{"task":"Use DynamicMap Benchmark","agent":"codex","constraints":{"max_risk":"medium","needs_install_command":true,"min_stars":0},"feedback":{"event_id":"resolve_a60dbb30-a301-400e-88d0-414f30a86c1c","outcome_api":"https://www.openagentskill.com/api/agent/outcome","method":"POST","selected_skill_slug":"kth-rpl-dynamicmap-benchmark","selected_skill_name":"DynamicMap Benchmark","alternative_skill_slugs":["gmberton-deep-visual-geo-localization-benchmark","zeyofu-blink-benchmark","hyperledger-caliper-caliper-benchmarks","jeinlee1991-chinese-llm-benchmark"],"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_a60dbb30-a301-400e-88d0-414f30a86c1c","skill_slug":"kth-rpl-dynamicmap-benchmark","task":"Use DynamicMap Benchmark","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."},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz outcome \"resolve_a60dbb30-a301-400e-88d0-414f30a86c1c\" --skill \"kth-rpl-dynamicmap-benchmark\" --task \"Use DynamicMap Benchmark\" --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_a60dbb30-a301-400e-88d0-414f30a86c1c","selected_skill_slug":"kth-rpl-dynamicmap-benchmark","selected_skill_name":"DynamicMap Benchmark","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_a60dbb30-a301-400e-88d0-414f30a86c1c","skill_slug":"kth-rpl-dynamicmap-benchmark","task":"Use DynamicMap Benchmark","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."},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz outcome \"resolve_a60dbb30-a301-400e-88d0-414f30a86c1c\" --skill \"kth-rpl-dynamicmap-benchmark\" --task \"Use DynamicMap Benchmark\" --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-v1","receipt_id":"receipt_a60dbb30-a301-400e-88d0-414f30a86c1c","resolve_event_id":"resolve_a60dbb30-a301-400e-88d0-414f30a86c1c","generated_at":"2026-08-22T23:19:12.432Z","task":"Use DynamicMap Benchmark","agent":"codex","constraints":{"max_risk":"medium","needs_install_command":true,"min_stars":0},"urls":{"web":"https://www.openagentskill.com/resolve?task=Use+DynamicMap+Benchmark&agent=codex&max_risk=medium","json":"https://www.openagentskill.com/api/agent/receipt?task=Use+DynamicMap+Benchmark&agent=codex&max_risk=medium","text":"https://www.openagentskill.com/api/agent/receipt?task=Use+DynamicMap+Benchmark&agent=codex&max_risk=medium&format=text","resolve_json":"https://www.openagentskill.com/api/agent/resolve?task=Use+DynamicMap+Benchmark&agent=codex&max_risk=medium","resolve_text":"https://www.openagentskill.com/api/agent/resolve?task=Use+DynamicMap+Benchmark&agent=codex&max_risk=medium&format=text"},"selected_skill":{"slug":"kth-rpl-dynamicmap-benchmark","name":"DynamicMap Benchmark","description":"The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating","category":"robotics-iot","url":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark","api_url":"https://www.openagentskill.com/api/agent/skills/kth-rpl-dynamicmap-benchmark","audit_url":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=kth-rpl-dynamicmap-benchmark&task=Use%20DynamicMap%20Benchmark&max_risk=medium","install_api_url":"https://www.openagentskill.com/api/skills/kth-rpl-dynamicmap-benchmark/install","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark"},"install":{"command":"npx skills add KTH-RPL/DynamicMap_Benchmark","target":"codex","label":"Codex install prompt","kind":"agent-prompt","value":"Install the \"DynamicMap Benchmark\" agent skill from https://github.com/KTH-RPL/DynamicMap_Benchmark. 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: The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating 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\":\"kth-rpl-dynamicmap-benchmark\",\"task\":\"Install DynamicMap Benchmark\",\"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: dynamicmap, benchmark","Install handoff is available","Repository freshness signal is available","Registry match score 42","Needs validation for GitHub automation","67/100 Trust Score","0/100 Agent Proven Score","73/100 audit score"],"suited_tasks":["GitHub automation workflows","general agent builders","builders willing to evaluate younger projects","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Navigate local resources","Run repeatable desktop actions"],"suited_agents":["Jupyter Notebook","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"]},"trust":{"score":67,"label":"Sandbox only","version":"trust-score-v5","base_score":75,"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":["67/100 Trust Score v5","75/100 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-v3","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"],"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":61,"audit_score":73,"notes":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata","61/100 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","Documentation summary is thin","Quality score needs review","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata","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: 75/100 Strong shortlist","Audit: 73/100 Needs review","Safety: 61/100 Review before install","Review repository, license, install command, and permission surface before production use."]},"alternatives":[{"slug":"gmberton-deep-visual-geo-localization-benchmark","name":"Deep Visual Geo Localization Benchmark","url":"https://www.openagentskill.com/skills/gmberton-deep-visual-geo-localization-benchmark","audit_url":"https://www.openagentskill.com/skills/gmberton-deep-visual-geo-localization-benchmark/audit","install_command":"npx skills add gmberton/deep-visual-geo-localization-benchmark","trust_score":77,"audit_score":77,"safety_score":65,"reason":"Matches task terms: benchmark","policy":"review"},{"slug":"zeyofu-blink-benchmark","name":"BLINK Benchmark","url":"https://www.openagentskill.com/skills/zeyofu-blink-benchmark","audit_url":"https://www.openagentskill.com/skills/zeyofu-blink-benchmark/audit","install_command":"npx skills add zeyofu/BLINK_Benchmark","trust_score":74,"audit_score":71,"safety_score":55,"reason":"Matches task terms: benchmark","policy":"review"},{"slug":"hyperledger-caliper-caliper-benchmarks","name":"Caliper Benchmarks","url":"https://www.openagentskill.com/skills/hyperledger-caliper-caliper-benchmarks","audit_url":"https://www.openagentskill.com/skills/hyperledger-caliper-caliper-benchmarks/audit","install_command":"npx skills add hyperledger-caliper/caliper-benchmarks","trust_score":73,"audit_score":64,"safety_score":48,"reason":"Matches task terms: benchmark","policy":"review"},{"slug":"jeinlee1991-chinese-llm-benchmark","name":"Chinese Llm Benchmark","url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark","audit_url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark/audit","install_command":"npx skills add jeinlee1991/chinese-llm-benchmark","trust_score":85,"audit_score":89,"safety_score":77,"reason":"Matches task terms: benchmark","policy":"review"}],"outcome_feedback":{"event_id":"resolve_a60dbb30-a301-400e-88d0-414f30a86c1c","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_a60dbb30-a301-400e-88d0-414f30a86c1c","skill_slug":"kth-rpl-dynamicmap-benchmark","task":"Use DynamicMap Benchmark","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."},"dry_run_payload":{"event_id":"resolve_a60dbb30-a301-400e-88d0-414f30a86c1c","skill_slug":"kth-rpl-dynamicmap-benchmark","task":"Use DynamicMap Benchmark","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.","dry_run":true},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz outcome \"resolve_a60dbb30-a301-400e-88d0-414f30a86c1c\" --skill \"kth-rpl-dynamicmap-benchmark\" --task \"Use DynamicMap Benchmark\" --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/kth-rpl-dynamicmap-benchmark/audit","Fetch the pre-install eval: https://www.openagentskill.com/api/agent/evals?slug=kth-rpl-dynamicmap-benchmark&task=Use%20DynamicMap%20Benchmark&max_risk=medium","Do not auto-install yet. Ask for human review before running: npx skills add KTH-RPL/DynamicMap_Benchmark","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_a60dbb30-a301-400e-88d0-414f30a86c1c."],"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 DynamicMap Benchmark","agent":"codex","best_skill":{"slug":"kth-rpl-dynamicmap-benchmark","name":"DynamicMap Benchmark","description":"The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating","category":"robotics-iot","url":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark","api_url":"https://www.openagentskill.com/api/agent/skills/kth-rpl-dynamicmap-benchmark","audit_url":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=kth-rpl-dynamicmap-benchmark&task=Use%20DynamicMap%20Benchmark&max_risk=medium","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark"},"install":{"command":"npx skills add KTH-RPL/DynamicMap_Benchmark","target":"codex","label":"Codex install prompt","kind":"agent-prompt","value":"Install the \"DynamicMap Benchmark\" agent skill from https://github.com/KTH-RPL/DynamicMap_Benchmark. 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: The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating 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\":\"kth-rpl-dynamicmap-benchmark\",\"task\":\"Install DynamicMap Benchmark\",\"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/kth-rpl-dynamicmap-benchmark/install","ready":true,"review_required":true,"auto_install_allowed":false,"policy":"review"},"why_recommended":["Matches task terms: dynamicmap, benchmark","Install handoff is available","Repository freshness signal is available","Registry match score 42","Needs validation for GitHub automation","67/100 OpenAgentSkill Trust Score v5","73/100 audit score","61/100 safety score"],"trust_score_v5":{"score":67,"base_score":75,"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":["67/100 Trust Score v5","75/100 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":"425 GitHub stars","repoActivity":"425 stars, 30 forks","lastPushed":"11mo since push","license":"BSD-3-Clause","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark","install":"npx skills add KTH-RPL/DynamicMap_Benchmark","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"},"agent_compatibility":["Jupyter Notebook","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"risk":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"]},"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-v3","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"],"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":["robotics-iot","robotics","automation","autonomous-driving","benchmark","dataset"],"suited_agents":["Jupyter Notebook","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add KTH-RPL/DynamicMap_Benchmark","trust_score":67,"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":["robotics-iot","robotics","automation","autonomous-driving","benchmark","dataset"],"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","Documentation summary is thin","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":75,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"trust_score_v4":{"score":75,"tier":"strong","label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"425 GitHub stars","repoActivity":"425 stars, 30 forks","lastPushed":"11mo since push","license":"BSD-3-Clause","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark","install":"npx skills add KTH-RPL/DynamicMap_Benchmark","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"},"agent_compatibility":["Jupyter Notebook","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"risk":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"]},"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":["robotics-iot","robotics","automation","autonomous-driving","benchmark","dataset"],"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","Documentation summary is thin","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"]},"trust_score_v3":{"score":75,"tier":"strong","label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"425 GitHub stars","repoActivity":"425 stars, 30 forks","lastPushed":"11mo since push","license":"BSD-3-Clause","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark","install":"npx skills add KTH-RPL/DynamicMap_Benchmark","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"},"agent_compatibility":["Jupyter Notebook","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"risk":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"]}},"trust_score_v2":{"score":75,"tier":"strong","label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"425 GitHub stars","repoActivity":"425 stars, 30 forks","lastPushed":"11mo since push","license":"BSD-3-Clause","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark","install":"npx skills add KTH-RPL/DynamicMap_Benchmark","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"},"agent_compatibility":["Jupyter Notebook","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"risk":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"]}},"risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"61/100 Review before install","trust":"75/100 Strong shortlist","notes":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"]},"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":["Documentation summary is thin","61/100 agent safety score"]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"kth-rpl-dynamicmap-benchmark","name":"DynamicMap Benchmark","description":"The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating","category":"robotics-iot","url":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark","github_repo":"KTH-RPL/DynamicMap_Benchmark"},"suited_tasks":["GitHub automation workflows","general agent builders","builders willing to evaluate younger projects","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Navigate local resources","Run repeatable desktop actions"],"suited_agents":["Jupyter Notebook","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add KTH-RPL/DynamicMap_Benchmark","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install kth-rpl-dynamicmap-benchmark"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"DynamicMap Benchmark\" agent skill from https://github.com/KTH-RPL/DynamicMap_Benchmark. 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: The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating 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\":\"kth-rpl-dynamicmap-benchmark\",\"task\":\"Install DynamicMap Benchmark\",\"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 \"DynamicMap Benchmark\" as a Claude Code skill from https://github.com/KTH-RPL/DynamicMap_Benchmark. 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: The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating 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\":\"kth-rpl-dynamicmap-benchmark\",\"task\":\"Install DynamicMap Benchmark\",\"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 \"DynamicMap Benchmark\" from https://github.com/KTH-RPL/DynamicMap_Benchmark 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: The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating 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\":\"kth-rpl-dynamicmap-benchmark\",\"task\":\"Install DynamicMap Benchmark\",\"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/kth-rpl-dynamicmap-benchmark/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/kth-rpl-dynamicmap-benchmark"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"425 GitHub stars","repoActivity":"425 stars, 30 forks","lastPushed":"11mo since push","license":"BSD-3-Clause","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark","install":"npx skills add KTH-RPL/DynamicMap_Benchmark","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":["robotics-iot","robotics","automation","autonomous-driving","benchmark","dataset"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"]},"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":73,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"]},"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":60,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"11mo 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","Documentation summary is thin","Quality score needs review","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata","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 DynamicMap Benchmark","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 73/100 Needs review","Safety: 61/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"kth-rpl-dynamicmap-benchmark (DynamicMap Benchmark)","install_command":"npx skills add KTH-RPL/DynamicMap_Benchmark","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":"kth-rpl-dynamicmap-benchmark","task":"Use DynamicMap Benchmark","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/kth-rpl-dynamicmap-benchmark","api":"https://www.openagentskill.com/api/agent/skills/kth-rpl-dynamicmap-benchmark","audit":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=kth-rpl-dynamicmap-benchmark&task=Use%20DynamicMap%20Benchmark&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20DynamicMap%20Benchmark&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20DynamicMap%20Benchmark&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/kth-rpl-dynamicmap-benchmark/install","manifest":"https://www.openagentskill.com/api/registry/manifest/kth-rpl-dynamicmap-benchmark"}},"agent_contract":{"version":"openagentskill-resolve-contract-v2","input_task":"Use DynamicMap Benchmark","recommended_skill_slug":"kth-rpl-dynamicmap-benchmark","recommended_skill_name":"DynamicMap Benchmark","install_command":"npx skills add KTH-RPL/DynamicMap_Benchmark","install_policy":"review","auto_install_allowed":false,"human_review_required":true,"audit_url":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=kth-rpl-dynamicmap-benchmark&task=Use%20DynamicMap%20Benchmark&max_risk=medium","skill_api_url":"https://www.openagentskill.com/api/agent/skills/kth-rpl-dynamicmap-benchmark","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","Quality score needs review","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata","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: 75/100 Strong shortlist","Audit: 73/100 Needs review","Safety: 61/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"kth-rpl-dynamicmap-benchmark (DynamicMap Benchmark)","install_command":"npx skills add KTH-RPL/DynamicMap_Benchmark","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":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"GitHub automation","description":"I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.","useCases":[{"slug":"github-automation","title":"GitHub automation"},{"slug":"local-desktop","title":"Local desktop"},{"slug":"coding-agents","title":"Coding agents"}]},"maintenance":{"status":"stable","label":"11mo since push","daysSincePush":334,"lastPushedAt":"2025-09-22T08:40:00+00:00"},"github_quality":{"stars":425,"starsLabel":"425","forks":30,"license":"BSD-3-Clause","qualityScore":60,"trustScore":75,"auditScore":73},"coverage_tags":["Coding","GitHub automation","robotics-iot","robotics","automation","autonomous-driving","benchmark","dataset"]},"alternatives":[{"slug":"gmberton-deep-visual-geo-localization-benchmark","name":"Deep Visual Geo Localization Benchmark","url":"https://www.openagentskill.com/skills/gmberton-deep-visual-geo-localization-benchmark","install_command":"npx skills add gmberton/deep-visual-geo-localization-benchmark","trust_score":77,"audit_score":77,"safety_score":65,"why_consider":"Matches task terms: benchmark","risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"65/100 Review before install","trust":"77/100 Strong shortlist","notes":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 256 stars, 32 forks; issue activity unavailable in current metadata"]}},{"slug":"zeyofu-blink-benchmark","name":"BLINK Benchmark","url":"https://www.openagentskill.com/skills/zeyofu-blink-benchmark","install_command":"npx skills add zeyofu/BLINK_Benchmark","trust_score":74,"audit_score":71,"safety_score":55,"why_consider":"Matches task terms: benchmark","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"55/100 Review before install","trust":"74/100 Strong shortlist","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 169 stars, 8 forks; issue activity unavailable in current metadata"]}},{"slug":"hyperledger-caliper-caliper-benchmarks","name":"Caliper Benchmarks","url":"https://www.openagentskill.com/skills/hyperledger-caliper-caliper-benchmarks","install_command":"npx skills add hyperledger-caliper/caliper-benchmarks","trust_score":73,"audit_score":64,"safety_score":48,"why_consider":"Matches task terms: benchmark","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"48/100 Avoid automatic install","trust":"73/100 Strong shortlist","notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push"]}},{"slug":"jeinlee1991-chinese-llm-benchmark","name":"Chinese Llm Benchmark","url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark","install_command":"npx skills add jeinlee1991/chinese-llm-benchmark","trust_score":85,"audit_score":89,"safety_score":77,"why_consider":"Matches task terms: benchmark","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"77/100 Review before install","trust":"85/100 Strong shortlist","notes":["License is unclear","License clarity: Unknown"]}}],"decision_packet":{"version":"openagentskill-agent-decision-packet-v1","task":"Use DynamicMap Benchmark","agent":"codex","selected_skill":{"slug":"kth-rpl-dynamicmap-benchmark","name":"DynamicMap Benchmark","url":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark","api_url":"https://www.openagentskill.com/api/agent/skills/kth-rpl-dynamicmap-benchmark","audit_url":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark/audit","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark"},"suited_tasks":["GitHub automation workflows","general agent builders","builders willing to evaluate younger projects","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Navigate local resources","Run repeatable desktop actions"],"suited_agents":["Jupyter Notebook","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add KTH-RPL/DynamicMap_Benchmark","target":"codex","label":"Codex install prompt","policy":"review","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true},"trust":{"score":67,"label":"Sandbox only","version":"trust-score-v5","base_score":75,"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":["67/100 Trust Score v5","75/100 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":"425 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"status":"warn","detail":"425 stars, 30 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":62,"status":"info","detail":"11mo since push"},{"id":"license","label":"License clarity","score":86,"status":"pass","detail":"BSD-3-Clause"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"status":"info","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 KTH-RPL/DynamicMap_Benchmark"},{"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/KTH-RPL/DynamicMap_Benchmark"},{"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":"61/100 Review before install","trust":"75/100 Strong shortlist","safety_tier":"Reviewed with permission notes","notes":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"],"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","Quality score needs review","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata","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: 75/100 Strong shortlist","Audit: 73/100 Needs review","Safety: 61/100 Review before install","Review repository, license, install command, and permission surface before production use."]