research","url":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","github_repo":"gaasher/Agent-Loop-Skills"},"suited_tasks":["Research agents workflows","Claude Code teams","builders willing to evaluate younger projects","Search sources","Extract claims","Synthesize findings","Chunk documents","Create embeddings"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add gaasher-exploratory-autoresearch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"exploratory-autoresearch\" agent skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"exploratory-autoresearch\" as a Claude Code skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"exploratory-autoresearch\" from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/gaasher-exploratory-autoresearch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/gaasher-exploratory-autoresearch"},"trust":{"score":76,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","install":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","agent-skill"],"known_risks":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":63,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use exploratory-autoresearch","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 76/100 Strong shortlist","Audit: 78/100 Needs review","Safety: 66/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"gaasher-exploratory-autoresearch (exploratory-autoresearch)","install_command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"gaasher-exploratory-autoresearch","task":"Use exploratory-autoresearch","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch","api":"https://www.openagentskill.com/api/agent/skills/gaasher-exploratory-autoresearch","audit":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=gaasher-exploratory-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20exploratory-autoresearch&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20exploratory-autoresearch&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/gaasher-exploratory-autoresearch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/gaasher-exploratory-autoresearch"}},"use_cases":[{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"urls":{"web":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch","api":"https://www.openagentskill.com/api/agent/skills/gaasher-exploratory-autoresearch","install_api":"https://www.openagentskill.com/api/skills/gaasher-exploratory-autoresearch/install","audit":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=gaasher-exploratory-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/gaasher-exploratory-autoresearch?metric=audit","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch"}},"safer_alternative":{"rank":2,"match_score":30,"raw_match_score":219.9,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"uditgoenka-autoresearch","name":"Autoresearch","description":"Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.","category":"development","github_stars":5975,"created_at":"2026-06-16T08:45:37.929318+00:00","updated_at":"2026-08-12T22:28:18+00:00","repository":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch","github_repo":"uditgoenka/autoresearch","source_version":{"version":"2.2.2","commit_sha":"050e30dc4ba0974b03f2873111b9901ec3211390","content_hash":"c3ec24a5c90e72bfeca1f69702d5c9159c90b3c8546e94a87eead20a715e6045","ref":"master","path":".agents/skills/autoresearch/SKILL.md","sync_status":"changed"}},"recommendation_reasons":["Matches task terms: autoresearch","Useful GitHub adoption: 5,975 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"research-agents","title":"Research agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","JavaScript"],"install":{"ready":true,"command":"npx skills add uditgoenka/autoresearch","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":5975,"starsLabel":"6.0K","forks":446,"license":"MIT","qualityScore":100,"trustScore":90,"auditScore":94},"maintenance":{"status":"fresh","label":"25d since push","daysSincePush":25,"lastPushedAt":"2026-08-12T22:28:18+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Coding","Coding agents","development","claude-code","agent-skills","developer-tools","ai","autonomous-agent"]},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"6.0K","tone":"positive"},{"label":"Freshness","value":"25d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":90,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"weight":0.13,"status":"pass","detail":"6.0K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"6.0K stars, 446 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"25d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add uditgoenka/autoresearch"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"6.0K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"6.0K stars, 446 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"25d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add uditgoenka/autoresearch"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin"],"evidence":{"stars":"6.0K GitHub stars","repoActivity":"6.0K stars, 446 forks","lastPushed":"25d since push","license":"MIT","repository":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch","install":"npx skills add uditgoenka/autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add uditgoenka/autoresearch","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","25d since push"]},"agentCompatibility":["JavaScript","Claude Code","Codex","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["development","claude-code","agent-skills","developer-tools","ai","autonomous-agent"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin"]},"trust_v5":{"version":"trust-score-v5","score":87,"base_score":90,"outcome_confidence":0,"tier":"strong","label":"Review then install","summary":"Good shortlist signal, but the agent should review audit notes, install policy, and outcome evidence before running it.","recommendedAction":"Use as the primary candidate after human or sandbox review.","decision":{"install_policy":"agent_install_candidate","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Ask for approval or run a sandbox-only trial before installing.","reasoning":["87/100 Trust Score v5","90/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Low metadata risk"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"weight":0.13,"status":"pass","detail":"6.0K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"6.0K stars, 446 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"25d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add uditgoenka/autoresearch"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"6.0K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"6.0K stars, 446 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"25d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add uditgoenka/autoresearch"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Documentation summary is thin","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"6.0K GitHub stars","repoActivity":"6.0K stars, 446 forks","lastPushed":"25d since push","license":"MIT","repository":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch","install":"npx skills add uditgoenka/autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"agent_install_candidate"},"installReadiness":{"ready":true,"command":"npx skills add uditgoenka/autoresearch","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","25d since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["JavaScript","Claude Code","Codex","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Ask for approval or run a sandbox-only trial before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["development","claude-code","agent-skills","developer-tools","ai","autonomous-agent"],"suited_agents":["JavaScript","Claude Code","Codex","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add uditgoenka/autoresearch","trust_score":87,"trust_version":"trust-score-v5","risk_level":"low","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["development","claude-code","agent-skills","developer-tools","ai","autonomous-agent"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":90,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":94,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety":{"score":82,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","82/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","82/100 agent safety score"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Coding agents","role":"Primary pick","best_for":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add uditgoenka/autoresearch","value":"Install the \"Autoresearch\" agent skill from https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"uditgoenka-autoresearch\",\"task\":\"Install Autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review Autoresearch trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add uditgoenka-autoresearch","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Autoresearch\" agent skill from https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"uditgoenka-autoresearch\",\"task\":\"Install Autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Autoresearch\" as a Claude Code skill from https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"uditgoenka-autoresearch\",\"task\":\"Install Autoresearch\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Autoresearch\" from https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"uditgoenka-autoresearch\",\"task\":\"Install Autoresearch\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"uditgoenka-autoresearch","name":"Autoresearch","description":"Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.","category":"development","url":"https://www.openagentskill.com/skills/uditgoenka-autoresearch","repository":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch","github_repo":"uditgoenka/autoresearch"},"suited_tasks":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Search sources","Extract claims"],"suited_agents":["JavaScript","Claude Code","Codex","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add uditgoenka/autoresearch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add uditgoenka-autoresearch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Autoresearch\" agent skill from https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"uditgoenka-autoresearch\",\"task\":\"Install Autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Autoresearch\" as a Claude Code skill from https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"uditgoenka-autoresearch\",\"task\":\"Install Autoresearch\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Autoresearch\" from https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"uditgoenka-autoresearch\",\"task\":\"Install Autoresearch\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/uditgoenka-autoresearch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/uditgoenka-autoresearch"},"trust":{"score":90,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"6.0K GitHub stars","repoActivity":"6.0K stars, 446 forks","lastPushed":"25d since push","license":"MIT","repository":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch","install":"npx skills add uditgoenka/autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["development","claude-code","agent-skills","developer-tools","ai","autonomous-agent"],"known_risks":["Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":94,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"25d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use exploratory-autoresearch","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 90/100 Production candidate","Audit: 94/100 Safe to try","Safety: 82/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"uditgoenka-autoresearch (Autoresearch)","install_command":"npx skills add uditgoenka/autoresearch","risk_summary":"Safe to try; Reviewed; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"uditgoenka-autoresearch","task":"Use exploratory-autoresearch","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/uditgoenka-autoresearch","api":"https://www.openagentskill.com/api/agent/skills/uditgoenka-autoresearch","audit":"https://www.openagentskill.com/skills/uditgoenka-autoresearch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=uditgoenka-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20exploratory-autoresearch&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20exploratory-autoresearch&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/uditgoenka-autoresearch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/uditgoenka-autoresearch"}},"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"}],"urls":{"web":"https://www.openagentskill.com/skills/uditgoenka-autoresearch","api":"https://www.openagentskill.com/api/agent/skills/uditgoenka-autoresearch","install_api":"https://www.openagentskill.com/api/skills/uditgoenka-autoresearch/install","audit":"https://www.openagentskill.com/skills/uditgoenka-autoresearch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=uditgoenka-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/uditgoenka-autoresearch?metric=audit","repository":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch"}},"popular_alternative":{"rank":15,"match_score":30,"raw_match_score":133.5,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"alirezarezvani-agent-harness","name":"agent-harness","description":"Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).","category":"research","github_stars":24795,"created_at":"2026-08-22T13:22:51.977696+00:00","updated_at":"2026-08-22T12:31:34+00:00","repository":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness","github_repo":"alirezarezvani/claude-skills","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"recommendation_reasons":["Matches task terms: autoresearch","Strong GitHub adoption: 24,795 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"Research agents","description":"I need my agent to research a topic, compare sources, and produce a concise report.","useCases":[{"slug":"research-agents","title":"Research agents"},{"slug":"workflow-automation","title":"Workflow automation"},{"slug":"finance-quant","title":"Finance and quant"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add alirezarezvani/claude-skills --skill agent-harness","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":24795,"starsLabel":"25K","forks":3494,"license":"MIT","qualityScore":91,"trustScore":80,"auditScore":88},"maintenance":{"status":"fresh","label":"15d since push","daysSincePush":15,"lastPushedAt":"2026-08-22T12:31:34+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Financial research output is not financial advice; require human review before any live investment decision","The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"coverageTags":["Research","Research agents","agent-skill"]},"quality":{"score":91,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"25K","tone":"positive"},{"label":"Freshness","value":"15d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":["The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently."]},"trust":{"version":"trust-score-v4","score":80,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"25K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"25K stars, 3.5K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"15d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add alirezarezvani/claude-skills --skill agent-harness"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"25K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"25K stars, 3.5K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"15d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add alirezarezvani/claude-skills --skill agent-harness"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness"},{"status":"info","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"25K GitHub stars","repoActivity":"25K stars, 3.5K forks","lastPushed":"15d since push","license":"MIT","repository":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness","install":"npx skills add alirezarezvani/claude-skills --skill agent-harness","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add alirezarezvani/claude-skills --skill agent-harness","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","15d since push","Financial domain: human review is required before use in a live investment workflow."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Autonomous investment, trading, tax, or suitability decisions without a qualified human review"],"knownRisks":["The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":72,"base_score":80,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["72/100 Trust Score v5","80/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"25K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"25K stars, 3.5K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"15d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add alirezarezvani/claude-skills --skill agent-harness"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"25K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"25K stars, 3.5K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"15d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add alirezarezvani/claude-skills --skill agent-harness"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness"},{"status":"info","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"25K GitHub stars","repoActivity":"25K stars, 3.5K forks","lastPushed":"15d since push","license":"MIT","repository":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness","install":"npx skills add alirezarezvani/claude-skills --skill agent-harness","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add alirezarezvani/claude-skills --skill agent-harness","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","15d since push","Financial domain: human review is required before use in a live investment workflow.","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["research","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add alirezarezvani/claude-skills --skill agent-harness","trust_score":72,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Autonomous investment, trading, tax, or suitability decisions without a qualified human review"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Autonomous investment, trading, tax, or suitability decisions without a qualified human review"],"knownRisks":["The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":80,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":88,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Financial research output is not financial advice; require human review before any live investment decision","The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":72,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Financial research output is not financial advice; require human review before any live investment decision","72/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["Financial research output is not financial advice; require human review before any live investment decision"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Financial research output is not financial advice; require human review before any live investment decision","72/100 agent safety score"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Research agents","role":"Primary pick","best_for":["Research agents workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Research agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add alirezarezvani/claude-skills --skill agent-harness","value":"Install the \"agent-harness\" agent skill from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-harness\",\"task\":\"Install agent-harness\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review agent-harness trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add alirezarezvani-agent-harness","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"agent-harness\" agent skill from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-harness\",\"task\":\"Install agent-harness\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"agent-harness\" as a Claude Code skill from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-harness\",\"task\":\"Install agent-harness\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"agent-harness\" from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-harness\",\"task\":\"Install agent-harness\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"alirezarezvani-agent-harness","name":"agent-harness","description":"Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library).","category":"research","url":"https://www.openagentskill.com/skills/alirezarezvani-agent-harness","repository":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness","github_repo":"alirezarezvani/claude-skills"},"suited_tasks":["Research agents workflows","Claude Code teams","teams that value GitHub adoption signals","Search sources","Extract claims","Synthesize findings","Move data between tools","Transform files"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add alirezarezvani/claude-skills --skill agent-harness","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add alirezarezvani-agent-harness"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"agent-harness\" agent skill from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-harness\",\"task\":\"Install agent-harness\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"agent-harness\" as a Claude Code skill from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-harness\",\"task\":\"Install agent-harness\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"agent-harness\" from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Turn any domain folder of skills into a bounded agentic loop: compile a goal into a verifiable task plan, execute tasks with the domain's own tools, verify every task with machine-run checks, retry with caps, escalate to a human when budgets exhaust, and refuse to close until everything is verified or explicitly waived. Use when you want an agent or subagent to pick up a goal and drive it to a verified close across one of this repo's 18 domains ('run this goal through the engineering harness', 'set up an agentic loop for marketing work', 'make the finance domain self-verifying'). NOT for authoring Claude Code Workflow-tool .js scripts (workflow-builder), N-agent tournaments on one task (agenthub), single-file metric optimization (autoresearch-agent), or discovering published loop recipes (loop-library). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-harness\",\"task\":\"Install agent-harness\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/alirezarezvani-agent-harness/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/alirezarezvani-agent-harness"},"trust":{"score":80,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"25K GitHub stars","repoActivity":"25K stars, 3.5K forks","lastPushed":"15d since push","license":"MIT","repository":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness","install":"npx skills add alirezarezvani/claude-skills --skill agent-harness","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","agent-skill"],"known_risks":["The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":88,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Financial research output is not financial advice; require human review before any live investment decision","The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":91,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"15d since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","production agents without a repository review","The skill relies on external scripts (goal_compiler.py, loop_controller.py, etc.) not fully reviewed in this excerpt; their security posture should be verified independently.","No OpenAgentSkill engagement data yet","Financial research output is not financial advice; require human review before any live investment decision","Financial research output is not financial advice; require human review before any live investment decision.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"agent_contract":{"task_input":"Use exploratory-autoresearch","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 80/100 Strong shortlist","Audit: 88/100 Needs review","Safety: 72/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"alirezarezvani-agent-harness (agent-harness)","install_command":"npx skills add alirezarezvani/claude-skills --skill agent-harness","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"alirezarezvani-agent-harness","task":"Use exploratory-autoresearch","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/alirezarezvani-agent-harness","api":"https://www.openagentskill.com/api/agent/skills/alirezarezvani-agent-harness","audit":"https://www.openagentskill.com/skills/alirezarezvani-agent-harness/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=alirezarezvani-agent-harness&task=Use%20exploratory-autoresearch&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20exploratory-autoresearch&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20exploratory-autoresearch&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/alirezarezvani-agent-harness/install","manifest":"https://www.openagentskill.com/api/registry/manifest/alirezarezvani-agent-harness"}},"use_cases":[{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"slug":"finance-quant","title":"Finance and quant","url":"https://www.openagentskill.com/use-cases/finance-quant"}],"urls":{"web":"https://www.openagentskill.com/skills/alirezarezvani-agent-harness","api":"https://www.openagentskill.com/api/agent/skills/alirezarezvani-agent-harness","install_api":"https://www.openagentskill.com/api/skills/alirezarezvani-agent-harness/install","audit":"https://www.openagentskill.com/skills/alirezarezvani-agent-harness/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=alirezarezvani-agent-harness&task=Use%20exploratory-autoresearch&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/alirezarezvani-agent-harness?metric=audit","repository":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-harness"}},"new_contender":{"rank":6,"match_score":30,"raw_match_score":174,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"gaasher-ml-autoresearch","name":"ml-autoresearch","description":"Use when the user wants an autonomous ML research loop that does more than blindly try changes. After every training run the agent analyses what actually happened inside the model — gradients, activations, embeddings, errors, data — and grounds the next change in that evidence. A `<literature>` on/off dial adds scientific-literature grounding: off behaves as a pure analysis-first loop; on searches papers, grades the evidence, and implements only what prior work supports. One change per run; loops forever until interrupted. Not for one-off training runs or hyperparameter sweeps.","category":"research","github_stars":163,"created_at":"2026-09-04T05:11:02.690012+00:00","updated_at":"2026-06-30T04:03:49+00:00","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/ml-autoresearch","github_repo":"gaasher/Agent-Loop-Skills","source_version":{"version":"1.0.0","commit_sha":"f1169e6db0b0f8a83ced3a18562b7c57e14a748a","content_hash":"294f14ed472491d9bc582e9e2915837ac88ce9d51ec6b784d6b759e473b4c84d","ref":"main","path":"loops/ml-autoresearch/SKILL.md","sync_status":"current"}},"recommendation_reasons":["Matches task terms: autoresearch","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"Research agents","description":"I need my agent to research a topic, compare sources, and produce a concise report.","useCases":[{"slug":"research-agents","title":"Research agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"github-automation","title":"GitHub automation"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add gaasher/Agent-Loop-Skills --skill ml-autoresearch","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":163,"starsLabel":"163","forks":19,"license":"MIT","qualityScore":63,"trustScore":76,"auditScore":78},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":68,"lastPushedAt":"2026-06-30T04:03:49+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Needs review"]},"coverageTags":["Research","Research agents","agent-skill"]},"quality":{"score":63,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"163","tone":"neutral"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":76,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"163 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add gaasher/Agent-Loop-Skills --skill ml-autoresearch"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/ml-autoresearch"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"info","label":"GitHub adoption","detail":"163 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add gaasher/Agent-Loop-Skills --skill ml-autoresearch"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/ml-autoresearch"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/ml-autoresearch","install":"npx skills add gaasher/Agent-Loop-Skills --skill ml-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add gaasher/Agent-Loop-Skills --skill ml-autoresearch","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":68,"base_score":76,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["68/100 Trust Score v5","76/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"163 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add gaasher/Agent-Loop-Skills --skill ml-autoresearch"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/ml-autoresearch"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"info","label":"GitHub adoption","detail":"163 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add gaasher/Agent-Loop-Skills --skill ml-autoresearch"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/ml-autoresearch"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/ml-autoresearch","install":"npx skills add gaasher/Agent-Loop-Skills --skill ml-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add gaasher/Agent-Loop-Skills --skill ml-autoresearch","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["research","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add gaasher/Agent-Loop-Skills --skill ml-autoresearch","trust_score":68,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":76,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":66,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Quality score needs review","66/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Quality score needs review"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Quality