},"alternatives":[{"slug":"gmberton-deep-visual-geo-localization-benchmark","name":"Deep Visual Geo Localization Benchmark","url":"https://www.openagentskill.com/skills/gmberton-deep-visual-geo-localization-benchmark","install_command":"npx skills add gmberton/deep-visual-geo-localization-benchmark","trust_score":77,"audit_score":77,"safety_score":65,"why_consider":"Matches task terms: benchmark","risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"65/100 Review before install","trust":"77/100 Strong shortlist","notes":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 256 stars, 32 forks; issue activity unavailable in current metadata"]}},{"slug":"zeyofu-blink-benchmark","name":"BLINK Benchmark","url":"https://www.openagentskill.com/skills/zeyofu-blink-benchmark","install_command":"npx skills add zeyofu/BLINK_Benchmark","trust_score":74,"audit_score":71,"safety_score":55,"why_consider":"Matches task terms: benchmark","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"55/100 Review before install","trust":"74/100 Strong shortlist","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 169 stars, 8 forks; issue activity unavailable in current metadata"]}},{"slug":"hyperledger-caliper-caliper-benchmarks","name":"Caliper Benchmarks","url":"https://www.openagentskill.com/skills/hyperledger-caliper-caliper-benchmarks","install_command":"npx skills add hyperledger-caliper/caliper-benchmarks","trust_score":73,"audit_score":64,"safety_score":48,"why_consider":"Matches task terms: benchmark","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"48/100 Avoid automatic install","trust":"73/100 Strong shortlist","notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push"]}},{"slug":"jeinlee1991-chinese-llm-benchmark","name":"Chinese Llm Benchmark","url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark","install_command":"npx skills add jeinlee1991/chinese-llm-benchmark","trust_score":85,"audit_score":89,"safety_score":77,"why_consider":"Matches task terms: benchmark","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"77/100 Review before install","trust":"85/100 Strong shortlist","notes":["License is unclear","License clarity: Unknown"]}}],"outcome_feedback":{"event_id":"resolve_a60dbb30-a301-400e-88d0-414f30a86c1c","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_a60dbb30-a301-400e-88d0-414f30a86c1c","skill_slug":"kth-rpl-dynamicmap-benchmark","task":"Use DynamicMap Benchmark","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."},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz outcome \"resolve_a60dbb30-a301-400e-88d0-414f30a86c1c\" --skill \"kth-rpl-dynamicmap-benchmark\" --task \"Use DynamicMap Benchmark\" --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 DynamicMap Benchmark for: Use DynamicMap Benchmark\nReview audit: https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark/audit\nAsk for human approval before installing: npx skills add KTH-RPL/DynamicMap_Benchmark\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":175.4,"semantic_relevance":42,"skill":{"slug":"kth-rpl-dynamicmap-benchmark","name":"DynamicMap Benchmark","description":"The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating","category":"robotics-iot","github_stars":425,"created_at":"2026-06-20T18:56:56.543204+00:00","updated_at":"2025-09-22T08:40:00+00:00","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark","github_repo":"KTH-RPL/DynamicMap_Benchmark"},"recommendation_reasons":["Matches task terms: dynamicmap, benchmark","Install handoff is available","Repository freshness signal is available","Registry match score 42"],"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":"GitHub automation","description":"I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.","useCases":[{"slug":"github-automation","title":"GitHub automation"},{"slug":"local-desktop","title":"Local desktop"},{"slug":"coding-agents","title":"Coding agents"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Jupyter Notebook"],"install":{"ready":true,"command":"npx skills add KTH-RPL/DynamicMap_Benchmark","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":425,"starsLabel":"425","forks":30,"license":"BSD-3-Clause","qualityScore":60,"trustScore":75,"auditScore":73},"maintenance":{"status":"stable","label":"11mo since push","daysSincePush":334,"lastPushedAt":"2025-09-22T08:40:00+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata","Needs review"]},"coverageTags":["Coding","GitHub automation","robotics-iot","robotics","automation","autonomous-driving","benchmark","dataset"]},"quality":{"score":60,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"425","tone":"neutral"},{"label":"Freshness","value":"11mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"BSD-3-Clause","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":75,"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":"425 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"425 stars, 30 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":62,"weight":0.14,"status":"info","detail":"11mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"BSD-3-Clause"},{"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 KTH-RPL/DynamicMap_Benchmark"},{"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/KTH-RPL/DynamicMap_Benchmark"},{"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":"425 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"425 stars, 30 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"11mo since push"},{"status":"pass","label":"License clarity","detail":"BSD-3-Clause"},{"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 KTH-RPL/DynamicMap_Benchmark"},{"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/KTH-RPL/DynamicMap_Benchmark"},{"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","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"],"evidence":{"stars":"425 GitHub stars","repoActivity":"425 stars, 30 forks","lastPushed":"11mo since push","license":"BSD-3-Clause","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark","install":"npx skills add KTH-RPL/DynamicMap_Benchmark","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 KTH-RPL/DynamicMap_Benchmark","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","11mo since push"]},"agentCompatibility":["Jupyter Notebook","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"]},"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":["robotics-iot","robotics","automation","autonomous-driving","benchmark","dataset"],"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","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"]},"trust_v5":{"version":"trust-score-v5","score":67,"base_score":75,"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":["67/100 Trust Score v5","75/100 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":"425 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"425 stars, 30 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":62,"weight":0.14,"status":"info","detail":"11mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"BSD-3-Clause"},{"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 KTH-RPL/DynamicMap_Benchmark"},{"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/KTH-RPL/DynamicMap_Benchmark"},{"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":"425 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"425 stars, 30 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"11mo since push"},{"status":"pass","label":"License clarity","detail":"BSD-3-Clause"},{"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 KTH-RPL/DynamicMap_Benchmark"},{"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/KTH-RPL/DynamicMap_Benchmark"},{"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","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","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"425 GitHub stars","repoActivity":"425 stars, 30 forks","lastPushed":"11mo since push","license":"BSD-3-Clause","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark","install":"npx skills add KTH-RPL/DynamicMap_Benchmark","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 KTH-RPL/DynamicMap_Benchmark","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","11mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Jupyter Notebook","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"]},"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-v3","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"],"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":["robotics-iot","robotics","automation","autonomous-driving","benchmark","dataset"],"suited_agents":["Jupyter Notebook","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add KTH-RPL/DynamicMap_Benchmark","trust_score":67,"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":["robotics-iot","robotics","automation","autonomous-driving","benchmark","dataset"],"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","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":75,"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":73,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"]},"safety":{"score":61,"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":["Documentation summary is thin","61/100 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":["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":["Documentation summary is thin","61/100 agent safety score"]},"decision":{"readiness_score":50,"readiness_label":"Needs manual review","headline":"Needs validation for GitHub automation","role":"Needs validation","best_for":["GitHub automation workflows","general agent builders","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one GitHub automation 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 KTH-RPL/DynamicMap_Benchmark","value":"Install the \"DynamicMap Benchmark\" agent skill from https://github.com/KTH-RPL/DynamicMap_Benchmark. 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: The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating 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\":\"kth-rpl-dynamicmap-benchmark\",\"task\":\"Install DynamicMap Benchmark\",\"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 DynamicMap Benchmark 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-v0.2.1/openagentskill-0.2.1.tgz install kth-rpl-dynamicmap-benchmark","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 \"DynamicMap Benchmark\" agent skill from https://github.com/KTH-RPL/DynamicMap_Benchmark. 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: The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating 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\":\"kth-rpl-dynamicmap-benchmark\",\"task\":\"Install DynamicMap Benchmark\",\"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 \"DynamicMap Benchmark\" as a Claude Code skill from https://github.com/KTH-RPL/DynamicMap_Benchmark. 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: The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating 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\":\"kth-rpl-dynamicmap-benchmark\",\"task\":\"Install DynamicMap Benchmark\",\"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 \"DynamicMap Benchmark\" from https://github.com/KTH-RPL/DynamicMap_Benchmark 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: The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating 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\":\"kth-rpl-dynamicmap-benchmark\",\"task\":\"Install DynamicMap Benchmark\",\"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":"kth-rpl-dynamicmap-benchmark","name":"DynamicMap Benchmark","description":"The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating","category":"robotics-iot","url":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark","github_repo":"KTH-RPL/DynamicMap_Benchmark"},"suited_tasks":["GitHub automation workflows","general agent builders","builders willing to evaluate younger projects","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Navigate local resources","Run repeatable desktop actions"],"suited_agents":["Jupyter Notebook","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add KTH-RPL/DynamicMap_Benchmark","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install kth-rpl-dynamicmap-benchmark"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"DynamicMap Benchmark\" agent skill from https://github.com/KTH-RPL/DynamicMap_Benchmark. 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: The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating 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\":\"kth-rpl-dynamicmap-benchmark\",\"task\":\"Install DynamicMap Benchmark\",\"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 \"DynamicMap Benchmark\" as a Claude Code skill from https://github.com/KTH-RPL/DynamicMap_Benchmark. 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: The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating 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\":\"kth-rpl-dynamicmap-benchmark\",\"task\":\"Install DynamicMap Benchmark\",\"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 \"DynamicMap Benchmark\" from https://github.com/KTH-RPL/DynamicMap_Benchmark 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: The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating 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\":\"kth-rpl-dynamicmap-benchmark\",\"task\":\"Install DynamicMap Benchmark\",\"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/kth-rpl-dynamicmap-benchmark/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/kth-rpl-dynamicmap-benchmark"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"425 GitHub stars","repoActivity":"425 stars, 30 forks","lastPushed":"11mo since push","license":"BSD-3-Clause","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark","install":"npx skills add KTH-RPL/DynamicMap_Benchmark","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":["robotics-iot","robotics","automation","autonomous-driving","benchmark","dataset"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"]},"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":73,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"]},"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":60,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"11mo 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","Documentation summary is thin","Quality score needs review","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata","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 DynamicMap Benchmark","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 73/100 Needs review","Safety: 61/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"kth-rpl-dynamicmap-benchmark (DynamicMap Benchmark)","install_command":"npx skills add KTH-RPL/DynamicMap_Benchmark","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":"kth-rpl-dynamicmap-benchmark","task":"Use DynamicMap Benchmark","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/kth-rpl-dynamicmap-benchmark","api":"https://www.openagentskill.com/api/agent/skills/kth-rpl-dynamicmap-benchmark","audit":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=kth-rpl-dynamicmap-benchmark&task=Use%20DynamicMap%20Benchmark&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20DynamicMap%20Benchmark&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20DynamicMap%20Benchmark&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/kth-rpl-dynamicmap-benchmark/install","manifest":"https://www.openagentskill.com/api/registry/manifest/kth-rpl-dynamicmap-benchmark"}},"use_cases":[{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"}],"urls":{"web":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark","api":"https://www.openagentskill.com/api/agent/skills/kth-rpl-dynamicmap-benchmark","install_api":"https://www.openagentskill.com/api/skills/kth-rpl-dynamicmap-benchmark/install","audit":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=kth-rpl-dynamicmap-benchmark&task=Use%20DynamicMap%20Benchmark&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/kth-rpl-dynamicmap-benchmark?metric=audit","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark"}},"safer_alternative":{"rank":13,"match_score":30,"raw_match_score":76,"semantic_relevance":30,"skill":{"slug":"prowler-cloud-prowler","name":"Prowler","description":"Prowler is the world’s most widely used open-source cloud security platform that automates security and compliance across any cloud environment.","category":"legal-compliance","github_stars":14008,"created_at":"2026-06-16T10:06:25.675093+00:00","updated_at":"2026-06-17T19:02:47+00:00","repository":"https://github.com/prowler-cloud/prowler","github_repo":"prowler-cloud/prowler"},"recommendation_reasons":["Matches task terms: benchmark","Strong GitHub adoption: 14,008 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"legal","label":"Legal, policy, and compliance","shortLabel":"Legal","description":"Contract analysis, privacy, policy review, compliance checks, governance, and document risk review."},"scenario":{"label":"Legal and compliance","description":"I need my agent to review contracts, privacy policies, or compliance documents and summarize risks.","useCases":[{"slug":"legal-compliance","title":"Legal and compliance"},{"slug":"security-compliance","title":"Security and compliance"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add prowler-cloud/prowler","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":14008,"starsLabel":"14K","forks":2189,"license":"Apache-2.0","qualityScore":100,"trustScore":90,"auditScore":93},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":66,"lastPushedAt":"2026-06-17T19:02:47+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Legal","Legal and compliance","legal-compliance","gdpr","privacy","compliance","aws","azure"]},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"14K","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","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":100,"weight":0.13,"status":"pass","detail":"14K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"14K stars, 2.2K 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":"Apache-2.0"},{"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 prowler-cloud/prowler"},{"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/prowler-cloud/prowler"},{"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":"14K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"14K stars, 2.2K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"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 prowler-cloud/prowler"},{"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/prowler-cloud/prowler"},{"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":"14K GitHub stars","repoActivity":"14K stars, 2.2K forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/prowler-cloud/prowler","install":"npx skills add prowler-cloud/prowler","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 prowler-cloud/prowler","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","2mo since push"]},"agentCompatibility":["Python","GDPR","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":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["legal-compliance","gdpr","privacy","compliance","aws","azure"],"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":100,"weight":0.13,"status":"pass","detail":"14K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"14K stars, 2.2K 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":"Apache-2.0"},{"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 prowler-cloud/prowler"},{"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/prowler-cloud/prowler"},{"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":"14K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"14K stars, 2.2K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"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 prowler-cloud/prowler"},{"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/prowler-cloud/prowler"},{"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":"14K GitHub stars","repoActivity":"14K stars, 2.2K forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/prowler-cloud/prowler","install":"npx skills add prowler-cloud/prowler","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 prowler-cloud/prowler","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","2mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Python","GDPR","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":"agent_install_candidate","reason":"Ask for approval or run a sandbox-only trial before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v3","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"],"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":["legal-compliance","gdpr","privacy","compliance","aws","azure"],"suited_agents":["Python","GDPR","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add prowler-cloud/prowler","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":["legal-compliance","gdpr","privacy","compliance","aws","azure"],"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":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety":{"score":81,"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","81/100 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","81/100 agent safety score"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Legal and compliance","role":"Primary pick","best_for":["Legal and compliance workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Legal and compliance 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 prowler-cloud/prowler","value":"Install the \"Prowler\" agent skill from https://github.com/prowler-cloud/prowler. 