score needs review","66/100 agent safety score"]},"decision":{"readiness_score":62,"readiness_label":"Prototype first","headline":"Fallback candidate for Research agents","role":"Fallback candidate","best_for":["Research agents workflows","Claude Code teams","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Research agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add gaasher/Agent-Loop-Skills --skill ml-autoresearch","value":"Install the \"ml-autoresearch\" agent skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/ml-autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Use when the user wants an autonomous ML research loop that does more than blindly try changes. After every training run the agent analyses what actually happened inside the model — gradients, activations, embeddings, errors, data — and grounds the next change in that evidence. A `<literature>` on/off dial adds scientific-literature grounding: off behaves as a pure analysis-first loop; on searches papers, grades the evidence, and implements only what prior work supports. One change per run; loops forever until interrupted. Not for one-off training runs or hyperparameter sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-ml-autoresearch\",\"task\":\"Install ml-autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review ml-autoresearch trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add gaasher-ml-autoresearch","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"ml-autoresearch\" agent skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/ml-autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Use when the user wants an autonomous ML research loop that does more than blindly try changes. After every training run the agent analyses what actually happened inside the model — gradients, activations, embeddings, errors, data — and grounds the next change in that evidence. A `<literature>` on/off dial adds scientific-literature grounding: off behaves as a pure analysis-first loop; on searches papers, grades the evidence, and implements only what prior work supports. One change per run; loops forever until interrupted. Not for one-off training runs or hyperparameter sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-ml-autoresearch\",\"task\":\"Install ml-autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"ml-autoresearch\" as a Claude Code skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/ml-autoresearch. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Use when the user wants an autonomous ML research loop that does more than blindly try changes. After every training run the agent analyses what actually happened inside the model — gradients, activations, embeddings, errors, data — and grounds the next change in that evidence. A `<literature>` on/off dial adds scientific-literature grounding: off behaves as a pure analysis-first loop; on searches papers, grades the evidence, and implements only what prior work supports. One change per run; loops forever until interrupted. Not for one-off training runs or hyperparameter sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-ml-autoresearch\",\"task\":\"Install ml-autoresearch\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"ml-autoresearch\" from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/ml-autoresearch into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Use when the user wants an autonomous ML research loop that does more than blindly try changes. After every training run the agent analyses what actually happened inside the model — gradients, activations, embeddings, errors, data — and grounds the next change in that evidence. A `<literature>` on/off dial adds scientific-literature grounding: off behaves as a pure analysis-first loop; on searches papers, grades the evidence, and implements only what prior work supports. One change per run; loops forever until interrupted. Not for one-off training runs or hyperparameter sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-ml-autoresearch\",\"task\":\"Install ml-autoresearch\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"gaasher-ml-autoresearch","name":"ml-autoresearch","description":"Use when the user wants an autonomous ML research loop that does more than blindly try changes. After every training run the agent analyses what actually happened inside the model — gradients, activations, embeddings, errors, data — and grounds the next change in that evidence. A `<literature>` on/off dial adds scientific-literature grounding: off behaves as a pure analysis-first loop; on searches papers, grades the evidence, and implements only what prior work supports. One change per run; loops forever until interrupted. Not for one-off training runs or hyperparameter sweeps.","category":"research","url":"https://www.openagentskill.com/skills/gaasher-ml-autoresearch","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/ml-autoresearch","github_repo":"gaasher/Agent-Loop-Skills"},"suited_tasks":["Research agents workflows","Claude Code teams","builders willing to evaluate younger projects","Search sources","Extract claims","Synthesize findings","Chunk documents","Create embeddings"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add gaasher/Agent-Loop-Skills --skill ml-autoresearch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add gaasher-ml-autoresearch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"ml-autoresearch\" agent skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/ml-autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Use when the user wants an autonomous ML research loop that does more than blindly try changes. After every training run the agent analyses what actually happened inside the model — gradients, activations, embeddings, errors, data — and grounds the next change in that evidence. A `<literature>` on/off dial adds scientific-literature grounding: off behaves as a pure analysis-first loop; on searches papers, grades the evidence, and implements only what prior work supports. One change per run; loops forever until interrupted. Not for one-off training runs or hyperparameter sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-ml-autoresearch\",\"task\":\"Install ml-autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"ml-autoresearch\" as a Claude Code skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/ml-autoresearch. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Use when the user wants an autonomous ML research loop that does more than blindly try changes. After every training run the agent analyses what actually happened inside the model — gradients, activations, embeddings, errors, data — and grounds the next change in that evidence. A `<literature>` on/off dial adds scientific-literature grounding: off behaves as a pure analysis-first loop; on searches papers, grades the evidence, and implements only what prior work supports. One change per run; loops forever until interrupted. Not for one-off training runs or hyperparameter sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-ml-autoresearch\",\"task\":\"Install ml-autoresearch\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"ml-autoresearch\" from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/ml-autoresearch into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Use when the user wants an autonomous ML research loop that does more than blindly try changes. After every training run the agent analyses what actually happened inside the model — gradients, activations, embeddings, errors, data — and grounds the next change in that evidence. A `<literature>` on/off dial adds scientific-literature grounding: off behaves as a pure analysis-first loop; on searches papers, grades the evidence, and implements only what prior work supports. One change per run; loops forever until interrupted. Not for one-off training runs or hyperparameter sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-ml-autoresearch\",\"task\":\"Install ml-autoresearch\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/gaasher-ml-autoresearch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/gaasher-ml-autoresearch"},"trust":{"score":76,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/ml-autoresearch","install":"npx skills add gaasher/Agent-Loop-Skills --skill ml-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","agent-skill"],"known_risks":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":63,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use exploratory-autoresearch","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 76/100 Strong shortlist","Audit: 78/100 Needs review","Safety: 66/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"gaasher-ml-autoresearch (ml-autoresearch)","install_command":"npx skills add gaasher/Agent-Loop-Skills --skill ml-autoresearch","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"gaasher-ml-autoresearch","task":"Use exploratory-autoresearch","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/gaasher-ml-autoresearch","api":"https://www.openagentskill.com/api/agent/skills/gaasher-ml-autoresearch","audit":"https://www.openagentskill.com/skills/gaasher-ml-autoresearch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=gaasher-ml-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20exploratory-autoresearch&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20exploratory-autoresearch&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/gaasher-ml-autoresearch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/gaasher-ml-autoresearch"}},"use_cases":[{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"}],"urls":{"web":"https://www.openagentskill.com/skills/gaasher-ml-autoresearch","api":"https://www.openagentskill.com/api/agent/skills/gaasher-ml-autoresearch","install_api":"https://www.openagentskill.com/api/skills/gaasher-ml-autoresearch/install","audit":"https://www.openagentskill.com/skills/gaasher-ml-autoresearch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=gaasher-ml-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/gaasher-ml-autoresearch?metric=audit","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/ml-autoresearch"}},"no_skill_option":{"recommended":true,"label":"Build without a third-party skill","reason":"Use a native agent workflow when the third-party permission or maintenance surface is not acceptable.","action":"Use the agent’s built-in tools for one narrow run, then reconsider a skill only if the workflow repeats."}},"selected":{"rank":1,"match_score":42,"raw_match_score":229.8,"semantic_relevance":42,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"gaasher-exploratory-autoresearch","name":"exploratory-autoresearch","description":"Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps.","category":"research","github_stars":163,"created_at":"2026-09-04T05:11:21.841977+00:00","updated_at":"2026-06-30T04:03:49+00:00","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","github_repo":"gaasher/Agent-Loop-Skills","source_version":{"version":"1.0.0","commit_sha":"f1169e6db0b0f8a83ced3a18562b7c57e14a748a","content_hash":"94f2fbf5cad3f6036dfa20764ca1f13622b620e88dc43e2bf35e9c9424149d77","ref":"main","path":"loops/exploratory-autoresearch/SKILL.md","sync_status":"current"}},"recommendation_reasons":["Matches task terms: exploratory, autoresearch","Install handoff is available","Repository freshness signal is available","Registry match score 42"],"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"Research agents","description":"I need my agent to research a topic, compare sources, and produce a concise report.","useCases":[{"slug":"research-agents","title":"Research agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"workflow-automation","title":"Workflow automation"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":163,"starsLabel":"163","forks":19,"license":"MIT","qualityScore":63,"trustScore":76,"auditScore":78},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":68,"lastPushedAt":"2026-06-30T04:03:49+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Needs review"]},"coverageTags":["Research","Research agents","agent-skill"]},"quality":{"score":63,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"163","tone":"neutral"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":76,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"163 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"info","label":"GitHub adoption","detail":"163 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","install":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":68,"base_score":76,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["68/100 Trust Score v5","76/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"163 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"info","label":"GitHub adoption","detail":"163 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","install":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["research","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","trust_score":68,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":76,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":66,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Quality score needs review","66/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Quality score needs review"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Quality score needs review","66/100 agent safety score"]},"decision":{"readiness_score":62,"readiness_label":"Prototype first","headline":"Fallback candidate for Research agents","role":"Fallback candidate","best_for":["Research agents workflows","Claude Code teams","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Research agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","value":"Install the \"exploratory-autoresearch\" agent skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review exploratory-autoresearch trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add gaasher-exploratory-autoresearch","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"exploratory-autoresearch\" agent skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"exploratory-autoresearch\" as a Claude Code skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"exploratory-autoresearch\" from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"gaasher-exploratory-autoresearch","name":"exploratory-autoresearch","description":"Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps.","category":"research","url":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","github_repo":"gaasher/Agent-Loop-Skills"},"suited_tasks":["Research agents workflows","Claude Code teams","builders willing to evaluate younger projects","Search sources","Extract claims","Synthesize findings","Chunk documents","Create embeddings"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add gaasher-exploratory-autoresearch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"exploratory-autoresearch\" agent skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"exploratory-autoresearch\" as a Claude Code skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"exploratory-autoresearch\" from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/gaasher-exploratory-autoresearch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/gaasher-exploratory-autoresearch"},"trust":{"score":76,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","install":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","agent-skill"],"known_risks":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":63,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use exploratory-autoresearch","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 76/100 Strong shortlist","Audit: 78/100 Needs review","Safety: 66/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"gaasher-exploratory-autoresearch (exploratory-autoresearch)","install_command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"gaasher-exploratory-autoresearch","task":"Use exploratory-autoresearch","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch","api":"https://www.openagentskill.com/api/agent/skills/gaasher-exploratory-autoresearch","audit":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=gaasher-exploratory-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20exploratory-autoresearch&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20exploratory-autoresearch&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/gaasher-exploratory-autoresearch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/gaasher-exploratory-autoresearch"}},"use_cases":[{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"urls":{"web":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch","api":"https://www.openagentskill.com/api/agent/skills/gaasher-exploratory-autoresearch","install_api":"https://www.openagentskill.com/api/skills/gaasher-exploratory-autoresearch/install","audit":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=gaasher-exploratory-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/gaasher-exploratory-autoresearch?metric=audit","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch"}},"alternatives":[{"rank":2,"match_score":30,"raw_match_score":219.9,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"uditgoenka-autoresearch","name":"Autoresearch","description":"Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.","category":"development","github_stars":5975,"created_at":"2026-06-16T08:45:37.929318+00:00","updated_at":"2026-08-12T22:28:18+00:00","repository":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch","github_repo":"uditgoenka/autoresearch","source_version":{"version":"2.2.2","commit_sha":"050e30dc4ba0974b03f2873111b9901ec3211390","content_hash":"c3ec24a5c90e72bfeca1f69702d5c9159c90b3c8546e94a87eead20a715e6045","ref":"master","path":".agents/skills/autoresearch/SKILL.md","sync_status":"changed"}},"recommendation_reasons":["Matches task terms: autoresearch","Useful GitHub adoption: 5,975 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"research-agents","title":"Research agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","JavaScript"],"install":{"ready":true,"command":"npx skills add uditgoenka/autoresearch","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":5975,"starsLabel":"6.0K","forks":446,"license":"MIT","qualityScore":100,"trustScore":90,"auditScore":94},"maintenance":{"status":"fresh","label":"25d since push","daysSincePush":25,"lastPushedAt":"2026-08-12T22:28:18+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Coding","Coding agents","development","claude-code","agent-skills","developer-tools","ai","autonomous-agent"]},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"6.0K","tone":"positive"},{"label":"Freshness","value":"25d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":90,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"weight":0.13,"status":"pass","detail":"6.0K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"6.0K stars, 446 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"25d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add uditgoenka/autoresearch"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"6.0K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"6.0K stars, 446 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"25d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add uditgoenka/autoresearch"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin"],"evidence":{"stars":"6.0K GitHub stars","repoActivity":"6.0K stars, 446 forks","lastPushed":"25d since push","license":"MIT","repository":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch","install":"npx skills add uditgoenka/autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add uditgoenka/autoresearch","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","25d since push"]},"agentCompatibility":["JavaScript","Claude Code","Codex","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["development","claude-code","agent-skills","developer-tools","ai","autonomous-agent"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin"]},"trust_v5":{"version":"trust-score-v5","score":87,"base_score":90,"outcome_confidence":0,"tier":"strong","label":"Review then install","summary":"Good shortlist signal, but the agent should review audit notes, install policy, and outcome evidence before running it.","recommendedAction":"Use as the primary candidate after human or sandbox review.","decision":{"install_policy":"agent_install_candidate","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Ask for approval or run a sandbox-only trial before installing.","reasoning":["87/100 Trust Score v5","90/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Low metadata risk"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"weight":0.13,"status":"pass","detail":"6.0K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"6.0K stars, 446 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"25d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add uditgoenka/autoresearch"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"6.0K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"6.0K stars, 446 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"25d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add uditgoenka/autoresearch"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Documentation summary is thin","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"6.0K GitHub stars","repoActivity":"6.0K stars, 446 forks","lastPushed":"25d since push","license":"MIT","repository":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch","install":"npx skills add uditgoenka/autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"agent_install_candidate"},"installReadiness":{"ready":true,"command":"npx skills add uditgoenka/autoresearch","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","25d since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["JavaScript","Claude Code","Codex","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Ask for approval or run a sandbox-only trial before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["development","claude-code","agent-skills","developer-tools","ai","autonomous-agent"],"suited_agents":["JavaScript","Claude Code","Codex","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add uditgoenka/autoresearch","trust_score":87,"trust_version":"trust-score-v5","risk_level":"low","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["development","claude-code","agent-skills","developer-tools","ai","autonomous-agent"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":90,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":94,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety":{"score":82,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","82/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","82/100 agent safety score"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Coding agents","role":"Primary pick","best_for":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add uditgoenka/autoresearch","value":"Install the \"Autoresearch\" agent skill from https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"uditgoenka-autoresearch\",\"task\":\"Install Autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review Autoresearch trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add uditgoenka-autoresearch","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Autoresearch\" agent skill from https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"uditgoenka-autoresearch\",\"task\":\"Install Autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Autoresearch\" as a Claude Code skill from https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"uditgoenka-autoresearch\",\"task\":\"Install Autoresearch\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Autoresearch\" from https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"uditgoenka-autoresearch\",\"task\":\"Install Autoresearch\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"uditgoenka-autoresearch","name":"Autoresearch","description":"Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.","category":"development","url":"https://www.openagentskill.com/skills/uditgoenka-autoresearch","repository":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch","github_repo":"uditgoenka/autoresearch"},"suited_tasks":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Search sources","Extract claims"],"suited_agents":["JavaScript","Claude Code","Codex","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add uditgoenka/autoresearch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add uditgoenka-autoresearch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Autoresearch\" agent skill from https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"uditgoenka-autoresearch\",\"task\":\"Install Autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Autoresearch\" as a Claude Code skill from https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"uditgoenka-autoresearch\",\"task\":\"Install Autoresearch\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Autoresearch\" from https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"uditgoenka-autoresearch\",\"task\":\"Install Autoresearch\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/uditgoenka-autoresearch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/uditgoenka-autoresearch"},"trust":{"score":90,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"6.0K GitHub stars","repoActivity":"6.0K stars, 446 forks","lastPushed":"25d since push","license":"MIT","repository":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch","install":"npx skills add uditgoenka/autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["development","claude-code","agent-skills","developer-tools","ai","autonomous-agent"],"known_risks":["Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":94,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"25d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use exploratory-autoresearch","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 90/100 Production candidate","Audit: 94/100 Safe to try","Safety: 82/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"uditgoenka-autoresearch (Autoresearch)","install_command":"npx skills add uditgoenka/autoresearch","risk_summary":"Safe to try; Reviewed; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"uditgoenka-autoresearch","task":"Use exploratory-autoresearch","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/uditgoenka-autoresearch","api":"https://www.openagentskill.com/api/agent/skills/uditgoenka-autoresearch","audit":"https://www.openagentskill.com/skills/uditgoenka-autoresearch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=uditgoenka-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20exploratory-autoresearch&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20exploratory-autoresearch&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/uditgoenka-autoresearch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/uditgoenka-autoresearch"}},"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"}],"urls":{"web":"https://www.openagentskill.com/skills/uditgoenka-autoresearch","api":"https://www.openagentskill.com/api/agent/skills/uditgoenka-autoresearch","install_api":"https://www.openagentskill.com/api/skills/uditgoenka-autoresearch/install","audit":"https://www.openagentskill.com/skills/uditgoenka-autoresearch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=uditgoenka-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/uditgoenka-autoresearch?metric=audit","repository":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch"}},{"rank":3,"match_score":30,"raw_match_score":217.3,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"alvinreal-awesome-autoresearch","name":"Awesome Autoresearch","description":"A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch.","category":"agent-frameworks","github_stars":2478,"created_at":"2026-05-24T11:00:46.890181+00:00","updated_at":"2026-08-10T11:34:18+00:00","repository":"https://github.com/alvinreal/awesome-autoresearch","github_repo":"alvinreal/awesome-autoresearch","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"recommendation_reasons":["Matches task terms: autoresearch","Useful GitHub adoption: 2,478 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"research-agents","title":"Research agents"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","AI Agents"],"install":{"ready":true,"command":"npx skills add alvinreal/awesome-autoresearch","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":2478,"starsLabel":"2.5K","forks":186,"license":"Unknown","qualityScore":94,"trustScore":85,"auditScore":90},"maintenance":{"status":"fresh","label":"27d since push","daysSincePush":27,"lastPushedAt":"2026-08-10T11:34:18+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"coverageTags":["Coding","Coding agents","agent-frameworks","agents","ai-agents","agentic-systems","ai-research","ai-tools"]},"quality":{"score":94,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"2.5K","tone":"positive"},{"label":"Freshness","value":"27d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":85,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"2.5K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":77,"weight":0.08,"status":"info","detail":"2.5K stars, 186 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"27d since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add alvinreal/awesome-autoresearch"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/alvinreal/awesome-autoresearch"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"2.5K GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"2.5K stars, 186 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"27d since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add alvinreal/awesome-autoresearch"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/alvinreal/awesome-autoresearch"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"pass","label":"OpenAgentSkill usage","detail":"9 views, 0 install copies"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown"],"evidence":{"stars":"2.5K GitHub stars","repoActivity":"2.5K stars, 186 forks","lastPushed":"27d since push","license":"Unknown","repository":"https://github.com/alvinreal/awesome-autoresearch","install":"npx skills add alvinreal/awesome-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add alvinreal/awesome-autoresearch","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","No Agent Proven outcome evidence yet","27d since push"]},"agentCompatibility":["AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["agent-frameworks","agents","ai-agents","agentic-systems","ai-research","ai-tools"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"trust_v5":{"version":"trust-score-v5","score":77,"base_score":85,"outcome_confidence":0,"tier":"strong","label":"Review then install","summary":"Good shortlist signal, but the agent should review audit notes, install policy, and outcome evidence before running it.","recommendedAction":"Use as the primary candidate after human or sandbox review.