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: Prowler is the world’s most widely used open-source cloud security platform that automates security and compliance across any cloud environment. 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\":\"prowler-cloud-prowler\",\"task\":\"Install Prowler\",\"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 Prowler 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-v0.2.1/openagentskill-0.2.1.tgz install prowler-cloud-prowler","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 \"Prowler\" agent skill from https://github.com/prowler-cloud/prowler. 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: Prowler is the world’s most widely used open-source cloud security platform that automates security and compliance across any cloud environment. 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\":\"prowler-cloud-prowler\",\"task\":\"Install Prowler\",\"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 \"Prowler\" as a Claude Code skill from https://github.com/prowler-cloud/prowler. 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: Prowler is the world’s most widely used open-source cloud security platform that automates security and compliance across any cloud environment. 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\":\"prowler-cloud-prowler\",\"task\":\"Install Prowler\",\"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 \"Prowler\" from https://github.com/prowler-cloud/prowler 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: Prowler is the world’s most widely used open-source cloud security platform that automates security and compliance across any cloud environment. 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\":\"prowler-cloud-prowler\",\"task\":\"Install Prowler\",\"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":"prowler-cloud-prowler","name":"Prowler","description":"Prowler is the world’s most widely used open-source cloud security platform that automates security and compliance across any cloud environment.","category":"legal-compliance","url":"https://www.openagentskill.com/skills/prowler-cloud-prowler","repository":"https://github.com/prowler-cloud/prowler","github_repo":"prowler-cloud/prowler"},"suited_tasks":["Legal and compliance workflows","general agent builders","teams that value GitHub adoption signals","Extract obligations","Highlight risky clauses","Prepare review-ready summaries","Inspect risky files","Prioritize findings"],"suited_agents":["Python","GDPR","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add prowler-cloud/prowler","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install prowler-cloud-prowler"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Prowler\" agent skill from https://github.com/prowler-cloud/prowler. 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: Prowler is the world’s most widely used open-source cloud security platform that automates security and compliance across any cloud environment. 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\":\"prowler-cloud-prowler\",\"task\":\"Install Prowler\",\"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 \"Prowler\" as a Claude Code skill from https://github.com/prowler-cloud/prowler. 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: Prowler is the world’s most widely used open-source cloud security platform that automates security and compliance across any cloud environment. 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\":\"prowler-cloud-prowler\",\"task\":\"Install Prowler\",\"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 \"Prowler\" from https://github.com/prowler-cloud/prowler 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: Prowler is the world’s most widely used open-source cloud security platform that automates security and compliance across any cloud environment. 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\":\"prowler-cloud-prowler\",\"task\":\"Install Prowler\",\"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/prowler-cloud-prowler/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/prowler-cloud-prowler"},"trust":{"score":90,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"14K GitHub stars","repoActivity":"14K stars, 2.2K forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/prowler-cloud/prowler","install":"npx skills add prowler-cloud/prowler","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":["legal-compliance","gdpr","privacy","compliance","aws","azure"],"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":93,"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":"Legal, policy, and compliance","scenario":"Legal and compliance","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","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 DynamicMap Benchmark","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: 93/100 Safe to try","Safety: 81/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"prowler-cloud-prowler (Prowler)","install_command":"npx skills add prowler-cloud/prowler","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":"prowler-cloud-prowler","task":"Use DynamicMap Benchmark","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/prowler-cloud-prowler","api":"https://www.openagentskill.com/api/agent/skills/prowler-cloud-prowler","audit":"https://www.openagentskill.com/skills/prowler-cloud-prowler/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=prowler-cloud-prowler&task=Use%20DynamicMap%20Benchmark&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20DynamicMap%20Benchmark&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20DynamicMap%20Benchmark&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/prowler-cloud-prowler/install","manifest":"https://www.openagentskill.com/api/registry/manifest/prowler-cloud-prowler"}},"use_cases":[{"slug":"legal-compliance","title":"Legal and compliance","url":"https://www.openagentskill.com/use-cases/legal-compliance"},{"slug":"security-compliance","title":"Security and compliance","url":"https://www.openagentskill.com/use-cases/security-compliance"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"urls":{"web":"https://www.openagentskill.com/skills/prowler-cloud-prowler","api":"https://www.openagentskill.com/api/agent/skills/prowler-cloud-prowler","install_api":"https://www.openagentskill.com/api/skills/prowler-cloud-prowler/install","audit":"https://www.openagentskill.com/skills/prowler-cloud-prowler/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=prowler-cloud-prowler&task=Use%20DynamicMap%20Benchmark&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/prowler-cloud-prowler?metric=audit","repository":"https://github.com/prowler-cloud/prowler"}},"popular_alternative":{"rank":15,"match_score":30,"raw_match_score":72.8,"semantic_relevance":30,"skill":{"slug":"zalandoresearch-fashion-mnist","name":"Fashion Mnist","description":"A MNIST-like fashion product database. Benchmark :point_down: ","category":"ml-automation","github_stars":12754,"created_at":"2026-06-16T08:55:46.581693+00:00","updated_at":"2022-06-13T20:36:21+00:00","repository":"https://github.com/zalandoresearch/fashion-mnist","github_repo":"zalandoresearch/fashion-mnist"},"recommendation_reasons":["Matches task terms: benchmark","Strong GitHub adoption: 12,754 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":"multimodal-media","title":"Multimodal media"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add zalandoresearch/fashion-mnist","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":12754,"starsLabel":"13K","forks":3071,"license":"MIT","qualityScore":77,"trustScore":79,"auditScore":72},"maintenance":{"status":"stale","label":"4y since push","daysSincePush":1531,"lastPushedAt":"2022-06-13T20:36:21+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Recent maintenance: 4y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"coverageTags":["Research","Research agents","ml-automation","machine-learning","automation","ml-media","benchmark","computer-vision"]},"quality":{"score":77,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"13K","tone":"positive"},{"label":"Freshness","value":"4y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":79,"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":"13K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"13K stars, 3.1K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":22,"weight":0.14,"status":"fail","detail":"4y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":82,"weight":0.12,"status":"pass","detail":"database surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add zalandoresearch/fashion-mnist"},{"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":88,"weight":0.07,"status":"pass","detail":"database access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/zalandoresearch/fashion-mnist"},{"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":"13K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"13K stars, 3.1K forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"4y 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":"database surface"},{"status":"pass","label":"Install availability","detail":"npx skills add zalandoresearch/fashion-mnist"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"database access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/zalandoresearch/fashion-mnist"},{"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","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Repository looks stale","Documentation summary is thin","Recent maintenance: 4y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"13K GitHub stars","repoActivity":"13K stars, 3.1K forks","lastPushed":"4y since push","license":"MIT","repository":"https://github.com/zalandoresearch/fashion-mnist","install":"npx skills add zalandoresearch/fashion-mnist","installSafety":"standard package or runtime install path","permissionSurface":"database access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add zalandoresearch/fashion-mnist","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","4y since push"]},"agentCompatibility":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Documentation summary is thin","Recent maintenance: 4y since push","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":["ml-automation","machine-learning","automation","ml-media","benchmark","computer-vision"],"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":["Repository looks stale","Documentation summary is thin","Recent maintenance: 4y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":71,"base_score":79,"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":["71/100 Trust Score v5","79/100 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":"13K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"13K stars, 3.1K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":22,"weight":0.14,"status":"fail","detail":"4y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":82,"weight":0.12,"status":"pass","detail":"database surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add zalandoresearch/fashion-mnist"},{"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":88,"weight":0.07,"status":"pass","detail":"database access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/zalandoresearch/fashion-mnist"},{"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":"13K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"13K stars, 3.1K forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"4y 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":"database surface"},{"status":"pass","label":"Install availability","detail":"npx skills add zalandoresearch/fashion-mnist"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"database access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/zalandoresearch/fashion-mnist"},{"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","Large GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Repository looks stale","Documentation summary is thin","Recent maintenance: 4y since push","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":"13K GitHub stars","repoActivity":"13K stars, 3.1K forks","lastPushed":"4y since push","license":"MIT","repository":"https://github.com/zalandoresearch/fashion-mnist","install":"npx skills add zalandoresearch/fashion-mnist","installSafety":"standard package or runtime install path","permissionSurface":"database 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 zalandoresearch/fashion-mnist","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","4y since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Documentation summary is thin","Recent maintenance: 4y since push","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-v3","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"],"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":["ml-automation","machine-learning","automation","ml-media","benchmark","computer-vision"],"suited_agents":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add zalandoresearch/fashion-mnist","trust_score":71,"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":["ml-automation","machine-learning","automation","ml-media","benchmark","computer-vision"],"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":["Repository looks stale","Documentation summary is thin","Recent maintenance: 4y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":79,"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":72,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Recent maintenance: 4y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":56,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","summary":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","auto_install_policy":"review","reasons":["Documentation summary is thin","56/100 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":"database","label":"Database access","reason":"Skill may inspect schemas, query databases, or work with persistent stores.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","reasons":["Documentation summary is thin","56/100 agent safety score"]},"decision":{"readiness_score":79,"readiness_label":"Strong shortlist","headline":"Companion skill for Research agents","role":"Companion skill","best_for":["Research agents workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["Repository looks stale","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 zalandoresearch/fashion-mnist","value":"Install the \"Fashion Mnist\" agent skill from https://github.com/zalandoresearch/fashion-mnist. 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 MNIST-like fashion product database. Benchmark :point_down: 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\":\"zalandoresearch-fashion-mnist\",\"task\":\"Install Fashion Mnist\",\"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 Fashion Mnist 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-v0.2.1/openagentskill-0.2.1.tgz install zalandoresearch-fashion-mnist","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 \"Fashion Mnist\" agent skill from https://github.com/zalandoresearch/fashion-mnist. 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 MNIST-like fashion product database. Benchmark :point_down: 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\":\"zalandoresearch-fashion-mnist\",\"task\":\"Install Fashion Mnist\",\"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 \"Fashion Mnist\" as a Claude Code skill from https://github.com/zalandoresearch/fashion-mnist. 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 MNIST-like fashion product database. Benchmark :point_down: 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\":\"zalandoresearch-fashion-mnist\",\"task\":\"Install Fashion Mnist\",\"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 \"Fashion Mnist\" from https://github.com/zalandoresearch/fashion-mnist 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 MNIST-like fashion product database. Benchmark :point_down: 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\":\"zalandoresearch-fashion-mnist\",\"task\":\"Install Fashion Mnist\",\"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":"zalandoresearch-fashion-mnist","name":"Fashion Mnist","description":"A MNIST-like fashion product database. Benchmark :point_down: ","category":"ml-automation","url":"https://www.openagentskill.com/skills/zalandoresearch-fashion-mnist","repository":"https://github.com/zalandoresearch/fashion-mnist","github_repo":"zalandoresearch/fashion-mnist"},"suited_tasks":["Research agents workflows","general agent builders","teams that value GitHub adoption signals","Search sources","Extract claims","Synthesize findings","Read media metadata","Convert formats"],"suited_agents":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add zalandoresearch/fashion-mnist","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install zalandoresearch-fashion-mnist"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Fashion Mnist\" agent skill from https://github.com/zalandoresearch/fashion-mnist. 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 MNIST-like fashion product database. Benchmark :point_down: 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\":\"zalandoresearch-fashion-mnist\",\"task\":\"Install Fashion Mnist\",\"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 \"Fashion Mnist\" as a Claude Code skill from https://github.com/zalandoresearch/fashion-mnist. 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 MNIST-like fashion product database. Benchmark :point_down: 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\":\"zalandoresearch-fashion-mnist\",\"task\":\"Install Fashion Mnist\",\"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 \"Fashion Mnist\" from https://github.com/zalandoresearch/fashion-mnist 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 MNIST-like fashion product database. Benchmark :point_down: 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\":\"zalandoresearch-fashion-mnist\",\"task\":\"Install Fashion Mnist\",\"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/zalandoresearch-fashion-mnist/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/zalandoresearch-fashion-mnist"},"trust":{"score":79,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"13K GitHub stars","repoActivity":"13K stars, 3.1K forks","lastPushed":"4y since push","license":"MIT","repository":"https://github.com/zalandoresearch/fashion-mnist","install":"npx skills add zalandoresearch/fashion-mnist","installSafety":"standard package or runtime install path","permissionSurface":"database 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":["ml-automation","machine-learning","automation","ml-media","benchmark","computer-vision"],"known_risks":["Repository looks stale","Documentation summary is thin","Recent maintenance: 4y since push","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":72,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Recent maintenance: 4y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":77,"label":"Strong"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"4y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Documentation summary is thin","Repository appears stale","Recent maintenance: 4y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"agent_contract":{"task_input":"Use DynamicMap Benchmark","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 79/100 Strong shortlist","Audit: 72/100 Needs review","Safety: 56/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"zalandoresearch-fashion-mnist (Fashion Mnist)","install_command":"npx skills add zalandoresearch/fashion-mnist","risk_summary":"Needs review; Experimental; 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":"zalandoresearch-fashion-mnist","task":"Use DynamicMap Benchmark","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/zalandoresearch-fashion-mnist","api":"https://www.openagentskill.com/api/agent/skills/zalandoresearch-fashion-mnist","audit":"https://www.openagentskill.com/skills/zalandoresearch-fashion-mnist/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=zalandoresearch-fashion-mnist&task=Use%20DynamicMap%20Benchmark&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20DynamicMap%20Benchmark&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20DynamicMap%20Benchmark&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/zalandoresearch-fashion-mnist/install","manifest":"https://www.openagentskill.com/api/registry/manifest/zalandoresearch-fashion-mnist"}},"use_cases":[{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"}],"urls":{"web":"https://www.openagentskill.com/skills/zalandoresearch-fashion-mnist","api":"https://www.openagentskill.com/api/agent/skills/zalandoresearch-fashion-mnist","install_api":"https://www.openagentskill.com/api/skills/zalandoresearch-fashion-mnist/install","audit":"https://www.openagentskill.com/skills/zalandoresearch-fashion-mnist/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=zalandoresearch-fashion-mnist&task=Use%20DynamicMap%20Benchmark&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/zalandoresearch-fashion-mnist?metric=audit","repository":"https://github.com/zalandoresearch/fashion-mnist"}},"new_contender":{"rank":8,"match_score":30,"raw_match_score":93.3,"semantic_relevance":30,"skill":{"slug":"samber-golang-benchmark","name":"golang-benchmark","description":"Golang benchmarking, profiling, and performance measurement. Use when writing, running, or comparing Go benchmarks, profiling hot paths with pprof, interpreting CPU/memory/trace profiles, analyzing results with benchstat, setting up CI benchmark regression detection, or investigating production performance with Prometheus runtime metrics. Also use when the developer needs deep analysis on a specific performance indicator - this skill provides the measurement methodology, while `samber/cc-skills-golang@golang-performance` provides the optimization patterns.","category":"research","github_stars":3010,"created_at":"2026-08-20T13:24:25.139418+00:00","updated_at":"2026-08-20T13:08:12+00:00","repository":"https://github.com/samber/cc-skills-golang/tree/main/skills/golang-benchmark","github_repo":"samber/cc-skills-golang"},"recommendation_reasons":["Matches task terms: benchmark","Useful GitHub adoption: 3,010 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":"coding-agents","title":"Coding agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add samber/cc-skills-golang --skill golang-benchmark","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":3010,"starsLabel":"3.0K","forks":197,"license":"MIT","qualityScore":82,"trustScore":75,"auditScore":84},"maintenance":{"status":"fresh","label":"2d since push","daysSincePush":2,"lastPushedAt":"2026-08-20T13:08:12+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["The allowed-tools list includes broad `Bash(curl:*)` and `Agent` permissions, which could be misused to fetch arbitrary URLs or launch subagents if a malicious prompt is encountered. The skill should explicitly restrict curl usage to local/trusted endpoints and disallow exfiltrating data.","The skill cross-references other skills (`golang-performance`, `golang-testing`, `golang-troubleshooting`) that are not part of this submission. If these are unavailable, the agent may fail to follow the intended workflow or spend time looking for missing references.