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Ask for approval or run a sandbox-only trial before installing.","reasoning":["77/100 Trust Score v5","85/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"2.5K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":77,"weight":0.08,"status":"info","detail":"2.5K stars, 186 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"27d since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add alvinreal/awesome-autoresearch"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/alvinreal/awesome-autoresearch"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"2.5K GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"2.5K stars, 186 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"27d since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add alvinreal/awesome-autoresearch"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/alvinreal/awesome-autoresearch"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"pass","label":"OpenAgentSkill usage","detail":"9 views, 0 install copies"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"2.5K GitHub stars","repoActivity":"2.5K stars, 186 forks","lastPushed":"27d since push","license":"Unknown","repository":"https://github.com/alvinreal/awesome-autoresearch","install":"npx skills add alvinreal/awesome-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add alvinreal/awesome-autoresearch","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","No Agent Proven outcome evidence yet","27d since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Ask for approval or run a sandbox-only trial before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["agent-frameworks","agents","ai-agents","agentic-systems","ai-research","ai-tools"],"suited_agents":["AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add alvinreal/awesome-autoresearch","trust_score":77,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["agent-frameworks","agents","ai-agents","agentic-systems","ai-research","ai-tools"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","Documentation summary is thin","License clarity: Unknown"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":85,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":90,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"safety":{"score":78,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","78/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["License is unclear"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","78/100 agent safety score"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Research agents","role":"Primary pick","best_for":["Research agents workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No major risk signals from current metadata"],"next_steps":["Install it in a sandbox agent and run one Research agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add alvinreal/awesome-autoresearch","value":"Install the \"Awesome Autoresearch\" agent skill from https://github.com/alvinreal/awesome-autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alvinreal-awesome-autoresearch\",\"task\":\"Install Awesome Autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review Awesome Autoresearch trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add alvinreal-awesome-autoresearch","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Awesome Autoresearch\" agent skill from https://github.com/alvinreal/awesome-autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alvinreal-awesome-autoresearch\",\"task\":\"Install Awesome Autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Awesome Autoresearch\" as a Claude Code skill from https://github.com/alvinreal/awesome-autoresearch. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alvinreal-awesome-autoresearch\",\"task\":\"Install Awesome Autoresearch\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Awesome Autoresearch\" from https://github.com/alvinreal/awesome-autoresearch into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alvinreal-awesome-autoresearch\",\"task\":\"Install Awesome Autoresearch\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"alvinreal-awesome-autoresearch","name":"Awesome Autoresearch","description":"A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch.","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/alvinreal-awesome-autoresearch","repository":"https://github.com/alvinreal/awesome-autoresearch","github_repo":"alvinreal/awesome-autoresearch"},"suited_tasks":["Research agents workflows","Claude Code teams","teams that value GitHub adoption signals","Search sources","Extract claims","Synthesize findings","Inspect source files","Explain architecture"],"suited_agents":["AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add alvinreal/awesome-autoresearch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add alvinreal-awesome-autoresearch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Awesome Autoresearch\" agent skill from https://github.com/alvinreal/awesome-autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alvinreal-awesome-autoresearch\",\"task\":\"Install Awesome Autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Awesome Autoresearch\" as a Claude Code skill from https://github.com/alvinreal/awesome-autoresearch. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alvinreal-awesome-autoresearch\",\"task\":\"Install Awesome Autoresearch\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Awesome Autoresearch\" from https://github.com/alvinreal/awesome-autoresearch into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A curated list of autonomous improvement loops, research agents, and autoresearch-style systems inspired by Karpathy's autoresearch. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alvinreal-awesome-autoresearch\",\"task\":\"Install Awesome Autoresearch\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/alvinreal-awesome-autoresearch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/alvinreal-awesome-autoresearch"},"trust":{"score":85,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"2.5K GitHub stars","repoActivity":"2.5K stars, 186 forks","lastPushed":"27d since push","license":"Unknown","repository":"https://github.com/alvinreal/awesome-autoresearch","install":"npx skills add alvinreal/awesome-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["agent-frameworks","agents","ai-agents","agentic-systems","ai-research","ai-tools"],"known_risks":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":90,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":94,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"27d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No major risk signals from current metadata","License is unclear","Documentation summary is thin","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use exploratory-autoresearch","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 85/100 Strong shortlist","Audit: 90/100 Safe to try","Safety: 78/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"alvinreal-awesome-autoresearch (Awesome Autoresearch)","install_command":"npx skills add alvinreal/awesome-autoresearch","risk_summary":"Safe to try; Reviewed; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"alvinreal-awesome-autoresearch","task":"Use exploratory-autoresearch","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/alvinreal-awesome-autoresearch","api":"https://www.openagentskill.com/api/agent/skills/alvinreal-awesome-autoresearch","audit":"https://www.openagentskill.com/skills/alvinreal-awesome-autoresearch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=alvinreal-awesome-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20exploratory-autoresearch&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20exploratory-autoresearch&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/alvinreal-awesome-autoresearch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/alvinreal-awesome-autoresearch"}},"use_cases":[{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"}],"urls":{"web":"https://www.openagentskill.com/skills/alvinreal-awesome-autoresearch","api":"https://www.openagentskill.com/api/agent/skills/alvinreal-awesome-autoresearch","install_api":"https://www.openagentskill.com/api/skills/alvinreal-awesome-autoresearch/install","audit":"https://www.openagentskill.com/skills/alvinreal-awesome-autoresearch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=alvinreal-awesome-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/alvinreal-awesome-autoresearch?metric=audit","repository":"https://github.com/alvinreal/awesome-autoresearch"}},{"rank":4,"match_score":30,"raw_match_score":215.9,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"leo-lilinxiao-codex-autoresearch","name":"Codex Autoresearch","description":"Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify, retain or discard, and repeat indefinitely. Inspired by Karpathy’s autoresearch concept.","category":"automation","github_stars":1985,"created_at":"2026-07-08T13:21:29.747295+00:00","updated_at":"2026-07-13T13:53:30+00:00","repository":"https://github.com/leo-lilinxiao/codex-autoresearch","github_repo":"leo-lilinxiao/codex-autoresearch","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"recommendation_reasons":["Matches task terms: autoresearch","Useful GitHub adoption: 1,985 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"Research agents","description":"I need my agent to research a topic, compare sources, and produce a concise report.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"research-agents","title":"Research agents"},{"slug":"workflow-automation","title":"Workflow automation"}]},"applicableAgents":["Claude Code","OpenAI Agents","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add leo-lilinxiao/codex-autoresearch","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":1985,"starsLabel":"2.0K","forks":115,"license":"MIT","qualityScore":92,"trustScore":84,"auditScore":88},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":55,"lastPushedAt":"2026-07-13T13:53:30+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Research","Research agents","automation","workflow","autonomous-agent","autoresearch","codex","codex-cli"]},"quality":{"score":92,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"2.0K","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":84,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"2.0K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":77,"weight":0.08,"status":"info","detail":"2.0K stars, 115 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"command execution surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add leo-lilinxiao/codex-autoresearch"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":76,"weight":0.07,"status":"info","detail":"shell or command execution"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/leo-lilinxiao/codex-autoresearch"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"2.0K GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"2.0K stars, 115 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface"},{"status":"pass","label":"Install availability","detail":"npx skills add leo-lilinxiao/codex-autoresearch"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"shell or command execution"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/leo-lilinxiao/codex-autoresearch"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin"],"evidence":{"stars":"2.0K GitHub stars","repoActivity":"2.0K stars, 115 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/leo-lilinxiao/codex-autoresearch","install":"npx skills add leo-lilinxiao/codex-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add leo-lilinxiao/codex-autoresearch","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Python","Automation","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["automation","workflow","autonomous-agent","autoresearch","codex","codex-cli"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Documentation summary is thin"]},"trust_v5":{"version":"trust-score-v5","score":79,"base_score":84,"outcome_confidence":0,"tier":"strong","label":"Review then install","summary":"Good shortlist signal, but the agent should review audit notes, install policy, and outcome evidence before running it.","recommendedAction":"Use as the primary candidate after human or sandbox review.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Ask for approval or run a sandbox-only trial before installing.","reasoning":["79/100 Trust Score v5","84/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Low metadata risk"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"2.0K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":77,"weight":0.08,"status":"info","detail":"2.0K stars, 115 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"command execution surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add leo-lilinxiao/codex-autoresearch"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":76,"weight":0.07,"status":"info","detail":"shell or command execution"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/leo-lilinxiao/codex-autoresearch"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"2.0K GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"2.0K stars, 115 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface"},{"status":"pass","label":"Install availability","detail":"npx skills add leo-lilinxiao/codex-autoresearch"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"shell or command execution"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/leo-lilinxiao/codex-autoresearch"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Documentation summary is thin","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"2.0K GitHub stars","repoActivity":"2.0K stars, 115 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/leo-lilinxiao/codex-autoresearch","install":"npx skills add leo-lilinxiao/codex-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add leo-lilinxiao/codex-autoresearch","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Python","Automation","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Ask for approval or run a sandbox-only trial before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["automation","workflow","autonomous-agent","autoresearch","codex","codex-cli"],"suited_agents":["Python","Automation","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add leo-lilinxiao/codex-autoresearch","trust_score":79,"trust_version":"trust-score-v5","risk_level":"low","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["automation","workflow","autonomous-agent","autoresearch","codex","codex-cli"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Documentation summary is thin"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":84,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":88,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety":{"score":64,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["High-risk permission hints: Shell or command execution","64/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"shell","label":"Shell or command execution","reason":"Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.","severity":"high"},{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["High-risk permission hints: Shell or command execution","Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["High-risk permission hints: Shell or command execution","64/100 agent safety score"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Coding agents","role":"Primary pick","best_for":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add leo-lilinxiao/codex-autoresearch","value":"Install the \"Codex Autoresearch\" agent skill from https://github.com/leo-lilinxiao/codex-autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify, retain or discard, and repeat indefinitely. Inspired by Karpathy’s autoresearch concept. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"leo-lilinxiao-codex-autoresearch\",\"task\":\"Install Codex Autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review Codex Autoresearch trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add leo-lilinxiao-codex-autoresearch","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Codex Autoresearch\" agent skill from https://github.com/leo-lilinxiao/codex-autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify, retain or discard, and repeat indefinitely. Inspired by Karpathy’s autoresearch concept. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"leo-lilinxiao-codex-autoresearch\",\"task\":\"Install Codex Autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Codex Autoresearch\" as a Claude Code skill from https://github.com/leo-lilinxiao/codex-autoresearch. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify, retain or discard, and repeat indefinitely. Inspired by Karpathy’s autoresearch concept. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"leo-lilinxiao-codex-autoresearch\",\"task\":\"Install Codex Autoresearch\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Codex Autoresearch\" from https://github.com/leo-lilinxiao/codex-autoresearch into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify, retain or discard, and repeat indefinitely. Inspired by Karpathy’s autoresearch concept. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"leo-lilinxiao-codex-autoresearch\",\"task\":\"Install Codex Autoresearch\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"leo-lilinxiao-codex-autoresearch","name":"Codex Autoresearch","description":"Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify, retain or discard, and repeat indefinitely. Inspired by Karpathy’s autoresearch concept.","category":"automation","url":"https://www.openagentskill.com/skills/leo-lilinxiao-codex-autoresearch","repository":"https://github.com/leo-lilinxiao/codex-autoresearch","github_repo":"leo-lilinxiao/codex-autoresearch"},"suited_tasks":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Search sources","Extract claims"],"suited_agents":["Python","Automation","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add leo-lilinxiao/codex-autoresearch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add leo-lilinxiao-codex-autoresearch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Codex Autoresearch\" agent skill from https://github.com/leo-lilinxiao/codex-autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify, retain or discard, and repeat indefinitely. Inspired by Karpathy’s autoresearch concept. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"leo-lilinxiao-codex-autoresearch\",\"task\":\"Install Codex Autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Codex Autoresearch\" as a Claude Code skill from https://github.com/leo-lilinxiao/codex-autoresearch. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify, retain or discard, and repeat indefinitely. Inspired by Karpathy’s autoresearch concept. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"leo-lilinxiao-codex-autoresearch\",\"task\":\"Install Codex Autoresearch\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Codex Autoresearch\" from https://github.com/leo-lilinxiao/codex-autoresearch into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify, retain or discard, and repeat indefinitely. Inspired by Karpathy’s autoresearch concept. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"leo-lilinxiao-codex-autoresearch\",\"task\":\"Install Codex Autoresearch\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/leo-lilinxiao-codex-autoresearch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/leo-lilinxiao-codex-autoresearch"},"trust":{"score":84,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"2.0K GitHub stars","repoActivity":"2.0K stars, 115 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/leo-lilinxiao/codex-autoresearch","install":"npx skills add leo-lilinxiao/codex-autoresearch","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["automation","workflow","autonomous-agent","autoresearch","codex","codex-cli"],"known_risks":["Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":88,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":92,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use exploratory-autoresearch","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 84/100 Strong shortlist","Audit: 88/100 Safe to try","Safety: 64/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"leo-lilinxiao-codex-autoresearch (Codex Autoresearch)","install_command":"npx skills add leo-lilinxiao/codex-autoresearch","risk_summary":"Safe to try; Reviewed with permission notes; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"leo-lilinxiao-codex-autoresearch","task":"Use exploratory-autoresearch","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/leo-lilinxiao-codex-autoresearch","api":"https://www.openagentskill.com/api/agent/skills/leo-lilinxiao-codex-autoresearch","audit":"https://www.openagentskill.com/skills/leo-lilinxiao-codex-autoresearch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=leo-lilinxiao-codex-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20exploratory-autoresearch&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20exploratory-autoresearch&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/leo-lilinxiao-codex-autoresearch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/leo-lilinxiao-codex-autoresearch"}},"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"urls":{"web":"https://www.openagentskill.com/skills/leo-lilinxiao-codex-autoresearch","api":"https://www.openagentskill.com/api/agent/skills/leo-lilinxiao-codex-autoresearch","install_api":"https://www.openagentskill.com/api/skills/leo-lilinxiao-codex-autoresearch/install","audit":"https://www.openagentskill.com/skills/leo-lilinxiao-codex-autoresearch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=leo-lilinxiao-codex-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/leo-lilinxiao-codex-autoresearch?metric=audit","repository":"https://github.com/leo-lilinxiao/codex-autoresearch"}},{"rank":5,"match_score":30,"raw_match_score":180.8,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"rlaope-omh-autoresearch-goal","name":"omh-autoresearch-goal","description":"[omh] Hermes adaptation for durable research-goal execution. Use when the user says: autoresearch-goal, research goal, durable research, critic research.","category":"research","github_stars":1309,"created_at":"2026-09-02T07:32:49.356373+00:00","updated_at":"2026-09-02T07:27:36+00:00","repository":"https://github.com/rlaope/oh-my-hermes/tree/main/skills/omh-autoresearch-goal","github_repo":"rlaope/oh-my-hermes","source_version":{"version":"1.0.0","commit_sha":"1a1f9e0c76845473a5cde15c95b50ddb191684d9","content_hash":"56a99d5ae03868f1887a226ff995f578775b328cf47e81360ac9b115b419a59b","ref":"main","path":"skills/omh-autoresearch-goal/SKILL.md","sync_status":"current"}},"recommendation_reasons":["Matches task terms: autoresearch","Useful GitHub adoption: 1,309 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"Research agents","description":"I need my agent to research a topic, compare sources, and produce a concise report.","useCases":[{"slug":"research-agents","title":"Research agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"web-scraping","title":"Web scraping"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add rlaope/oh-my-hermes --skill omh-autoresearch-goal","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":1309,"starsLabel":"1.3K","forks":125,"license":"MIT","qualityScore":72,"trustScore":82,"auditScore":84},"maintenance":{"status":"fresh","label":"4d since push","daysSincePush":4,"lastPushedAt":"2026-09-02T07:27:36+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"coverageTags":["Research","Research agents","agent-skill"]},"quality":{"score":72,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"1.3K","tone":"positive"},{"label":"Freshness","value":"4d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":82,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"1.3K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":77,"weight":0.08,"status":"info","detail":"1.3K stars, 125 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"4d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add rlaope/oh-my-hermes --skill omh-autoresearch-goal"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/rlaope/oh-my-hermes/tree/main/skills/omh-autoresearch-goal"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"1.3K GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"1.3K stars, 125 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"4d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add rlaope/oh-my-hermes --skill omh-autoresearch-goal"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/rlaope/oh-my-hermes/tree/main/skills/omh-autoresearch-goal"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"1.3K GitHub stars","repoActivity":"1.3K stars, 125 forks","lastPushed":"4d since push","license":"MIT","repository":"https://github.com/rlaope/oh-my-hermes/tree/main/skills/omh-autoresearch-goal","install":"npx skills add rlaope/oh-my-hermes --skill omh-autoresearch-goal","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add rlaope/oh-my-hermes --skill omh-autoresearch-goal","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","4d since push"]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":74,"base_score":82,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["74/100 Trust Score v5","82/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"1.3K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":77,"weight":0.08,"status":"info","detail":"1.3K stars, 125 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"4d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add rlaope/oh-my-hermes --skill omh-autoresearch-goal"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/rlaope/oh-my-hermes/tree/main/skills/omh-autoresearch-goal"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"1.3K GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"1.3K stars, 125 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"4d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add rlaope/oh-my-hermes --skill omh-autoresearch-goal"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/rlaope/oh-my-hermes/tree/main/skills/omh-autoresearch-goal"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"1.3K GitHub stars","repoActivity":"1.3K stars, 125 forks","lastPushed":"4d since push","license":"MIT","repository":"https://github.com/rlaope/oh-my-hermes/tree/main/skills/omh-autoresearch-goal","install":"npx skills add rlaope/oh-my-hermes --skill omh-autoresearch-goal","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add rlaope/oh-my-hermes --skill omh-autoresearch-goal","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","4d since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["research","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add rlaope/oh-my-hermes --skill omh-autoresearch-goal","trust_score":74,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["research","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":82,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":84,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":72,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","72/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Quality score needs review"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","72/100 agent safety score"]},"decision":{"readiness_score":83,"readiness_label":"Strong shortlist","headline":"Companion skill for Research agents","role":"Companion skill","best_for":["Research agents workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Research agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add rlaope/oh-my-hermes --skill omh-autoresearch-goal","value":"Install the \"omh-autoresearch-goal\" agent skill from https://github.com/rlaope/oh-my-hermes/tree/main/skills/omh-autoresearch-goal. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: [omh] Hermes adaptation for durable research-goal execution. Use when the user says: autoresearch-goal, research goal, durable research, critic research. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"rlaope-omh-autoresearch-goal\",\"task\":\"Install omh-autoresearch-goal\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review omh-autoresearch-goal trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add rlaope-omh-autoresearch-goal","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"omh-autoresearch-goal\" agent skill from https://github.com/rlaope/oh-my-hermes/tree/main/skills/omh-autoresearch-goal. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: [omh] Hermes adaptation for durable research-goal execution. Use when the user says: autoresearch-goal, research goal, durable research, critic research. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"rlaope-omh-autoresearch-goal\",\"task\":\"Install omh-autoresearch-goal\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"omh-autoresearch-goal\" as a Claude Code skill from https://github.com/rlaope/oh-my-hermes/tree/main/skills/omh-autoresearch-goal. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: [omh] Hermes adaptation for durable research-goal execution. Use when the user says: autoresearch-goal, research goal, durable research, critic research. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"rlaope-omh-autoresearch-goal\",\"task\":\"Install omh-autoresearch-goal\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"omh-autoresearch-goal\" from https://github.com/rlaope/oh-my-hermes/tree/main/skills/omh-autoresearch-goal into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: [omh] Hermes adaptation for durable research-goal execution. Use when the user says: autoresearch-goal, research goal, durable research, critic research. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"rlaope-omh-autoresearch-goal\",\"task\":\"Install omh-autoresearch-goal\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"rlaope-omh-autoresearch-goal","name":"omh-autoresearch-goal","description":"[omh] Hermes adaptation for durable research-goal execution. Use when the user says: autoresearch-goal, research goal, durable research, critic research.","category":"research","url":"https://www.openagentskill.com/skills/rlaope-omh-autoresearch-goal","repository":"https://github.com/rlaope/oh-my-hermes/tree/main/skills/omh-autoresearch-goal","github_repo":"rlaope/oh-my-hermes"},"suited_tasks":["Research agents workflows","Claude Code teams","teams that value GitHub adoption signals","Search sources","Extract claims","Synthesize findings","Chunk documents","Create embeddings"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add rlaope/oh-my-hermes --skill omh-autoresearch-goal","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add rlaope-omh-autoresearch-goal"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"omh-autoresearch-goal\" agent skill from https://github.com/rlaope/oh-my-hermes/tree/main/skills/omh-autoresearch-goal. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: [omh] Hermes adaptation for durable research-goal execution. Use when the user says: autoresearch-goal, research goal, durable research, critic research. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"rlaope-omh-autoresearch-goal\",\"task\":\"Install omh-autoresearch-goal\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"omh-autoresearch-goal\" as a Claude Code skill from https://github.com/rlaope/oh-my-hermes/tree/main/skills/omh-autoresearch-goal. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: [omh] Hermes adaptation for durable research-goal execution. Use when the user says: autoresearch-goal, research goal, durable research, critic research. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"rlaope-omh-autoresearch-goal\",\"task\":\"Install omh-autoresearch-goal\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"omh-autoresearch-goal\" from https://github.com/rlaope/oh-my-hermes/tree/main/skills/omh-autoresearch-goal into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: [omh] Hermes adaptation for durable research-goal execution. Use when the user says: autoresearch-goal, research goal, durable research, critic research. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"rlaope-omh-autoresearch-goal\",\"task\":\"Install omh-autoresearch-goal\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/rlaope-omh-autoresearch-goal/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/rlaope-omh-autoresearch-goal"},"trust":{"score":82,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"1.3K GitHub stars","repoActivity":"1.3K stars, 125 forks","lastPushed":"4d since push","license":"MIT","repository":"https://github.com/rlaope/oh-my-hermes/tree/main/skills/omh-autoresearch-goal","install":"npx skills add rlaope/oh-my-hermes --skill omh-autoresearch-goal","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","agent-skill"],"known_risks":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":84,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":72,"label":"Strong"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"4d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use exploratory-autoresearch","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 82/100 Strong shortlist","Audit: 84/100 Safe to try","Safety: 72/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"rlaope-omh-autoresearch-goal (omh-autoresearch-goal)","install_command":"npx skills add rlaope/oh-my-hermes --skill omh-autoresearch-goal","risk_summary":"Safe to try; Reviewed; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"rlaope-omh-autoresearch-goal","task":"Use exploratory-autoresearch","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/rlaope-omh-autoresearch-goal","api":"https://www.openagentskill.com/api/agent/skills/rlaope-omh-autoresearch-goal","audit":"https://www.openagentskill.com/skills/rlaope-omh-autoresearch-goal/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=rlaope-omh-autoresearch-goal&task=Use%20exploratory-autoresearch&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20exploratory-autoresearch&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20exploratory-autoresearch&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/rlaope-omh-autoresearch-goal/install","manifest":"https://www.openagentskill.com/api/registry/manifest/rlaope-omh-autoresearch-goal"}},"use_cases":[{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"}],"urls":{"web":"https://www.openagentskill.com/skills/rlaope-omh-autoresearch-goal","api":"https://www.openagentskill.com/api/agent/skills/rlaope-omh-autoresearch-goal","install_api":"https://www.openagentskill.com/api/skills/rlaope-omh-autoresearch-goal/install","audit":"https://www.openagentskill.com/skills/rlaope-omh-autoresearch-goal/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=rlaope-omh-autoresearch-goal&task=Use%20exploratory-autoresearch&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/rlaope-omh-autoresearch-goal?metric=audit","repository":"https://github.com/rlaope/oh-my-hermes/tree/main/skills/omh-autoresearch-goal"}}],"blocked_candidates":[],"agent_workflow":{"mode":"resolve_review_install","recommended_action":"Require human approval before installing into a real workspace.","selected_skill":{"slug":"gaasher-exploratory-autoresearch","name":"exploratory-autoresearch","url":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch"},"install":{"target":"codex","label":"Codex install prompt","kind":"agent-prompt","command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","value":"Install the \"exploratory-autoresearch\" agent skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","api":"https://www.openagentskill.com/api/skills/gaasher-exploratory-autoresearch/install"},"copy_paste_prompt":"Task: Use exploratory-autoresearch\nUse exploratory-autoresearch from https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch.\nReview the audit first: https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch/audit\nReview the eval first: https://www.openagentskill.com/api/agent/evals?slug=gaasher-exploratory-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/gaasher-exploratory-autoresearch/install\nInstall command: npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch\nIf audit or policy warnings look unsafe for this workspace, use one of the alternatives instead.","api_sequence":[{"step":1,"label":"Resolve task","method":"GET","url":"https://www.openagentskill.com/api/agent/resolve?task=Use%20exploratory-autoresearch&agent=codex&max_risk=medium"},{"step":2,"label":"Fetch pre-install eval","method":"GET","url":"https://www.openagentskill.com/api/agent/evals?slug=gaasher-exploratory-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium"},{"step":3,"label":"Fetch selected skill profile","method":"GET","url":"https://www.openagentskill.com/api/agent/skills/gaasher-exploratory-autoresearch"},{"step":4,"label":"Fetch install handoff","method":"GET","url":"https://www.openagentskill.com/api/skills/gaasher-exploratory-autoresearch/install"},{"step":5,"label":"Review audit","method":"GET","url":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch/audit"},{"step":6,"label":"Report outcome","method":"POST","url":"https://www.openagentskill.com/api/agent/outcome","body":{"event_id":"resolve_4cb6fd18-b126-4411-8624-ece5adc79777","skill_slug":"gaasher-exploratory-autoresearch","task":"Use exploratory-autoresearch","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":"f1169e6db0b0f8a83ced3a18562b7c57e14a748a","content_hash":"94f2fbf5cad3f6036dfa20764ca1f13622b620e88dc43e2bf35e9c9424149d77","ref":"main","path":"loops/exploratory-autoresearch/SKILL.md","sync_status":"current"}}}],"review_checklist":["Safety tier: Reviewed with permission notes","Safety score: 66/100 Review before install","Audit score: 78/100 Needs review","Trust score: 68/100 Sandbox only","Readiness: 62/100 Prototype first","Quality score needs review","Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"fallback_strategy":[{"slug":"uditgoenka-autoresearch","name":"Autoresearch","reason":"Matches task terms: autoresearch","url":"https://www.openagentskill.com/skills/uditgoenka-autoresearch","install_api":"https://www.openagentskill.com/api/skills/uditgoenka-autoresearch/install"},{"slug":"alvinreal-awesome-autoresearch","name":"Awesome Autoresearch","reason":"Matches task terms: autoresearch","url":"https://www.openagentskill.com/skills/alvinreal-awesome-autoresearch","install_api":"https://www.openagentskill.com/api/skills/alvinreal-awesome-autoresearch/install"},{"slug":"leo-lilinxiao-codex-autoresearch","name":"Codex Autoresearch","reason":"Matches task terms: autoresearch","url":"https://www.openagentskill.com/skills/leo-lilinxiao-codex-autoresearch","install_api":"https://www.openagentskill.com/api/skills/leo-lilinxiao-codex-autoresearch/install"}],"expected_agent_output":{"selected_skill":"slug and name","install_command":"command or agent prompt used","risk_summary":"audit, trust, and policy notes","next_step":"what the agent will do after install","outcome_event_id":"resolve_4cb6fd18-b126-4411-8624-ece5adc79777"}},"agent_handoff":{"version":"openagentskill-agent-handoff-v1","mode":"resolve_compare_review_install","task":"Use exploratory-autoresearch","agent":"codex","selected_skill":{"slug":"gaasher-exploratory-autoresearch","name":"exploratory-autoresearch","url":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch","api_url":"https://www.openagentskill.com/api/agent/skills/gaasher-exploratory-autoresearch","audit_url":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=gaasher-exploratory-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch"},"install_plan":{"command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","target":"codex","label":"Codex install prompt","kind":"agent-prompt","value":"Install the \"exploratory-autoresearch\" agent skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Use when the user wants an autonomous ML research loop that explores the space broadly rather than hill-climbing one approach. A temperature scheduler replaces the usual hypothesis step: it forces several wild, diverse swings (full rewrites, different architectures/regimes) early, then enters an adaptive phase that picks swing / merge / exploit per iteration — with a hard stagnation guard that bans further small-step exploits once they run too long, forcing a pivot back to a swing or merge. Tracks an approaches.md registry and a move_type per iteration; analyses every run before the next move. One change per iteration; loops forever until interrupted. Not for the standard analysis-first ml-autoresearch (which lets analysis alone choose each change), one-off training runs, or sweeps. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-exploratory-autoresearch\",\"task\":\"Install exploratory-autoresearch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","install_api":"https://www.openagentskill.com/api/skills/gaasher-exploratory-autoresearch/install","auto_install_allowed":false,"human_review_required":true,"policy":"review"},"api_sequence":[{"step":1,"label":"Resolve task","method":"GET","url":"https://www.openagentskill.com/api/agent/resolve?task=Use%20exploratory-autoresearch&agent=codex&max_risk=medium"},{"step":2,"label":"Fetch pre-install eval","method":"GET","url":"https://www.openagentskill.com/api/agent/evals?slug=gaasher-exploratory-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium"},{"step":3,"label":"Fetch selected skill profile","method":"GET","url":"https://www.openagentskill.com/api/agent/skills/gaasher-exploratory-autoresearch"},{"step":4,"label":"Fetch install handoff","method":"GET","url":"https://www.openagentskill.com/api/skills/gaasher-exploratory-autoresearch/install"},{"step":5,"label":"Review audit","method":"GET","url":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch/audit"},{"step":6,"label":"Report outcome","method":"POST","url":"https://www.openagentskill.com/api/agent/outcome","body":{"event_id":"resolve_4cb6fd18-b126-4411-8624-ece5adc79777","skill_slug":"gaasher-exploratory-autoresearch","task":"Use exploratory-autoresearch","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":"f1169e6db0b0f8a83ced3a18562b7c57e14a748a","content_hash":"94f2fbf5cad3f6036dfa20764ca1f13622b620e88dc43e2bf35e9c9424149d77","ref":"main","path":"loops/exploratory-autoresearch/SKILL.md","sync_status":"current"}}}],"platform_templates":[{"id":"codex","name":"Codex","surface":"Coding agent / local workspace","copy_prompt":"Task: Use exploratory-autoresearch\nSelected skill: exploratory-autoresearch (gaasher-exploratory-autoresearch)\nSkill URL: https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch\nAudit URL: https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch/audit\nEval URL: https://www.openagentskill.com/api/agent/evals?slug=gaasher-exploratory-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/gaasher-exploratory-autoresearch/install\nInstall command: npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch\nInstall policy: Human review is required before install.\nOutcome feedback: use install_receipt.outcome_feedback.event_id or feedback.event_id from the Resolve API and report the result to /api/agent/outcome after one narrow run. Include outcome, install_used, task_success, output_quality, workspace, error_type, and human_review_required when known.\n\nBefore installing:\n1. Read the audit and eval result.\n2. Report risk notes and files or commands that will be touched.\n3. Install only in a sandbox or low-risk workspace first.\n4. If risk is unacceptable, use an alternative.\n\nAlternatives:\n- Autoresearch (uditgoenka-autoresearch): https://www.openagentskill.com/skills/uditgoenka-autoresearch\n- Awesome Autoresearch (alvinreal-awesome-autoresearch): https://www.openagentskill.com/skills/alvinreal-awesome-autoresearch\n- Codex Autoresearch (leo-lilinxiao-codex-autoresearch): https://www.openagentskill.com/skills/leo-lilinxiao-codex-autoresearch\n\nExpected Codex output:\n- selected_skill\n- install_command\n- risk_summary\n- outcome_event_id\n- alternatives\n- files_or_commands_to_touch\n- next_action"},{"id":"claude-code","name":"Claude Code","surface":"Claude Code skill workflow","copy_prompt":"Task: Use exploratory-autoresearch\nSelected skill: exploratory-autoresearch (gaasher-exploratory-autoresearch)\nSkill URL: https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch\nAudit URL: https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch/audit\nEval URL: https://www.openagentskill.com/api/agent/evals?slug=gaasher-exploratory-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/gaasher-exploratory-autoresearch/install\nInstall command: npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch\nInstall policy: Human review is required before install.\nOutcome feedback: use install_receipt.outcome_feedback.event_id or feedback.event_id from the Resolve API and report the result to /api/agent/outcome after one narrow run. Include outcome, install_used, task_success, output_quality, workspace, error_type, and human_review_required when known.\n\nBefore installing:\n1. Read the audit and eval result.\n2. Report risk notes and files or commands that will be touched.\n3. Install only in a sandbox or low-risk workspace first.\n4. If risk is unacceptable, use an alternative.