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Needs review"]},"coverageTags":["Research","Research agents","agent-skill"]},"quality":{"score":82,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"3.0K","tone":"positive"},{"label":"Freshness","value":"2d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":["The allowed-tools list includes broad `Bash(curl:*)` and `Agent` permissions, which could be misused to fetch arbitrary URLs or launch subagents if a malicious prompt is encountered. The skill should explicitly restrict curl usage to local/trusted endpoints and disallow exfiltrating data."]},"trust":{"version":"trust-score-v4","score":75,"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":"3.0K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":77,"weight":0.08,"status":"info","detail":"3.0K stars, 197 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"2d 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 samber/cc-skills-golang --skill golang-benchmark"},{"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/samber/cc-skills-golang/tree/main/skills/golang-benchmark"},{"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":"3.0K GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"3.0K stars, 197 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2d 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 samber/cc-skills-golang --skill golang-benchmark"},{"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/samber/cc-skills-golang/tree/main/skills/golang-benchmark"},{"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","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["The allowed-tools list includes broad `Bash(curl:*)` and `Agent` permissions, which could be misused to fetch arbitrary URLs or launch subagents if a malicious prompt is encountered. The skill should explicitly restrict curl usage to local/trusted endpoints and disallow exfiltrating data.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"3.0K GitHub stars","repoActivity":"3.0K stars, 197 forks","lastPushed":"2d since push","license":"MIT","repository":"https://github.com/samber/cc-skills-golang/tree/main/skills/golang-benchmark","install":"npx skills add samber/cc-skills-golang --skill golang-benchmark","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 samber/cc-skills-golang --skill golang-benchmark","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","2d since push"]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["The allowed-tools list includes broad `Bash(curl:*)` and `Agent` permissions, which could be misused to fetch arbitrary URLs or launch subagents if a malicious prompt is encountered. The skill should explicitly restrict curl usage to local/trusted endpoints and disallow exfiltrating data.","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"],"knownRisks":["The allowed-tools list includes broad `Bash(curl:*)` and `Agent` permissions, which could be misused to fetch arbitrary URLs or launch subagents if a malicious prompt is encountered. The skill should explicitly restrict curl usage to local/trusted endpoints and disallow exfiltrating data.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":67,"base_score":75,"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":["67/100 Trust Score v5","75/100 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":"3.0K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":77,"weight":0.08,"status":"info","detail":"3.0K stars, 197 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"2d 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 samber/cc-skills-golang --skill golang-benchmark"},{"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/samber/cc-skills-golang/tree/main/skills/golang-benchmark"},{"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":"3.0K GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"3.0K stars, 197 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2d 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 samber/cc-skills-golang --skill golang-benchmark"},{"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/samber/cc-skills-golang/tree/main/skills/golang-benchmark"},{"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","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["The allowed-tools list includes broad `Bash(curl:*)` and `Agent` permissions, which could be misused to fetch arbitrary URLs or launch subagents if a malicious prompt is encountered. The skill should explicitly restrict curl usage to local/trusted endpoints and disallow exfiltrating data.","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":"3.0K GitHub stars","repoActivity":"3.0K stars, 197 forks","lastPushed":"2d since push","license":"MIT","repository":"https://github.com/samber/cc-skills-golang/tree/main/skills/golang-benchmark","install":"npx skills add samber/cc-skills-golang --skill golang-benchmark","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 samber/cc-skills-golang --skill golang-benchmark","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","2d 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":["The allowed-tools list includes broad `Bash(curl:*)` and `Agent` permissions, which could be misused to fetch arbitrary URLs or launch subagents if a malicious prompt is encountered. The skill should explicitly restrict curl usage to local/trusted endpoints and disallow exfiltrating data.","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-v3","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"],"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 samber/cc-skills-golang --skill golang-benchmark","trust_score":67,"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":["The allowed-tools list includes broad `Bash(curl:*)` and `Agent` permissions, which could be misused to fetch arbitrary URLs or launch subagents if a malicious prompt is encountered. The skill should explicitly restrict curl usage to local/trusted endpoints and disallow exfiltrating data.","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":75,"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":"needs_review","risk_label":"Needs review","warnings":["The allowed-tools list includes broad `Bash(curl:*)` and `Agent` permissions, which could be misused to fetch arbitrary URLs or launch subagents if a malicious prompt is encountered. The skill should explicitly restrict curl usage to local/trusted endpoints and disallow exfiltrating data.","The skill cross-references other skills (`golang-performance`, `golang-testing`, `golang-troubleshooting`) that are not part of this submission. If these are unavailable, the agent may fail to follow the intended workflow or spend time looking for missing references.","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":["The allowed-tools list includes broad `Bash(curl:*)` and `Agent` permissions, which could be misused to fetch arbitrary URLs or launch subagents if a malicious prompt is encountered. The skill should explicitly restrict curl usage to local/trusted endpoints and disallow exfiltrating data.","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"}],"policy_warnings":["The allowed-tools list includes broad `Bash(curl:*)` and `Agent` permissions, which could be misused to fetch arbitrary URLs or launch subagents if a malicious prompt is encountered. The skill should explicitly restrict curl usage to local/trusted endpoints and disallow exfiltrating data."],"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":["The allowed-tools list includes broad `Bash(curl:*)` and `Agent` permissions, which could be misused to fetch arbitrary URLs or launch subagents if a malicious prompt is encountered. The skill should explicitly restrict curl usage to local/trusted endpoints and disallow exfiltrating data.","72/100 agent safety score"]},"decision":{"readiness_score":93,"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 allowed-tools list includes broad `Bash(curl:*)` and `Agent` permissions, which could be misused to fetch arbitrary URLs or launch subagents if a malicious prompt is encountered. The skill should explicitly restrict curl usage to local/trusted endpoints and disallow exfiltrating data.","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 samber/cc-skills-golang --skill golang-benchmark","value":"Install the \"golang-benchmark\" agent skill from https://github.com/samber/cc-skills-golang/tree/main/skills/golang-benchmark. 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: Golang benchmarking, profiling, and performance measurement. Use when writing, running, or comparing Go benchmarks, profiling hot paths with pprof, interpreting CPU/memory/trace profiles, analyzing results with benchstat, setting up CI benchmark regression detection, or investigating production performance with Prometheus runtime metrics. Also use when the developer needs deep analysis on a specific performance indicator - this skill provides the measurement methodology, while `samber/cc-skills-golang@golang-performance` provides the optimization patterns. 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\":\"samber-golang-benchmark\",\"task\":\"Install golang-benchmark\",\"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 golang-benchmark 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-v0.2.1/openagentskill-0.2.1.tgz install samber-golang-benchmark","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 \"golang-benchmark\" agent skill from https://github.com/samber/cc-skills-golang/tree/main/skills/golang-benchmark. 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: Golang benchmarking, profiling, and performance measurement. Use when writing, running, or comparing Go benchmarks, profiling hot paths with pprof, interpreting CPU/memory/trace profiles, analyzing results with benchstat, setting up CI benchmark regression detection, or investigating production performance with Prometheus runtime metrics. Also use when the developer needs deep analysis on a specific performance indicator - this skill provides the measurement methodology, while `samber/cc-skills-golang@golang-performance` provides the optimization patterns. 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\":\"samber-golang-benchmark\",\"task\":\"Install golang-benchmark\",\"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 \"golang-benchmark\" as a Claude Code skill from https://github.com/samber/cc-skills-golang/tree/main/skills/golang-benchmark. 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: Golang benchmarking, profiling, and performance measurement. Use when writing, running, or comparing Go benchmarks, profiling hot paths with pprof, interpreting CPU/memory/trace profiles, analyzing results with benchstat, setting up CI benchmark regression detection, or investigating production performance with Prometheus runtime metrics. Also use when the developer needs deep analysis on a specific performance indicator - this skill provides the measurement methodology, while `samber/cc-skills-golang@golang-performance` provides the optimization patterns. 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\":\"samber-golang-benchmark\",\"task\":\"Install golang-benchmark\",\"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 \"golang-benchmark\" from https://github.com/samber/cc-skills-golang/tree/main/skills/golang-benchmark 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: Golang benchmarking, profiling, and performance measurement. Use when writing, running, or comparing Go benchmarks, profiling hot paths with pprof, interpreting CPU/memory/trace profiles, analyzing results with benchstat, setting up CI benchmark regression detection, or investigating production performance with Prometheus runtime metrics. Also use when the developer needs deep analysis on a specific performance indicator - this skill provides the measurement methodology, while `samber/cc-skills-golang@golang-performance` provides the optimization patterns. 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\":\"samber-golang-benchmark\",\"task\":\"Install golang-benchmark\",\"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":"samber-golang-benchmark","name":"golang-benchmark","description":"Golang benchmarking, profiling, and performance measurement. Use when writing, running, or comparing Go benchmarks, profiling hot paths with pprof, interpreting CPU/memory/trace profiles, analyzing results with benchstat, setting up CI benchmark regression detection, or investigating production performance with Prometheus runtime metrics. Also use when the developer needs deep analysis on a specific performance indicator - this skill provides the measurement methodology, while `samber/cc-skills-golang@golang-performance` provides the optimization patterns.","category":"research","url":"https://www.openagentskill.com/skills/samber-golang-benchmark","repository":"https://github.com/samber/cc-skills-golang/tree/main/skills/golang-benchmark","github_repo":"samber/cc-skills-golang"},"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":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add samber/cc-skills-golang --skill golang-benchmark","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install samber-golang-benchmark"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"golang-benchmark\" agent skill from https://github.com/samber/cc-skills-golang/tree/main/skills/golang-benchmark. 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: Golang benchmarking, profiling, and performance measurement. Use when writing, running, or comparing Go benchmarks, profiling hot paths with pprof, interpreting CPU/memory/trace profiles, analyzing results with benchstat, setting up CI benchmark regression detection, or investigating production performance with Prometheus runtime metrics. Also use when the developer needs deep analysis on a specific performance indicator - this skill provides the measurement methodology, while `samber/cc-skills-golang@golang-performance` provides the optimization patterns. 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\":\"samber-golang-benchmark\",\"task\":\"Install golang-benchmark\",\"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 \"golang-benchmark\" as a Claude Code skill from https://github.com/samber/cc-skills-golang/tree/main/skills/golang-benchmark. 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: Golang benchmarking, profiling, and performance measurement. Use when writing, running, or comparing Go benchmarks, profiling hot paths with pprof, interpreting CPU/memory/trace profiles, analyzing results with benchstat, setting up CI benchmark regression detection, or investigating production performance with Prometheus runtime metrics. Also use when the developer needs deep analysis on a specific performance indicator - this skill provides the measurement methodology, while `samber/cc-skills-golang@golang-performance` provides the optimization patterns. 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\":\"samber-golang-benchmark\",\"task\":\"Install golang-benchmark\",\"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 \"golang-benchmark\" from https://github.com/samber/cc-skills-golang/tree/main/skills/golang-benchmark 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: Golang benchmarking, profiling, and performance measurement. Use when writing, running, or comparing Go benchmarks, profiling hot paths with pprof, interpreting CPU/memory/trace profiles, analyzing results with benchstat, setting up CI benchmark regression detection, or investigating production performance with Prometheus runtime metrics. Also use when the developer needs deep analysis on a specific performance indicator - this skill provides the measurement methodology, while `samber/cc-skills-golang@golang-performance` provides the optimization patterns. 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\":\"samber-golang-benchmark\",\"task\":\"Install golang-benchmark\",\"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/samber-golang-benchmark/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/samber-golang-benchmark"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"3.0K GitHub stars","repoActivity":"3.0K stars, 197 forks","lastPushed":"2d since push","license":"MIT","repository":"https://github.com/samber/cc-skills-golang/tree/main/skills/golang-benchmark","install":"npx skills add samber/cc-skills-golang --skill golang-benchmark","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":["The allowed-tools list includes broad `Bash(curl:*)` and `Agent` permissions, which could be misused to fetch arbitrary URLs or launch subagents if a malicious prompt is encountered. The skill should explicitly restrict curl usage to local/trusted endpoints and disallow exfiltrating data.","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":84,"risk_level":"needs_review","risk_label":"Needs review","warnings":["The allowed-tools list includes broad `Bash(curl:*)` and `Agent` permissions, which could be misused to fetch arbitrary URLs or launch subagents if a malicious prompt is encountered. The skill should explicitly restrict curl usage to local/trusted endpoints and disallow exfiltrating data.","The skill cross-references other skills (`golang-performance`, `golang-testing`, `golang-troubleshooting`) that are not part of this submission. If these are unavailable, the agent may fail to follow the intended workflow or spend time looking for missing references.","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":82,"label":"Strong"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"2d 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 allowed-tools list includes broad `Bash(curl:*)` and `Agent` permissions, which could be misused to fetch arbitrary URLs or launch subagents if a malicious prompt is encountered. The skill should explicitly restrict curl usage to local/trusted endpoints and disallow exfiltrating data.","No OpenAgentSkill engagement data yet","The skill cross-references other skills (`golang-performance`, `golang-testing`, `golang-troubleshooting`) that are not part of this submission. If these are unavailable, the agent may fail to follow the intended workflow or spend time looking for missing references.","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use DynamicMap Benchmark","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 84/100 Needs review","Safety: 72/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"samber-golang-benchmark (golang-benchmark)","install_command":"npx skills add samber/cc-skills-golang --skill golang-benchmark","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":"samber-golang-benchmark","task":"Use DynamicMap Benchmark","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/samber-golang-benchmark","api":"https://www.openagentskill.com/api/agent/skills/samber-golang-benchmark","audit":"https://www.openagentskill.com/skills/samber-golang-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=samber-golang-benchmark&task=Use%20DynamicMap%20Benchmark&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20DynamicMap%20Benchmark&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20DynamicMap%20Benchmark&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/samber-golang-benchmark/install","manifest":"https://www.openagentskill.com/api/registry/manifest/samber-golang-benchmark"}},"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/samber-golang-benchmark","api":"https://www.openagentskill.com/api/agent/skills/samber-golang-benchmark","install_api":"https://www.openagentskill.com/api/skills/samber-golang-benchmark/install","audit":"https://www.openagentskill.com/skills/samber-golang-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=samber-golang-benchmark&task=Use%20DynamicMap%20Benchmark&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/samber-golang-benchmark?metric=audit","repository":"https://github.com/samber/cc-skills-golang/tree/main/skills/golang-benchmark"}},"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":175.4,"semantic_relevance":42,"skill":{"slug":"kth-rpl-dynamicmap-benchmark","name":"DynamicMap Benchmark","description":"The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating","category":"robotics-iot","github_stars":425,"created_at":"2026-06-20T18:56:56.543204+00:00","updated_at":"2025-09-22T08:40:00+00:00","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark","github_repo":"KTH-RPL/DynamicMap_Benchmark"},"recommendation_reasons":["Matches task terms: dynamicmap, benchmark","Install handoff is available","Repository freshness signal is available","Registry match score 42"],"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":"GitHub automation","description":"I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.","useCases":[{"slug":"github-automation","title":"GitHub automation"},{"slug":"local-desktop","title":"Local desktop"},{"slug":"coding-agents","title":"Coding agents"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Jupyter Notebook"],"install":{"ready":true,"command":"npx skills add KTH-RPL/DynamicMap_Benchmark","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":425,"starsLabel":"425","forks":30,"license":"BSD-3-Clause","qualityScore":60,"trustScore":75,"auditScore":73},"maintenance":{"status":"stable","label":"11mo since push","daysSincePush":334,"lastPushedAt":"2025-09-22T08:40:00+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata","Needs review"]},"coverageTags":["Coding","GitHub automation","robotics-iot","robotics","automation","autonomous-driving","benchmark","dataset"]},"quality":{"score":60,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"425","tone":"neutral"},{"label":"Freshness","value":"11mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"BSD-3-Clause","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":75,"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":"425 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"425 stars, 30 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":62,"weight":0.14,"status":"info","detail":"11mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"BSD-3-Clause"},{"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 KTH-RPL/DynamicMap_Benchmark"},{"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/KTH-RPL/DynamicMap_Benchmark"},{"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":"425 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"425 stars, 30 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"11mo since push"},{"status":"pass","label":"License clarity","detail":"BSD-3-Clause"},{"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 KTH-RPL/DynamicMap_Benchmark"},{"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/KTH-RPL/DynamicMap_Benchmark"},{"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","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"],"evidence":{"stars":"425 GitHub stars","repoActivity":"425 stars, 30 forks","lastPushed":"11mo since push","license":"BSD-3-Clause","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark","install":"npx skills add KTH-RPL/DynamicMap_Benchmark","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 KTH-RPL/DynamicMap_Benchmark","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","11mo since push"]},"agentCompatibility":["Jupyter Notebook","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"]},"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":["robotics-iot","robotics","automation","autonomous-driving","benchmark","dataset"],"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","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"]},"trust_v5":{"version":"trust-score-v5","score":67,"base_score":75,"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":["67/100 Trust Score v5","75/100 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":"425 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"425 stars, 30 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":62,"weight":0.14,"status":"info","detail":"11mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"BSD-3-Clause"},{"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 KTH-RPL/DynamicMap_Benchmark"},{"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/KTH-RPL/DynamicMap_Benchmark"},{"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":"425 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"425 stars, 30 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"11mo since push"},{"status":"pass","label":"License clarity","detail":"BSD-3-Clause"},{"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 KTH-RPL/DynamicMap_Benchmark"},{"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/KTH-RPL/DynamicMap_Benchmark"},{"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","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","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"425 GitHub stars","repoActivity":"425 stars, 30 forks","lastPushed":"11mo since push","license":"BSD-3-Clause","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark","install":"npx skills add KTH-RPL/DynamicMap_Benchmark","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 KTH-RPL/DynamicMap_Benchmark","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","11mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Jupyter Notebook","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"]},"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-v3","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"],"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":["robotics-iot","robotics","automation","autonomous-driving","benchmark","dataset"],"suited_agents":["Jupyter Notebook","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add KTH-RPL/DynamicMap_Benchmark","trust_score":67,"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":["robotics-iot","robotics","automation","autonomous-driving","benchmark","dataset"],"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","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":75,"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":73,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"]},"safety":{"score":61,"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":["Documentation summary is thin","61/100 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":["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":["Documentation summary is thin","61/100 agent safety score"]},"decision":{"readiness_score":50,"readiness_label":"Needs manual review","headline":"Needs validation for GitHub automation","role":"Needs validation","best_for":["GitHub automation workflows","general agent builders","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one GitHub automation 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 KTH-RPL/DynamicMap_Benchmark","value":"Install the \"DynamicMap Benchmark\" agent skill from https://github.com/KTH-RPL/DynamicMap_Benchmark. 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: The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating 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\":\"kth-rpl-dynamicmap-benchmark\",\"task\":\"Install DynamicMap Benchmark\",\"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 DynamicMap Benchmark 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-v0.2.1/openagentskill-0.2.1.tgz install kth-rpl-dynamicmap-benchmark","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 \"DynamicMap Benchmark\" agent skill from https://github.com/KTH-RPL/DynamicMap_Benchmark. 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: The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating 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\":\"kth-rpl-dynamicmap-benchmark\",\"task\":\"Install DynamicMap Benchmark\",\"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 \"DynamicMap Benchmark\" as a Claude Code skill from https://github.com/KTH-RPL/DynamicMap_Benchmark. 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: The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating 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\":\"kth-rpl-dynamicmap-benchmark\",\"task\":\"Install DynamicMap Benchmark\",\"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 \"DynamicMap Benchmark\" from https://github.com/KTH-RPL/DynamicMap_Benchmark 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: The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating 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\":\"kth-rpl-dynamicmap-benchmark\",\"task\":\"Install DynamicMap Benchmark\",\"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":"kth-rpl-dynamicmap-benchmark","name":"DynamicMap Benchmark","description":"The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating","category":"robotics-iot","url":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark","github_repo":"KTH-RPL/DynamicMap_Benchmark"},"suited_tasks":["GitHub automation workflows","general agent builders","builders willing to evaluate younger projects","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Navigate local resources","Run repeatable desktop actions"],"suited_agents":["Jupyter Notebook","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add KTH-RPL/DynamicMap_Benchmark","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install kth-rpl-dynamicmap-benchmark"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"DynamicMap Benchmark\" agent skill from https://github.com/KTH-RPL/DynamicMap_Benchmark. 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: The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating 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\":\"kth-rpl-dynamicmap-benchmark\",\"task\":\"Install DynamicMap Benchmark\",\"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 \"DynamicMap Benchmark\" as a Claude Code skill from https://github.com/KTH-RPL/DynamicMap_Benchmark. 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: The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating 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\":\"kth-rpl-dynamicmap-benchmark\",\"task\":\"Install DynamicMap Benchmark\",\"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 \"DynamicMap Benchmark\" from https://github.com/KTH-RPL/DynamicMap_Benchmark 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: The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating 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\":\"kth-rpl-dynamicmap-benchmark\",\"task\":\"Install DynamicMap Benchmark\",\"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/kth-rpl-dynamicmap-benchmark/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/kth-rpl-dynamicmap-benchmark"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"425 GitHub stars","repoActivity":"425 stars, 30 forks","lastPushed":"11mo since push","license":"BSD-3-Clause","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark","install":"npx skills add KTH-RPL/DynamicMap_Benchmark","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":["robotics-iot","robotics","automation","autonomous-driving","benchmark","dataset"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"]},"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":73,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"]},"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":60,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"11mo 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","Documentation summary is thin","Quality score needs review","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata","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 DynamicMap Benchmark","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 73/100 Needs review","Safety: 61/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"kth-rpl-dynamicmap-benchmark (DynamicMap Benchmark)","install_command":"npx skills add KTH-RPL/DynamicMap_Benchmark","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":"kth-rpl-dynamicmap-benchmark","task":"Use DynamicMap Benchmark","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/kth-rpl-dynamicmap-benchmark","api":"https://www.openagentskill.com/api/agent/skills/kth-rpl-dynamicmap-benchmark","audit":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=kth-rpl-dynamicmap-benchmark&task=Use%20DynamicMap%20Benchmark&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20DynamicMap%20Benchmark&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20DynamicMap%20Benchmark&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/kth-rpl-dynamicmap-benchmark/install","manifest":"https://www.openagentskill.com/api/registry/manifest/kth-rpl-dynamicmap-benchmark"}},"use_cases":[{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"}],"urls":{"web":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark","api":"https://www.openagentskill.com/api/agent/skills/kth-rpl-dynamicmap-benchmark","install_api":"https://www.openagentskill.com/api/skills/kth-rpl-dynamicmap-benchmark/install","audit":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=kth-rpl-dynamicmap-benchmark&task=Use%20DynamicMap%20Benchmark&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/kth-rpl-dynamicmap-benchmark?metric=audit","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark"}},"alternatives":[{"rank":2,"match_score":30,"raw_match_score":110.9,"semantic_relevance":30,"skill":{"slug":"gmberton-deep-visual-geo-localization-benchmark","name":"Deep Visual Geo Localization Benchmark","description":"Official code for CVPR 2022 (Oral) paper \"Deep Visual Geo-localization Benchmark\"","category":"robotics-iot","github_stars":256,"created_at":"2026-06-21T01:57:11.053198+00:00","updated_at":"2026-03-15T09:50:51+00:00","repository":"https://github.com/gmberton/deep-visual-geo-localization-benchmark","github_repo":"gmberton/deep-visual-geo-localization-benchmark"},"recommendation_reasons":["Matches task terms: benchmark","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":"multimodal-media","title":"Multimodal media"},{"slug":"local-desktop","title":"Local desktop"},{"slug":"coding-agents","title":"Coding agents"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add gmberton/deep-visual-geo-localization-benchmark","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":256,"starsLabel":"256","forks":32,"license":"MIT","qualityScore":65,"trustScore":77,"auditScore":77},"maintenance":{"status":"active","label":"5mo since push","daysSincePush":160,"lastPushedAt":"2026-03-15T09:50:51+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 256 stars, 32 forks; issue activity unavailable in current metadata","Needs review"]},"coverageTags":["Coding","Coding agents","robotics-iot","computer-vision","automation","benchmark","datasets","deep-learning"]},"quality":{"score":65,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"256","tone":"neutral"},{"label":"Freshness","value":"5mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":77,"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":"256 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"256 stars, 32 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"5mo 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 gmberton/deep-visual-geo-localization-benchmark"},{"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/gmberton/deep-visual-geo-localization-benchmark"},{"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":"256 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"256 stars, 32 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"5mo 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 gmberton/deep-visual-geo-localization-benchmark"},{"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/gmberton/deep-visual-geo-localization-benchmark"},{"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","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 256 stars, 32 forks; issue activity unavailable in current metadata"],"evidence":{"stars":"256 GitHub stars","repoActivity":"256 stars, 32 forks","lastPushed":"5mo since push","license":"MIT","repository":"https://github.com/gmberton/deep-visual-geo-localization-benchmark","install":"npx skills add gmberton/deep-visual-geo-localization-benchmark","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 gmberton/deep-visual-geo-localization-benchmark","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","5mo since push"]},"agentCompatibility":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 256 stars, 32 forks; issue activity unavailable in current metadata"]},"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":["robotics-iot","computer-vision","automation","benchmark","datasets","deep-learning"],"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","Stars/forks activity: 256 stars, 32 forks; issue activity unavailable in current metadata"]},"trust_v5":{"version":"trust-score-v5","score":69,"base_score":77,"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":["69/100 Trust Score v5","77/100 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":"256 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"256 stars, 32 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"5mo 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 gmberton/deep-visual-geo-localization-benchmark"},{"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/gmberton/deep-visual-geo-localization-benchmark"},{"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":"256 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"256 stars, 32 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"5mo 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 gmberton/deep-visual-geo-localization-benchmark"},{"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/gmberton/deep-visual-geo-localization-benchmark"},{"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","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","Stars/forks activity: 256 stars, 32 forks; issue activity unavailable in current metadata","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"256 GitHub stars","repoActivity":"256 stars, 32 forks","lastPushed":"5mo since push","license":"MIT","repository":"https://github.com/gmberton/deep-visual-geo-localization-benchmark","install":"npx skills add gmberton/deep-visual-geo-localization-benchmark","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 gmberton/deep-visual-geo-localization-benchmark","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","5mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 256 stars, 32 forks; issue activity unavailable in current metadata"]},"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-v3","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"],"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":["robotics-iot","computer-vision","automation","benchmark","datasets","deep-learning"],"suited_agents":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add gmberton/deep-visual-geo-localization-benchmark","trust_score":69,"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":["robotics-iot","computer-vision","automation","benchmark","datasets","deep-learning"],"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","Stars/forks activity: 256 stars, 32 forks; issue activity unavailable in current metadata"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":77,"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":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 256 stars, 32 forks; issue activity unavailable in current metadata"]},"safety":{"score":65,"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":["Documentation summary is thin","65/100 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":["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":["Documentation summary is thin","65/100 agent safety score"]},"decision":{"readiness_score":64,"readiness_label":"Prototype first","headline":"Fallback candidate for Multimodal media","role":"Fallback candidate","best_for":["Multimodal media workflows","general agent builders","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Multimodal media 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 gmberton/deep-visual-geo-localization-benchmark","value":"Install the \"Deep Visual Geo Localization Benchmark\" agent skill from https://github.com/gmberton/deep-visual-geo-localization-benchmark. 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: Official code for CVPR 2022 (Oral) paper \"Deep Visual Geo-localization Benchmark\" 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\":\"gmberton-deep-visual-geo-localization-benchmark\",\"task\":\"Install Deep Visual Geo Localization Benchmark\",\"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 Deep Visual Geo Localization Benchmark 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-v0.2.1/openagentskill-0.2.1.tgz install gmberton-deep-visual-geo-localization-benchmark","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 \"Deep Visual Geo Localization Benchmark\" agent skill from https://github.com/gmberton/deep-visual-geo-localization-benchmark. 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: Official code for CVPR 2022 (Oral) paper \"Deep Visual Geo-localization Benchmark\" 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\":\"gmberton-deep-visual-geo-localization-benchmark\",\"task\":\"Install Deep Visual Geo Localization Benchmark\",\"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 \"Deep Visual Geo Localization Benchmark\" as a Claude Code skill from https://github.com/gmberton/deep-visual-geo-localization-benchmark. 