\n\nAlternatives:\n- Autoresearch (uditgoenka-autoresearch): https://www.openagentskill.com/skills/uditgoenka-autoresearch\n- Awesome Autoresearch (alvinreal-awesome-autoresearch): https://www.openagentskill.com/skills/alvinreal-awesome-autoresearch\n- Codex Autoresearch (leo-lilinxiao-codex-autoresearch): https://www.openagentskill.com/skills/leo-lilinxiao-codex-autoresearch\n\nExpected Claude Code output:\n- selected_skill\n- skill_files_or_instructions\n- install_prompt\n- risk_summary\n- outcome_event_id\n- activation_steps\n- fallback_skill"},{"id":"cursor","name":"Cursor","surface":"Cursor rules / agent instructions","copy_prompt":"Task: Use exploratory-autoresearch\nSelected skill: exploratory-autoresearch (gaasher-exploratory-autoresearch)\nSkill URL: https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch\nAudit URL: https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch/audit\nEval URL: https://www.openagentskill.com/api/agent/evals?slug=gaasher-exploratory-autoresearch&task=Use%20exploratory-autoresearch&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/gaasher-exploratory-autoresearch/install\nInstall command: npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch\nInstall policy: Human review is required before install.\nOutcome feedback: use install_receipt.outcome_feedback.event_id or feedback.event_id from the Resolve API and report the result to /api/agent/outcome after one narrow run. Include outcome, install_used, task_success, output_quality, workspace, error_type, and human_review_required when known.\n\nBefore installing:\n1. Read the audit and eval result.\n2. Report risk notes and files or commands that will be touched.\n3. Install only in a sandbox or low-risk workspace first.\n4. If risk is unacceptable, use an alternative.\n\nAlternatives:\n- Autoresearch (uditgoenka-autoresearch): https://www.openagentskill.com/skills/uditgoenka-autoresearch\n- Awesome Autoresearch (alvinreal-awesome-autoresearch): https://www.openagentskill.com/skills/alvinreal-awesome-autoresearch\n- Codex Autoresearch (leo-lilinxiao-codex-autoresearch): https://www.openagentskill.com/skills/leo-lilinxiao-codex-autoresearch\n\nExpected Cursor output:\n- selected_skill\n- cursor_rule_or_prompt\n- install_command\n- risk_summary\n- outcome_event_id\n- when_to_use\n- when_not_to_use"}],"review_checklist":["Safety tier: Reviewed with permission notes","Safety score: 66/100 Review before install","Audit score: 78/100 Needs review","Trust score: 68/100 Sandbox only","Readiness: 62/100 Prototype first","Quality score needs review","Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"expected_output":{"selected_skill":"slug and name","install_command":"command or agent prompt used","risk_summary":"audit, trust, and policy notes","next_step":"what the agent will do after install","outcome_event_id":"resolve_4cb6fd18-b126-4411-8624-ece5adc79777"},"feedback":{"event_id":"resolve_4cb6fd18-b126-4411-8624-ece5adc79777","outcome_api":"https://www.openagentskill.com/api/agent/outcome","cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_4cb6fd18-b126-4411-8624-ece5adc79777\" --skill \"gaasher-exploratory-autoresearch\" --task \"Use exploratory-autoresearch\" --agent \"codex\" --outcome success","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"]},"blocked_actions":["Do not install when safety_gate.blocked is true.","Do not install when the audit or eval reports unacceptable workspace risk.","Do not execute shell commands, access secrets, or call external services without user approval.","Do not keep the skill as an always-on instruction if it only fits a narrow task."]},"policy_decision":{"status":"human_review_required","summary":"Require human approval before installing into a real workspace."},"agent_decision":{"input_task":"Use exploratory-autoresearch","recommended_skill":{"slug":"gaasher-exploratory-autoresearch","name":"exploratory-autoresearch","url":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch","audit_url":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch/audit","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","safety_tier":"Reviewed with permission notes","auto_install_policy":"review"},"alternative_skills":[{"slug":"uditgoenka-autoresearch","name":"Autoresearch","url":"https://www.openagentskill.com/skills/uditgoenka-autoresearch","install_command":"npx skills add uditgoenka/autoresearch","why_consider":"Matches task terms: autoresearch","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"82/100 Review before install","trust":"90/100 Production candidate","notes":["Documentation summary is thin"]}},{"slug":"alvinreal-awesome-autoresearch","name":"Awesome Autoresearch","url":"https://www.openagentskill.com/skills/alvinreal-awesome-autoresearch","install_command":"npx skills add alvinreal/awesome-autoresearch","why_consider":"Matches task terms: autoresearch","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"78/100 Review before install","trust":"85/100 Strong shortlist","notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"]}},{"slug":"leo-lilinxiao-codex-autoresearch","name":"Codex Autoresearch","url":"https://www.openagentskill.com/skills/leo-lilinxiao-codex-autoresearch","install_command":"npx skills add leo-lilinxiao/codex-autoresearch","why_consider":"Matches task terms: autoresearch","risk":{"level":"Safe to try","safety_tier":"Reviewed with permission notes","safety":"64/100 Review before install","trust":"84/100 Strong shortlist","notes":["High-risk permission hints: Shell or command execution","Documentation summary is thin"]}}],"install_command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","install_target":"Codex install prompt","why_recommended":["Matches task terms: exploratory, autoresearch","Install handoff is available","Repository freshness signal is available","Registry match score 42","Fallback candidate for Research agents","68/100 OpenAgentSkill Trust Score v5"],"risk_summary":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"66/100 Review before install","trust":"76/100 Strong shortlist","notes":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","action":"Require human approval before installing into a real workspace."},"feedback":{"event_id":"resolve_4cb6fd18-b126-4411-8624-ece5adc79777","outcome_api":"https://www.openagentskill.com/api/agent/outcome","cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_4cb6fd18-b126-4411-8624-ece5adc79777\" --skill \"gaasher-exploratory-autoresearch\" --task \"Use exploratory-autoresearch\" --agent \"codex\" --outcome success","contract":{"version":"openagentskill-agent-feedback-loop-v3","status":"active","purpose":"Report the result of one resolved skill run so Trust Score v5 and future Resolve rankings learn from real use.","event_id":"resolve_4cb6fd18-b126-4411-8624-ece5adc79777","selected_skill_slug":"gaasher-exploratory-autoresearch","selected_skill_name":"exploratory-autoresearch","endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","idempotency":"Retrying the same event_id updates the previous outcome.","dry_run":{"supported":true,"instruction":"Set dry_run=true to validate a payload before wiring a new agent integration."},"expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"error_types":["install_failed","runtime_error","not_relevant","permission_blocked","risk_blocked","setup_required","low_quality_output","missing_dependency","timeout","other"],"workspaces":["sandbox","local","ci","production","unknown"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url"],"payload_template":{"event_id":"resolve_4cb6fd18-b126-4411-8624-ece5adc79777","skill_slug":"gaasher-exploratory-autoresearch","task":"Use exploratory-autoresearch","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":"f1169e6db0b0f8a83ced3a18562b7c57e14a748a","content_hash":"94f2fbf5cad3f6036dfa20764ca1f13622b620e88dc43e2bf35e9c9424149d77","ref":"main","path":"loops/exploratory-autoresearch/SKILL.md","sync_status":"current"}},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_4cb6fd18-b126-4411-8624-ece5adc79777\" --skill \"gaasher-exploratory-autoresearch\" --task \"Use exploratory-autoresearch\" --agent \"codex\" --outcome success","ranking_inputs_updated":["Trust Score v5 outcome confidence","Resolve ranking outcome evidence","Skill detail outcome signal block","Outcome leaderboard"]}},"agent_next_steps":["Read the audit URL before installing.","Ask for human approval before installing.","Use install command: npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","After one narrow task, report the outcome with: npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_4cb6fd18-b126-4411-8624-ece5adc79777\" --skill \"gaasher-exploratory-autoresearch\" --task \"Use exploratory-autoresearch\" --agent \"codex\" --outcome success","Summarize output, warnings, files touched, and whether setup or human review was required."]},"decision_packet":{"version":"openagentskill-agent-decision-packet-v1","task":"Use exploratory-autoresearch","agent":"codex","selected_skill":{"slug":"gaasher-exploratory-autoresearch","name":"exploratory-autoresearch","url":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch","api_url":"https://www.openagentskill.com/api/agent/skills/gaasher-exploratory-autoresearch","audit_url":"https://www.openagentskill.com/skills/gaasher-exploratory-autoresearch/audit","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch","source_version":{"version":"1.0.0","commit_sha":"f1169e6db0b0f8a83ced3a18562b7c57e14a748a","content_hash":"94f2fbf5cad3f6036dfa20764ca1f13622b620e88dc43e2bf35e9c9424149d77","ref":"main","path":"loops/exploratory-autoresearch/SKILL.md","sync_status":"current"}},"suited_tasks":["Research agents workflows","Claude Code teams","builders willing to evaluate younger projects","Search sources","Extract claims","Synthesize findings","Chunk documents","Create embeddings"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch","target":"codex","label":"Codex install prompt","policy":"review","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true},"trust":{"score":68,"label":"Sandbox only","version":"trust-score-v5","base_score":76,"outcome_confidence":0,"decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["68/100 Trust Score v5","76/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"status":"info","detail":"163 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"status":"warn","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"status":"pass","detail":"npx skills add gaasher/Agent-Loop-Skills --skill exploratory-autoresearch"},{"id":"install_safety","label":"Install command safety","score":92,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"status":"pass","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/exploratory-autoresearch"},{"id":"review_status","label":"Review status","score":88,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"status":"info","detail":"No agent outcome data yet"}]},"risk":{"level":"Needs review","audit_label":"Needs review","safety":"66/100 Review before install","trust":"76/100 Strong shortlist","safety_tier":"Reviewed with permission notes","notes":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"minimum_review_before_use":["Trust: 76/100 Strong shortlist","Audit: 78/100 Needs review","Safety: 66/100 Review before install","Review repository, license, install command, and permission surface before production use."]},"alternatives":[{"slug":"uditgoenka-autoresearch","name":"Autoresearch","url":"https://www.openagentskill.com/skills/uditgoenka-autoresearch","install_command":"npx skills add uditgoenka/autoresearch","trust_score":90,"audit_score":94,"safety_score":82,"why_consider":"Matches task terms: autoresearch","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"82/100 Review before install","trust":"90/100 Production candidate","notes":["Documentation summary is thin"]}},{"slug":"alvinreal-awesome-autoresearch","name":"Awesome Autoresearch","url":"https://www.openagentskill.com/skills/alvinreal-awesome-autoresearch","install_command":"npx skills add alvinreal/awesome-autoresearch","trust_score":85,"audit_score":90,"safety_score":78,"why_consider":"Matches task terms: autoresearch","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"78/100 Review before install","trust":"85/100 Strong shortlist","notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"]}},{"slug":"leo-lilinxiao-codex-autoresearch","name":"Codex Autoresearch","url":"https://www.openagentskill.com/skills/leo-lilinxiao-codex-autoresearch","install_command":"npx skills add leo-lilinxiao/codex-autoresearch","trust_score":84,"audit_score":88,"safety_score":64,"why_consider":"Matches task terms: autoresearch","risk":{"level":"Safe to try","safety_tier":"Reviewed with permission notes","safety":"64/100 Review before install","trust":"84/100 Strong shortlist","notes":["High-risk permission hints: Shell or command execution","Documentation summary is thin"]}},{"slug":"rlaope-omh-autoresearch-goal","name":"omh-autoresearch-goal","url":"https://www.openagentskill.com/skills/rlaope-omh-autoresearch-goal","install_command":"npx skills add rlaope/oh-my-hermes --skill omh-autoresearch-goal","trust_score":82,"audit_score":84,"safety_score":72,"why_consider":"Matches task terms: autoresearch","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"72/100 Review before install","trust":"82/100 Strong shortlist","notes":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}}],"outcome_feedback":{"event_id":"resolve_4cb6fd18-b126-4411-8624-ece5adc79777","endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"resolve_4cb6fd18-b126-4411-8624-ece5adc79777","skill_slug":"gaasher-exploratory-autoresearch","task":"Use exploratory-autoresearch","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":"f1169e6db0b0f8a83ced3a18562b7c57e14a748a","content_hash":"94f2fbf5cad3f6036dfa20764ca1f13622b620e88dc43e2bf35e9c9424149d77","ref":"main","path":"loops/exploratory-autoresearch/SKILL.md","sync_status":"current"}},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_4cb6fd18-b126-4411-8624-ece5adc79777\" --skill \"gaasher-exploratory-autoresearch\" --task \"Use exploratory-autoresearch\" --agent \"codex\" --outcome success"},"next_agent_action":"Ask for human approval or choose a safer alternative before installing.","stable_fields":["decision_packet.selected_skill","decision_packet.install","decision_packet.risk.do_not_use_when","decision_packet.alternatives","decision_packet.outcome_feedback","decision_packet.trust.decision"]},"benchmark":{"endpoint":"https://www.openagentskill.com/api/agent/evals","note":"Use the evals endpoint to regression-test recommendation quality before changing ranking logic."},"meta":{"endpoint":"/api/agent/resolve","api_version":"2.0","generated_at":"2026-09-06T22:35:03.259Z","total_skills_searched":857,"total_candidates":15,"candidate_pool":{"sort":"quality","size":857,"note":"Resolver searches the highest-quality candidate pool for low-latency agent use. Browse /skills for the full public index."},"contract":{"best_skill":"recommendation.best_skill","install":"recommendation.install","why":"recommendation.why_recommended","risk":"recommendation.risk","alternatives":"recommendation.alternatives","agent_handoff":"agent_handoff.platform_templates + agent_handoff.review_checklist","decision_packet":"decision_packet","install_receipt":"install_receipt","recommendation_lanes":"recommendation_lanes"}}}