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: Official code for CVPR 2022 (Oral) paper \"Deep Visual Geo-localization Benchmark\" 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\":\"gmberton-deep-visual-geo-localization-benchmark\",\"task\":\"Install Deep Visual Geo Localization Benchmark\",\"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 \"Deep Visual Geo Localization Benchmark\" from https://github.com/gmberton/deep-visual-geo-localization-benchmark 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: Official code for CVPR 2022 (Oral) paper \"Deep Visual Geo-localization Benchmark\" 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\":\"gmberton-deep-visual-geo-localization-benchmark\",\"task\":\"Install Deep Visual Geo Localization Benchmark\",\"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":"gmberton-deep-visual-geo-localization-benchmark","name":"Deep Visual Geo Localization Benchmark","description":"Official code for CVPR 2022 (Oral) paper \"Deep Visual Geo-localization Benchmark\"","category":"robotics-iot","url":"https://www.openagentskill.com/skills/gmberton-deep-visual-geo-localization-benchmark","repository":"https://github.com/gmberton/deep-visual-geo-localization-benchmark","github_repo":"gmberton/deep-visual-geo-localization-benchmark"},"suited_tasks":["Multimodal media workflows","general agent builders","builders willing to evaluate younger projects","Read media metadata","Convert formats","Summarize visual or audio content","Navigate local resources","Run repeatable desktop actions"],"suited_agents":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add gmberton/deep-visual-geo-localization-benchmark","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install gmberton-deep-visual-geo-localization-benchmark"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Deep Visual Geo Localization Benchmark\" agent skill from https://github.com/gmberton/deep-visual-geo-localization-benchmark. 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: Official code for CVPR 2022 (Oral) paper \"Deep Visual Geo-localization Benchmark\" 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\":\"gmberton-deep-visual-geo-localization-benchmark\",\"task\":\"Install Deep Visual Geo Localization Benchmark\",\"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 \"Deep Visual Geo Localization Benchmark\" as a Claude Code skill from https://github.com/gmberton/deep-visual-geo-localization-benchmark. 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: Official code for CVPR 2022 (Oral) paper \"Deep Visual Geo-localization Benchmark\" 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\":\"gmberton-deep-visual-geo-localization-benchmark\",\"task\":\"Install Deep Visual Geo Localization Benchmark\",\"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 \"Deep Visual Geo Localization Benchmark\" from https://github.com/gmberton/deep-visual-geo-localization-benchmark 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: Official code for CVPR 2022 (Oral) paper \"Deep Visual Geo-localization Benchmark\" 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\":\"gmberton-deep-visual-geo-localization-benchmark\",\"task\":\"Install Deep Visual Geo Localization Benchmark\",\"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/gmberton-deep-visual-geo-localization-benchmark/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/gmberton-deep-visual-geo-localization-benchmark"},"trust":{"score":77,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"256 GitHub stars","repoActivity":"256 stars, 32 forks","lastPushed":"5mo since push","license":"MIT","repository":"https://github.com/gmberton/deep-visual-geo-localization-benchmark","install":"npx skills add gmberton/deep-visual-geo-localization-benchmark","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":["robotics-iot","computer-vision","automation","benchmark","datasets","deep-learning"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 256 stars, 32 forks; issue activity unavailable in current metadata"]},"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":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 256 stars, 32 forks; issue activity unavailable in current metadata"]},"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":65,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"5mo 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","Documentation summary is thin","Quality score needs review","Stars/forks activity: 256 stars, 32 forks; issue activity unavailable in current metadata","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 DynamicMap Benchmark","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 77/100 Strong shortlist","Audit: 77/100 Needs review","Safety: 65/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"gmberton-deep-visual-geo-localization-benchmark (Deep Visual Geo Localization Benchmark)","install_command":"npx skills add gmberton/deep-visual-geo-localization-benchmark","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":"gmberton-deep-visual-geo-localization-benchmark","task":"Use DynamicMap Benchmark","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/gmberton-deep-visual-geo-localization-benchmark","api":"https://www.openagentskill.com/api/agent/skills/gmberton-deep-visual-geo-localization-benchmark","audit":"https://www.openagentskill.com/skills/gmberton-deep-visual-geo-localization-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=gmberton-deep-visual-geo-localization-benchmark&task=Use%20DynamicMap%20Benchmark&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20DynamicMap%20Benchmark&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20DynamicMap%20Benchmark&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/gmberton-deep-visual-geo-localization-benchmark/install","manifest":"https://www.openagentskill.com/api/registry/manifest/gmberton-deep-visual-geo-localization-benchmark"}},"use_cases":[{"slug":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"},{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"}],"urls":{"web":"https://www.openagentskill.com/skills/gmberton-deep-visual-geo-localization-benchmark","api":"https://www.openagentskill.com/api/agent/skills/gmberton-deep-visual-geo-localization-benchmark","install_api":"https://www.openagentskill.com/api/skills/gmberton-deep-visual-geo-localization-benchmark/install","audit":"https://www.openagentskill.com/skills/gmberton-deep-visual-geo-localization-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=gmberton-deep-visual-geo-localization-benchmark&task=Use%20DynamicMap%20Benchmark&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/gmberton-deep-visual-geo-localization-benchmark?metric=audit","repository":"https://github.com/gmberton/deep-visual-geo-localization-benchmark"}},{"rank":3,"match_score":30,"raw_match_score":108.7,"semantic_relevance":30,"skill":{"slug":"zeyofu-blink-benchmark","name":"BLINK Benchmark","description":"This repo contains evaluation code for the paper \"BLINK: Multimodal Large Language Models Can See but Not Perceive\".     https://arxiv.org/abs/2404.12390  [ECCV 2024]","category":"robotics-iot","github_stars":169,"created_at":"2026-06-21T02:02:12.427407+00:00","updated_at":"2025-09-27T20:06:21+00:00","repository":"https://github.com/zeyofu/BLINK_Benchmark","github_repo":"zeyofu/BLINK_Benchmark"},"recommendation_reasons":["Matches task terms: benchmark","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":"multimodal-media","title":"Multimodal media"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add zeyofu/BLINK_Benchmark","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":169,"starsLabel":"169","forks":8,"license":"Apache-2.0","qualityScore":55,"trustScore":74,"auditScore":71},"maintenance":{"status":"stable","label":"11mo since push","daysSincePush":329,"lastPushedAt":"2025-09-27T20:06:21+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 169 stars, 8 forks; issue activity unavailable in current metadata","Needs review"]},"coverageTags":["Coding","Coding agents","robotics-iot","computer-vision","automation","3d-understanding","ai","benchmark"]},"quality":{"score":55,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"169","tone":"neutral"},{"label":"Freshness","value":"11mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":74,"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":"169 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":51,"weight":0.08,"status":"warn","detail":"169 stars, 8 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":62,"weight":0.14,"status":"info","detail":"11mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"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 zeyofu/BLINK_Benchmark"},{"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/zeyofu/BLINK_Benchmark"},{"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":"169 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"169 stars, 8 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"11mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"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 zeyofu/BLINK_Benchmark"},{"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/zeyofu/BLINK_Benchmark"},{"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","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 169 stars, 8 forks; issue activity unavailable in current metadata"],"evidence":{"stars":"169 GitHub stars","repoActivity":"169 stars, 8 forks","lastPushed":"11mo since push","license":"Apache-2.0","repository":"https://github.com/zeyofu/BLINK_Benchmark","install":"npx skills add zeyofu/BLINK_Benchmark","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add zeyofu/BLINK_Benchmark","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","11mo since push"]},"agentCompatibility":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 169 stars, 8 forks; issue activity unavailable in current metadata"]},"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":["robotics-iot","computer-vision","automation","3d-understanding","ai","benchmark"],"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","Stars/forks activity: 169 stars, 8 forks; issue activity unavailable in current metadata"]},"trust_v5":{"version":"trust-score-v5","score":66,"base_score":74,"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":["66/100 Trust Score v5","74/100 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":"169 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":51,"weight":0.08,"status":"warn","detail":"169 stars, 8 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":62,"weight":0.14,"status":"info","detail":"11mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"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 zeyofu/BLINK_Benchmark"},{"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/zeyofu/BLINK_Benchmark"},{"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":"169 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"169 stars, 8 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"11mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"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 zeyofu/BLINK_Benchmark"},{"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/zeyofu/BLINK_Benchmark"},{"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","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","Stars/forks activity: 169 stars, 8 forks; issue activity unavailable in current metadata","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"169 GitHub stars","repoActivity":"169 stars, 8 forks","lastPushed":"11mo since push","license":"Apache-2.0","repository":"https://github.com/zeyofu/BLINK_Benchmark","install":"npx skills add zeyofu/BLINK_Benchmark","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","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 zeyofu/BLINK_Benchmark","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","11mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 169 stars, 8 forks; issue activity unavailable in current metadata"]},"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-v3","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"],"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":["robotics-iot","computer-vision","automation","3d-understanding","ai","benchmark"],"suited_agents":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add zeyofu/BLINK_Benchmark","trust_score":66,"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":["robotics-iot","computer-vision","automation","3d-understanding","ai","benchmark"],"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","Stars/forks activity: 169 stars, 8 forks; issue activity unavailable in current metadata"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":74,"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":71,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 169 stars, 8 forks; issue activity unavailable in current metadata"]},"safety":{"score":55,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","summary":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","auto_install_policy":"review","reasons":["Quality score needs review","55/100 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":["Quality score needs review"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","reasons":["Quality score needs review","55/100 agent safety score"]},"decision":{"readiness_score":45,"readiness_label":"Needs manual review","headline":"Needs validation for Multimodal media","role":"Needs validation","best_for":["Multimodal media workflows","general agent builders","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Multimodal media 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 zeyofu/BLINK_Benchmark","value":"Install the \"BLINK Benchmark\" agent skill from https://github.com/zeyofu/BLINK_Benchmark. 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: This repo contains evaluation code for the paper \"BLINK: Multimodal Large Language Models Can See but Not Perceive\". https://arxiv.org/abs/2404.12390 [ECCV 2024] 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\":\"zeyofu-blink-benchmark\",\"task\":\"Install BLINK Benchmark\",\"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 BLINK Benchmark 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-v0.2.1/openagentskill-0.2.1.tgz install zeyofu-blink-benchmark","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 \"BLINK Benchmark\" agent skill from https://github.com/zeyofu/BLINK_Benchmark. 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: This repo contains evaluation code for the paper \"BLINK: Multimodal Large Language Models Can See but Not Perceive\". https://arxiv.org/abs/2404.12390 [ECCV 2024] 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\":\"zeyofu-blink-benchmark\",\"task\":\"Install BLINK Benchmark\",\"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 \"BLINK Benchmark\" as a Claude Code skill from https://github.com/zeyofu/BLINK_Benchmark. 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: This repo contains evaluation code for the paper \"BLINK: Multimodal Large Language Models Can See but Not Perceive\". https://arxiv.org/abs/2404.12390 [ECCV 2024] 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\":\"zeyofu-blink-benchmark\",\"task\":\"Install BLINK Benchmark\",\"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 \"BLINK Benchmark\" from https://github.com/zeyofu/BLINK_Benchmark 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: This repo contains evaluation code for the paper \"BLINK: Multimodal Large Language Models Can See but Not Perceive\". https://arxiv.org/abs/2404.12390 [ECCV 2024] 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\":\"zeyofu-blink-benchmark\",\"task\":\"Install BLINK Benchmark\",\"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":"zeyofu-blink-benchmark","name":"BLINK Benchmark","description":"This repo contains evaluation code for the paper \"BLINK: Multimodal Large Language Models Can See but Not Perceive\".     https://arxiv.org/abs/2404.12390  [ECCV 2024]","category":"robotics-iot","url":"https://www.openagentskill.com/skills/zeyofu-blink-benchmark","repository":"https://github.com/zeyofu/BLINK_Benchmark","github_repo":"zeyofu/BLINK_Benchmark"},"suited_tasks":["Multimodal media workflows","general agent builders","builders willing to evaluate younger projects","Read media metadata","Convert formats","Summarize visual or audio content","Inspect source files","Explain architecture"],"suited_agents":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add zeyofu/BLINK_Benchmark","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install zeyofu-blink-benchmark"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"BLINK Benchmark\" agent skill from https://github.com/zeyofu/BLINK_Benchmark. 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: This repo contains evaluation code for the paper \"BLINK: Multimodal Large Language Models Can See but Not Perceive\". https://arxiv.org/abs/2404.12390 [ECCV 2024] 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\":\"zeyofu-blink-benchmark\",\"task\":\"Install BLINK Benchmark\",\"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 \"BLINK Benchmark\" as a Claude Code skill from https://github.com/zeyofu/BLINK_Benchmark. 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: This repo contains evaluation code for the paper \"BLINK: Multimodal Large Language Models Can See but Not Perceive\". https://arxiv.org/abs/2404.12390 [ECCV 2024] 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\":\"zeyofu-blink-benchmark\",\"task\":\"Install BLINK Benchmark\",\"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 \"BLINK Benchmark\" from https://github.com/zeyofu/BLINK_Benchmark 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: This repo contains evaluation code for the paper \"BLINK: Multimodal Large Language Models Can See but Not Perceive\". https://arxiv.org/abs/2404.12390 [ECCV 2024] 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\":\"zeyofu-blink-benchmark\",\"task\":\"Install BLINK Benchmark\",\"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/zeyofu-blink-benchmark/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/zeyofu-blink-benchmark"},"trust":{"score":74,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"169 GitHub stars","repoActivity":"169 stars, 8 forks","lastPushed":"11mo since push","license":"Apache-2.0","repository":"https://github.com/zeyofu/BLINK_Benchmark","install":"npx skills add zeyofu/BLINK_Benchmark","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","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":["robotics-iot","computer-vision","automation","3d-understanding","ai","benchmark"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 169 stars, 8 forks; issue activity unavailable in current metadata"]},"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":71,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 169 stars, 8 forks; issue activity unavailable in current metadata"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":55,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"11mo 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","Documentation summary is thin","Stars/forks activity: 169 stars, 8 forks; issue activity unavailable in current metadata","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 DynamicMap Benchmark","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 74/100 Strong shortlist","Audit: 71/100 Needs review","Safety: 55/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"zeyofu-blink-benchmark (BLINK Benchmark)","install_command":"npx skills add zeyofu/BLINK_Benchmark","risk_summary":"Needs review; Experimental; 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":"zeyofu-blink-benchmark","task":"Use DynamicMap Benchmark","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/zeyofu-blink-benchmark","api":"https://www.openagentskill.com/api/agent/skills/zeyofu-blink-benchmark","audit":"https://www.openagentskill.com/skills/zeyofu-blink-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=zeyofu-blink-benchmark&task=Use%20DynamicMap%20Benchmark&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20DynamicMap%20Benchmark&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20DynamicMap%20Benchmark&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/zeyofu-blink-benchmark/install","manifest":"https://www.openagentskill.com/api/registry/manifest/zeyofu-blink-benchmark"}},"use_cases":[{"slug":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"urls":{"web":"https://www.openagentskill.com/skills/zeyofu-blink-benchmark","api":"https://www.openagentskill.com/api/agent/skills/zeyofu-blink-benchmark","install_api":"https://www.openagentskill.com/api/skills/zeyofu-blink-benchmark/install","audit":"https://www.openagentskill.com/skills/zeyofu-blink-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=zeyofu-blink-benchmark&task=Use%20DynamicMap%20Benchmark&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/zeyofu-blink-benchmark?metric=audit","repository":"https://github.com/zeyofu/BLINK_Benchmark"}},{"rank":4,"match_score":30,"raw_match_score":106.7,"semantic_relevance":30,"skill":{"slug":"hyperledger-caliper-caliper-benchmarks","name":"Caliper Benchmarks","description":"Sample benchmark files for Hyperledger Caliper https://wiki.hyperledger.org/display/caliper","category":"web3-analytics","github_stars":117,"created_at":"2026-06-21T04:56:56.989697+00:00","updated_at":"2025-04-24T08:13:11+00:00","repository":"https://github.com/hyperledger-caliper/caliper-benchmarks","github_repo":"hyperledger-caliper/caliper-benchmarks"},"recommendation_reasons":["Matches task terms: benchmark","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":"GitHub automation","description":"I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.","useCases":[{"slug":"github-automation","title":"GitHub automation"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"workflow-automation","title":"Workflow automation"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","JavaScript"],"install":{"ready":true,"command":"npx skills add hyperledger-caliper/caliper-benchmarks","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":117,"starsLabel":"117","forks":127,"license":"Apache-2.0","qualityScore":41,"trustScore":73,"auditScore":64},"maintenance":{"status":"stale","label":"1y since push","daysSincePush":485,"lastPushedAt":"2025-04-24T08:13:11+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push"]},"coverageTags":["Coding","GitHub automation","web3-analytics","blockchain","web3","analytics","benchmark","caliper"]},"quality":{"score":41,"tier":"review","label":"Needs review","summary":"Inspect the repository carefully before adding it to an agent workflow.","signals":[{"label":"GitHub stars","value":"117","tone":"neutral"},{"label":"Freshness","value":"1y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":73,"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":"117 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":62,"weight":0.08,"status":"info","detail":"117 stars, 127 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":38,"weight":0.14,"status":"fail","detail":"1y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"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 hyperledger-caliper/caliper-benchmarks"},{"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/hyperledger-caliper/caliper-benchmarks"},{"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":"117 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"117 stars, 127 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"1y since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"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 hyperledger-caliper/caliper-benchmarks"},{"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/hyperledger-caliper/caliper-benchmarks"},{"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","Install command has no obvious high-risk pattern"],"warnings":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push"],"evidence":{"stars":"117 GitHub stars","repoActivity":"117 stars, 127 forks","lastPushed":"1y since push","license":"Apache-2.0","repository":"https://github.com/hyperledger-caliper/caliper-benchmarks","install":"npx skills add hyperledger-caliper/caliper-benchmarks","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 hyperledger-caliper/caliper-benchmarks","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","1y since push"]},"agentCompatibility":["JavaScript","Blockchain","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push"]},"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":["web3-analytics","blockchain","web3","analytics","benchmark","caliper"],"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":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push"]},"trust_v5":{"version":"trust-score-v5","score":65,"base_score":73,"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":["65/100 Trust Score v5","73/100 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":"117 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":62,"weight":0.08,"status":"info","detail":"117 stars, 127 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":38,"weight":0.14,"status":"fail","detail":"1y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"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 hyperledger-caliper/caliper-benchmarks"},{"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/hyperledger-caliper/caliper-benchmarks"},{"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":"117 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"117 stars, 127 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"1y since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"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 hyperledger-caliper/caliper-benchmarks"},{"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/hyperledger-caliper/caliper-benchmarks"},{"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","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"117 GitHub stars","repoActivity":"117 stars, 127 forks","lastPushed":"1y since push","license":"Apache-2.0","repository":"https://github.com/hyperledger-caliper/caliper-benchmarks","install":"npx skills add hyperledger-caliper/caliper-benchmarks","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 hyperledger-caliper/caliper-benchmarks","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","1y since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["JavaScript","Blockchain","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push"]},"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-v3","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"],"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":["web3-analytics","blockchain","web3","analytics","benchmark","caliper"],"suited_agents":["JavaScript","Blockchain","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add hyperledger-caliper/caliper-benchmarks","trust_score":65,"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":["web3-analytics","blockchain","web3","analytics","benchmark","caliper"],"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":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":73,"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":64,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push"]},"safety":{"score":48,"level":"avoid_auto_install","label":"Avoid automatic install","safety_tier":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","summary":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","auto_install_policy":"review","reasons":["Documentation summary is thin","48/100 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":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","reasons":["Documentation summary is thin","48/100 agent safety score"]},"decision":{"readiness_score":31,"readiness_label":"Needs manual review","headline":"Needs validation for GitHub automation","role":"Needs validation","best_for":["GitHub automation workflows","general agent builders","builders willing to evaluate younger projects"],"risks":["Repository looks stale","No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one GitHub automation 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 hyperledger-caliper/caliper-benchmarks","value":"Install the \"Caliper Benchmarks\" agent skill from https://github.com/hyperledger-caliper/caliper-benchmarks. 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: Sample benchmark files for Hyperledger Caliper https://wiki.hyperledger.org/display/caliper 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\":\"hyperledger-caliper-caliper-benchmarks\",\"task\":\"Install Caliper Benchmarks\",\"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 Caliper Benchmarks 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-v0.2.1/openagentskill-0.2.1.tgz install hyperledger-caliper-caliper-benchmarks","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 \"Caliper Benchmarks\" agent skill from https://github.com/hyperledger-caliper/caliper-benchmarks. 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: Sample benchmark files for Hyperledger Caliper https://wiki.hyperledger.org/display/caliper 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\":\"hyperledger-caliper-caliper-benchmarks\",\"task\":\"Install Caliper Benchmarks\",\"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 \"Caliper Benchmarks\" as a Claude Code skill from https://github.com/hyperledger-caliper/caliper-benchmarks. 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: Sample benchmark files for Hyperledger Caliper https://wiki.hyperledger.org/display/caliper 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\":\"hyperledger-caliper-caliper-benchmarks\",\"task\":\"Install Caliper Benchmarks\",\"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 \"Caliper Benchmarks\" from https://github.com/hyperledger-caliper/caliper-benchmarks 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: Sample benchmark files for Hyperledger Caliper https://wiki.hyperledger.org/display/caliper 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\":\"hyperledger-caliper-caliper-benchmarks\",\"task\":\"Install Caliper Benchmarks\",\"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":"hyperledger-caliper-caliper-benchmarks","name":"Caliper Benchmarks","description":"Sample benchmark files for Hyperledger Caliper https://wiki.hyperledger.org/display/caliper","category":"web3-analytics","url":"https://www.openagentskill.com/skills/hyperledger-caliper-caliper-benchmarks","repository":"https://github.com/hyperledger-caliper/caliper-benchmarks","github_repo":"hyperledger-caliper/caliper-benchmarks"},"suited_tasks":["GitHub automation workflows","general agent builders","builders willing to evaluate younger projects","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["JavaScript","Blockchain","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add hyperledger-caliper/caliper-benchmarks","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install hyperledger-caliper-caliper-benchmarks"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Caliper Benchmarks\" agent skill from https://github.com/hyperledger-caliper/caliper-benchmarks. 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: Sample benchmark files for Hyperledger Caliper https://wiki.hyperledger.org/display/caliper 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\":\"hyperledger-caliper-caliper-benchmarks\",\"task\":\"Install Caliper Benchmarks\",\"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 \"Caliper Benchmarks\" as a Claude Code skill from https://github.com/hyperledger-caliper/caliper-benchmarks. 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: Sample benchmark files for Hyperledger Caliper https://wiki.hyperledger.org/display/caliper 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\":\"hyperledger-caliper-caliper-benchmarks\",\"task\":\"Install Caliper Benchmarks\",\"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 \"Caliper Benchmarks\" from https://github.com/hyperledger-caliper/caliper-benchmarks 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: Sample benchmark files for Hyperledger Caliper https://wiki.hyperledger.org/display/caliper 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\":\"hyperledger-caliper-caliper-benchmarks\",\"task\":\"Install Caliper Benchmarks\",\"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/hyperledger-caliper-caliper-benchmarks/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/hyperledger-caliper-caliper-benchmarks"},"trust":{"score":73,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"117 GitHub stars","repoActivity":"117 stars, 127 forks","lastPushed":"1y since push","license":"Apache-2.0","repository":"https://github.com/hyperledger-caliper/caliper-benchmarks","install":"npx skills add hyperledger-caliper/caliper-benchmarks","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":["web3-analytics","blockchain","web3","analytics","benchmark","caliper"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push"]},"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":64,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":41,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"1y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Documentation summary is thin","Repository appears stale","Quality score needs review","Recent maintenance: 1y since push"],"agent_contract":{"task_input":"Use DynamicMap Benchmark","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 73/100 Strong shortlist","Audit: 64/100 Needs review","Safety: 48/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"hyperledger-caliper-caliper-benchmarks (Caliper Benchmarks)","install_command":"npx skills add hyperledger-caliper/caliper-benchmarks","risk_summary":"Needs review; Experimental; 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":"hyperledger-caliper-caliper-benchmarks","task":"Use DynamicMap Benchmark","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/hyperledger-caliper-caliper-benchmarks","api":"https://www.openagentskill.com/api/agent/skills/hyperledger-caliper-caliper-benchmarks","audit":"https://www.openagentskill.com/skills/hyperledger-caliper-caliper-benchmarks/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=hyperledger-caliper-caliper-benchmarks&task=Use%20DynamicMap%20Benchmark&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20DynamicMap%20Benchmark&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20DynamicMap%20Benchmark&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/hyperledger-caliper-caliper-benchmarks/install","manifest":"https://www.openagentskill.com/api/registry/manifest/hyperledger-caliper-caliper-benchmarks"}},"use_cases":[{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"urls":{"web":"https://www.openagentskill.com/skills/hyperledger-caliper-caliper-benchmarks","api":"https://www.openagentskill.com/api/agent/skills/hyperledger-caliper-caliper-benchmarks","install_api":"https://www.openagentskill.com/api/skills/hyperledger-caliper-caliper-benchmarks/install","audit":"https://www.openagentskill.com/skills/hyperledger-caliper-caliper-benchmarks/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=hyperledger-caliper-caliper-benchmarks&task=Use%20DynamicMap%20Benchmark&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/hyperledger-caliper-caliper-benchmarks?metric=audit","repository":"https://github.com/hyperledger-caliper/caliper-benchmarks"}},{"rank":5,"match_score":30,"raw_match_score":105.3,"semantic_relevance":30,"skill":{"slug":"jeinlee1991-chinese-llm-benchmark","name":"Chinese Llm Benchmark","description":"非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。","category":"agent-frameworks","github_stars":6163,"created_at":"2026-05-23T07:49:07.381504+00:00","updated_at":"2026-06-07T05:11:36+00:00","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","github_repo":"jeinlee1991/chinese-llm-benchmark"},"recommendation_reasons":["Matches task terms: benchmark","Useful GitHub adoption: 6,163 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":"GitHub automation","description":"I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.","useCases":[{"slug":"github-automation","title":"GitHub automation"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"testing-qa","title":"Testing and QA"}]},"applicableAgents":["Claude Code","OpenAI Agents","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add jeinlee1991/chinese-llm-benchmark","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":6163,"starsLabel":"6.2K","forks":250,"license":"Unknown","qualityScore":98,"trustScore":85,"auditScore":89},"maintenance":{"status":"active","label":"3mo since push","daysSincePush":76,"lastPushedAt":"2026-06-07T05:11:36+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["License is unclear","License clarity: Unknown"]},"coverageTags":["Coding","GitHub automation","agent-frameworks","llm-agent","agents","agentic-ai","artificial-intelligence","llm-evaluation"]},"quality":{"score":98,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"6.2K","tone":"positive"},{"label":"Freshness","value":"3mo 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":94,"weight":0.13,"status":"pass","detail":"6.2K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"6.2K stars, 250 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"3mo 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 jeinlee1991/chinese-llm-benchmark"},{"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/jeinlee1991/chinese-llm-benchmark"},{"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":"6.2K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"6.2K stars, 250 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3mo 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 jeinlee1991/chinese-llm-benchmark"},{"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/jeinlee1991/chinese-llm-benchmark"},{"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":["License is unclear","License clarity: Unknown"],"evidence":{"stars":"6.2K GitHub stars","repoActivity":"6.2K stars, 250 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","install":"npx skills add jeinlee1991/chinese-llm-benchmark","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 jeinlee1991/chinese-llm-benchmark","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","3mo since push"]},"agentCompatibility":["LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","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","llm-agent","agents","agentic-ai","artificial-intelligence","llm-evaluation"],"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","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":94,"weight":0.13,"status":"pass","detail":"6.2K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"6.2K stars, 250 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"3mo 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 jeinlee1991/chinese-llm-benchmark"},{"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/jeinlee1991/chinese-llm-benchmark"},{"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":"6.2K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"6.2K stars, 250 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3mo 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 jeinlee1991/chinese-llm-benchmark"},{"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/jeinlee1991/chinese-llm-benchmark"},{"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":["License is unclear","License clarity: Unknown","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"6.2K GitHub stars","repoActivity":"6.2K stars, 250 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","install":"npx skills add jeinlee1991/chinese-llm-benchmark","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 jeinlee1991/chinese-llm-benchmark","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","3mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","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-v3","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"],"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","llm-agent","agents","agentic-ai","artificial-intelligence","llm-evaluation"],"suited_agents":["LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add jeinlee1991/chinese-llm-benchmark","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","llm-agent","agents","agentic-ai","artificial-intelligence","llm-evaluation"],"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","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":89,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","License clarity: Unknown"]},"safety":{"score":77,"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","77/100 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","77/100 agent safety score"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for GitHub automation","role":"Primary pick","best_for":["GitHub automation 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 GitHub automation 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 jeinlee1991/chinese-llm-benchmark","value":"Install the \"Chinese Llm Benchmark\" agent skill from https://github.com/jeinlee1991/chinese-llm-benchmark. 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: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 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\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"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 Chinese Llm Benchmark 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-v0.2.1/openagentskill-0.2.1.tgz install jeinlee1991-chinese-llm-benchmark","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 \"Chinese Llm Benchmark\" agent skill from https://github.com/jeinlee1991/chinese-llm-benchmark. 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: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 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\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"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 \"Chinese Llm Benchmark\" as a Claude Code skill from https://github.com/jeinlee1991/chinese-llm-benchmark. 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: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 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\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"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 \"Chinese Llm Benchmark\" from https://github.com/jeinlee1991/chinese-llm-benchmark 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: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 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\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"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":"jeinlee1991-chinese-llm-benchmark","name":"Chinese Llm Benchmark","description":"非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","github_repo":"jeinlee1991/chinese-llm-benchmark"},"suited_tasks":["GitHub automation workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add jeinlee1991/chinese-llm-benchmark","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install jeinlee1991-chinese-llm-benchmark"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Chinese Llm Benchmark\" agent skill from https://github.com/jeinlee1991/chinese-llm-benchmark. 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: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 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\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"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 \"Chinese Llm Benchmark\" as a Claude Code skill from https://github.com/jeinlee1991/chinese-llm-benchmark. 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: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 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\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"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 \"Chinese Llm Benchmark\" from https://github.com/jeinlee1991/chinese-llm-benchmark 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: 非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat等商用模型， 以及step3.5-flash、kimi-k2.6、ernie4.5、MiniMax-M2.7、deepseek-v4、Qwen3.6、llama4、智谱GLM-5.1、MiMo-V2、LongCat、gemma4、mistral等开源大模型。不仅提供排行榜，也提供规模超200万的大模型缺陷库！方便广大社区研究分析、改进大模型。 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\":\"jeinlee1991-chinese-llm-benchmark\",\"task\":\"Install Chinese Llm Benchmark\",\"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/jeinlee1991-chinese-llm-benchmark/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/jeinlee1991-chinese-llm-benchmark"},"trust":{"score":85,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"6.2K GitHub stars","repoActivity":"6.2K stars, 250 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark","install":"npx skills add jeinlee1991/chinese-llm-benchmark","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","llm-agent","agents","agentic-ai","artificial-intelligence","llm-evaluation"],"known_risks":["License is unclear","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":89,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","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":98,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"3mo 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","License is unclear","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","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use DynamicMap Benchmark","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: 89/100 Safe to try","Safety: 77/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"jeinlee1991-chinese-llm-benchmark (Chinese Llm Benchmark)","install_command":"npx skills add jeinlee1991/chinese-llm-benchmark","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":"jeinlee1991-chinese-llm-benchmark","task":"Use DynamicMap Benchmark","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/jeinlee1991-chinese-llm-benchmark","api":"https://www.openagentskill.com/api/agent/skills/jeinlee1991-chinese-llm-benchmark","audit":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=jeinlee1991-chinese-llm-benchmark&task=Use%20DynamicMap%20Benchmark&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20DynamicMap%20Benchmark&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20DynamicMap%20Benchmark&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/jeinlee1991-chinese-llm-benchmark/install","manifest":"https://www.openagentskill.com/api/registry/manifest/jeinlee1991-chinese-llm-benchmark"}},"use_cases":[{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"testing-qa","title":"Testing and QA","url":"https://www.openagentskill.com/use-cases/testing-qa"}],"urls":{"web":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark","api":"https://www.openagentskill.com/api/agent/skills/jeinlee1991-chinese-llm-benchmark","install_api":"https://www.openagentskill.com/api/skills/jeinlee1991-chinese-llm-benchmark/install","audit":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=jeinlee1991-chinese-llm-benchmark&task=Use%20DynamicMap%20Benchmark&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/jeinlee1991-chinese-llm-benchmark?metric=audit","repository":"https://github.com/jeinlee1991/chinese-llm-benchmark"}}],"blocked_candidates":[],"agent_workflow":{"mode":"resolve_review_install","recommended_action":"Require human approval before installing into a real workspace.","selected_skill":{"slug":"kth-rpl-dynamicmap-benchmark","name":"DynamicMap Benchmark","url":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark"},"install":{"target":"codex","label":"Codex install prompt","kind":"agent-prompt","command":"npx skills add KTH-RPL/DynamicMap_Benchmark","value":"Install the \"DynamicMap Benchmark\" agent skill from https://github.com/KTH-RPL/DynamicMap_Benchmark. 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: The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating 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\":\"kth-rpl-dynamicmap-benchmark\",\"task\":\"Install DynamicMap Benchmark\",\"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/kth-rpl-dynamicmap-benchmark/install"},"copy_paste_prompt":"Task: Use DynamicMap Benchmark\nUse DynamicMap Benchmark from https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark.\nReview the audit first: https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark/audit\nReview the eval first: https://www.openagentskill.com/api/agent/evals?slug=kth-rpl-dynamicmap-benchmark&task=Use%20DynamicMap%20Benchmark&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/kth-rpl-dynamicmap-benchmark/install\nInstall command: npx skills add KTH-RPL/DynamicMap_Benchmark\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%20DynamicMap%20Benchmark&agent=codex&max_risk=medium"},{"step":2,"label":"Fetch pre-install eval","method":"GET","url":"https://www.openagentskill.com/api/agent/evals?slug=kth-rpl-dynamicmap-benchmark&task=Use%20DynamicMap%20Benchmark&max_risk=medium"},{"step":3,"label":"Fetch selected skill profile","method":"GET","url":"https://www.openagentskill.com/api/agent/skills/kth-rpl-dynamicmap-benchmark"},{"step":4,"label":"Fetch install handoff","method":"GET","url":"https://www.openagentskill.com/api/skills/kth-rpl-dynamicmap-benchmark/install"},{"step":5,"label":"Review audit","method":"GET","url":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark/audit"},{"step":6,"label":"Report outcome","method":"POST","url":"https://www.openagentskill.com/api/agent/outcome","body":{"event_id":"resolve_a60dbb30-a301-400e-88d0-414f30a86c1c","skill_slug":"kth-rpl-dynamicmap-benchmark","task":"Use DynamicMap Benchmark","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."}}],"review_checklist":["Safety tier: Reviewed with permission notes","Safety score: 61/100 Review before install","Audit score: 73/100 Needs review","Trust score: 67/100 Sandbox only","Readiness: 50/100 Needs manual review","Documentation summary is thin","Documentation summary is thin","Quality score needs review","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"],"fallback_strategy":[{"slug":"gmberton-deep-visual-geo-localization-benchmark","name":"Deep Visual Geo Localization Benchmark","reason":"Matches task terms: benchmark","url":"https://www.openagentskill.com/skills/gmberton-deep-visual-geo-localization-benchmark","install_api":"https://www.openagentskill.com/api/skills/gmberton-deep-visual-geo-localization-benchmark/install"},{"slug":"zeyofu-blink-benchmark","name":"BLINK Benchmark","reason":"Matches task terms: benchmark","url":"https://www.openagentskill.com/skills/zeyofu-blink-benchmark","install_api":"https://www.openagentskill.com/api/skills/zeyofu-blink-benchmark/install"},{"slug":"hyperledger-caliper-caliper-benchmarks","name":"Caliper Benchmarks","reason":"Matches task terms: benchmark","url":"https://www.openagentskill.com/skills/hyperledger-caliper-caliper-benchmarks","install_api":"https://www.openagentskill.com/api/skills/hyperledger-caliper-caliper-benchmarks/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_a60dbb30-a301-400e-88d0-414f30a86c1c"}},"agent_handoff":{"version":"openagentskill-agent-handoff-v1","mode":"resolve_compare_review_install","task":"Use DynamicMap Benchmark","agent":"codex","selected_skill":{"slug":"kth-rpl-dynamicmap-benchmark","name":"DynamicMap Benchmark","url":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark","api_url":"https://www.openagentskill.com/api/agent/skills/kth-rpl-dynamicmap-benchmark","audit_url":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=kth-rpl-dynamicmap-benchmark&task=Use%20DynamicMap%20Benchmark&max_risk=medium","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark"},"install_plan":{"command":"npx skills add KTH-RPL/DynamicMap_Benchmark","target":"codex","label":"Codex install prompt","kind":"agent-prompt","value":"Install the \"DynamicMap Benchmark\" agent skill from https://github.com/KTH-RPL/DynamicMap_Benchmark. 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: The First Dynamic Map Removal Benchmark | Included 8 SOTA methods | Continous updating 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\":\"kth-rpl-dynamicmap-benchmark\",\"task\":\"Install DynamicMap Benchmark\",\"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/kth-rpl-dynamicmap-benchmark/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%20DynamicMap%20Benchmark&agent=codex&max_risk=medium"},{"step":2,"label":"Fetch pre-install eval","method":"GET","url":"https://www.openagentskill.com/api/agent/evals?slug=kth-rpl-dynamicmap-benchmark&task=Use%20DynamicMap%20Benchmark&max_risk=medium"},{"step":3,"label":"Fetch selected skill profile","method":"GET","url":"https://www.openagentskill.com/api/agent/skills/kth-rpl-dynamicmap-benchmark"},{"step":4,"label":"Fetch install handoff","method":"GET","url":"https://www.openagentskill.com/api/skills/kth-rpl-dynamicmap-benchmark/install"},{"step":5,"label":"Review audit","method":"GET","url":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark/audit"},{"step":6,"label":"Report outcome","method":"POST","url":"https://www.openagentskill.com/api/agent/outcome","body":{"event_id":"resolve_a60dbb30-a301-400e-88d0-414f30a86c1c","skill_slug":"kth-rpl-dynamicmap-benchmark","task":"Use DynamicMap Benchmark","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."}}],"platform_templates":[{"id":"codex","name":"Codex","surface":"Coding agent / local workspace","copy_prompt":"Task: Use DynamicMap Benchmark\nSelected skill: DynamicMap Benchmark (kth-rpl-dynamicmap-benchmark)\nSkill URL: https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark\nAudit URL: https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark/audit\nEval URL: https://www.openagentskill.com/api/agent/evals?slug=kth-rpl-dynamicmap-benchmark&task=Use%20DynamicMap%20Benchmark&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/kth-rpl-dynamicmap-benchmark/install\nInstall command: npx skills add KTH-RPL/DynamicMap_Benchmark\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- Deep Visual Geo Localization Benchmark (gmberton-deep-visual-geo-localization-benchmark): https://www.openagentskill.com/skills/gmberton-deep-visual-geo-localization-benchmark\n- BLINK Benchmark (zeyofu-blink-benchmark): https://www.openagentskill.com/skills/zeyofu-blink-benchmark\n- Caliper Benchmarks (hyperledger-caliper-caliper-benchmarks): https://www.openagentskill.com/skills/hyperledger-caliper-caliper-benchmarks\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 DynamicMap Benchmark\nSelected skill: DynamicMap Benchmark (kth-rpl-dynamicmap-benchmark)\nSkill URL: https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark\nAudit URL: https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark/audit\nEval URL: https://www.openagentskill.com/api/agent/evals?slug=kth-rpl-dynamicmap-benchmark&task=Use%20DynamicMap%20Benchmark&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/kth-rpl-dynamicmap-benchmark/install\nInstall command: npx skills add KTH-RPL/DynamicMap_Benchmark\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- Deep Visual Geo Localization Benchmark (gmberton-deep-visual-geo-localization-benchmark): https://www.openagentskill.com/skills/gmberton-deep-visual-geo-localization-benchmark\n- BLINK Benchmark (zeyofu-blink-benchmark): https://www.openagentskill.com/skills/zeyofu-blink-benchmark\n- Caliper Benchmarks (hyperledger-caliper-caliper-benchmarks): https://www.openagentskill.com/skills/hyperledger-caliper-caliper-benchmarks\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 DynamicMap Benchmark\nSelected skill: DynamicMap Benchmark (kth-rpl-dynamicmap-benchmark)\nSkill URL: https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark\nAudit URL: https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark/audit\nEval URL: https://www.openagentskill.com/api/agent/evals?slug=kth-rpl-dynamicmap-benchmark&task=Use%20DynamicMap%20Benchmark&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/kth-rpl-dynamicmap-benchmark/install\nInstall command: npx skills add KTH-RPL/DynamicMap_Benchmark\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- Deep Visual Geo Localization Benchmark (gmberton-deep-visual-geo-localization-benchmark): https://www.openagentskill.com/skills/gmberton-deep-visual-geo-localization-benchmark\n- BLINK Benchmark (zeyofu-blink-benchmark): https://www.openagentskill.com/skills/zeyofu-blink-benchmark\n- Caliper Benchmarks (hyperledger-caliper-caliper-benchmarks): https://www.openagentskill.com/skills/hyperledger-caliper-caliper-benchmarks\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: 61/100 Review before install","Audit score: 73/100 Needs review","Trust score: 67/100 Sandbox only","Readiness: 50/100 Needs manual review","Documentation summary is thin","Documentation summary is thin","Quality score needs review","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"],"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_a60dbb30-a301-400e-88d0-414f30a86c1c"},"feedback":{"event_id":"resolve_a60dbb30-a301-400e-88d0-414f30a86c1c","outcome_api":"https://www.openagentskill.com/api/agent/outcome","cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz outcome \"resolve_a60dbb30-a301-400e-88d0-414f30a86c1c\" --skill \"kth-rpl-dynamicmap-benchmark\" --task \"Use DynamicMap Benchmark\" --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 DynamicMap Benchmark","recommended_skill":{"slug":"kth-rpl-dynamicmap-benchmark","name":"DynamicMap Benchmark","url":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark","audit_url":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark/audit","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark","safety_tier":"Reviewed with permission notes","auto_install_policy":"review"},"alternative_skills":[{"slug":"gmberton-deep-visual-geo-localization-benchmark","name":"Deep Visual Geo Localization Benchmark","url":"https://www.openagentskill.com/skills/gmberton-deep-visual-geo-localization-benchmark","install_command":"npx skills add gmberton/deep-visual-geo-localization-benchmark","why_consider":"Matches task terms: benchmark","risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"65/100 Review before install","trust":"77/100 Strong shortlist","notes":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 256 stars, 32 forks; issue activity unavailable in current metadata"]}},{"slug":"zeyofu-blink-benchmark","name":"BLINK Benchmark","url":"https://www.openagentskill.com/skills/zeyofu-blink-benchmark","install_command":"npx skills add zeyofu/BLINK_Benchmark","why_consider":"Matches task terms: benchmark","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"55/100 Review before install","trust":"74/100 Strong shortlist","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 169 stars, 8 forks; issue activity unavailable in current metadata"]}},{"slug":"hyperledger-caliper-caliper-benchmarks","name":"Caliper Benchmarks","url":"https://www.openagentskill.com/skills/hyperledger-caliper-caliper-benchmarks","install_command":"npx skills add hyperledger-caliper/caliper-benchmarks","why_consider":"Matches task terms: benchmark","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"48/100 Avoid automatic install","trust":"73/100 Strong shortlist","notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push"]}}],"install_command":"npx skills add KTH-RPL/DynamicMap_Benchmark","install_target":"Codex install prompt","why_recommended":["Matches task terms: dynamicmap, benchmark","Install handoff is available","Repository freshness signal is available","Registry match score 42","Needs validation for GitHub automation","67/100 OpenAgentSkill Trust Score v5"],"risk_summary":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"61/100 Review before install","trust":"75/100 Strong shortlist","notes":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"]},"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_a60dbb30-a301-400e-88d0-414f30a86c1c","outcome_api":"https://www.openagentskill.com/api/agent/outcome","cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz outcome \"resolve_a60dbb30-a301-400e-88d0-414f30a86c1c\" --skill \"kth-rpl-dynamicmap-benchmark\" --task \"Use DynamicMap Benchmark\" --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_a60dbb30-a301-400e-88d0-414f30a86c1c","selected_skill_slug":"kth-rpl-dynamicmap-benchmark","selected_skill_name":"DynamicMap Benchmark","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_a60dbb30-a301-400e-88d0-414f30a86c1c","skill_slug":"kth-rpl-dynamicmap-benchmark","task":"Use DynamicMap Benchmark","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."},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz outcome \"resolve_a60dbb30-a301-400e-88d0-414f30a86c1c\" --skill \"kth-rpl-dynamicmap-benchmark\" --task \"Use DynamicMap Benchmark\" --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 KTH-RPL/DynamicMap_Benchmark","After one narrow task, report the outcome with: npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz outcome \"resolve_a60dbb30-a301-400e-88d0-414f30a86c1c\" --skill \"kth-rpl-dynamicmap-benchmark\" --task \"Use DynamicMap Benchmark\" --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 DynamicMap Benchmark","agent":"codex","selected_skill":{"slug":"kth-rpl-dynamicmap-benchmark","name":"DynamicMap Benchmark","url":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark","api_url":"https://www.openagentskill.com/api/agent/skills/kth-rpl-dynamicmap-benchmark","audit_url":"https://www.openagentskill.com/skills/kth-rpl-dynamicmap-benchmark/audit","repository":"https://github.com/KTH-RPL/DynamicMap_Benchmark"},"suited_tasks":["GitHub automation workflows","general agent builders","builders willing to evaluate younger projects","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Navigate local resources","Run repeatable desktop actions"],"suited_agents":["Jupyter Notebook","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add KTH-RPL/DynamicMap_Benchmark","target":"codex","label":"Codex install prompt","policy":"review","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true},"trust":{"score":67,"label":"Sandbox only","version":"trust-score-v5","base_score":75,"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":["67/100 Trust Score v5","75/100 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":"425 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"status":"warn","detail":"425 stars, 30 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":62,"status":"info","detail":"11mo since push"},{"id":"license","label":"License clarity","score":86,"status":"pass","detail":"BSD-3-Clause"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"status":"info","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 KTH-RPL/DynamicMap_Benchmark"},{"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/KTH-RPL/DynamicMap_Benchmark"},{"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":"61/100 Review before install","trust":"75/100 Strong shortlist","safety_tier":"Reviewed with permission notes","notes":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata"],"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","Quality score needs review","Stars/forks activity: 425 stars, 30 forks; issue activity unavailable in current metadata","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: 75/100 Strong shortlist","Audit: 73/100 Needs review","Safety: 61/100 Review before install","Review repository, license, install command, and permission surface before production use."]},"alternatives":[{"slug":"gmberton-deep-visual-geo-localization-benchmark","name":"Deep Visual Geo Localization Benchmark","url":"https://www.openagentskill.com/skills/gmberton-deep-visual-geo-localization-benchmark","install_command":"npx skills add gmberton/deep-visual-geo-localization-benchmark","trust_score":77,"audit_score":77,"safety_score":65,"why_consider":"Matches task terms: benchmark","risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"65/100 Review before install","trust":"77/100 Strong shortlist","notes":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 256 stars, 32 forks; issue activity unavailable in current metadata"]}},{"slug":"zeyofu-blink-benchmark","name":"BLINK Benchmark","url":"https://www.openagentskill.com/skills/zeyofu-blink-benchmark","install_command":"npx skills add zeyofu/BLINK_Benchmark","trust_score":74,"audit_score":71,"safety_score":55,"why_consider":"Matches task terms: benchmark","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"55/100 Review before install","trust":"74/100 Strong shortlist","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 169 stars, 8 forks; issue activity unavailable in current metadata"]}},{"slug":"hyperledger-caliper-caliper-benchmarks","name":"Caliper Benchmarks","url":"https://www.openagentskill.com/skills/hyperledger-caliper-caliper-benchmarks","install_command":"npx skills add hyperledger-caliper/caliper-benchmarks","trust_score":73,"audit_score":64,"safety_score":48,"why_consider":"Matches task terms: benchmark","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"48/100 Avoid automatic install","trust":"73/100 Strong shortlist","notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push"]}},{"slug":"jeinlee1991-chinese-llm-benchmark","name":"Chinese Llm Benchmark","url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark","install_command":"npx skills add jeinlee1991/chinese-llm-benchmark","trust_score":85,"audit_score":89,"safety_score":77,"why_consider":"Matches task terms: benchmark","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"77/100 Review before install","trust":"85/100 Strong shortlist","notes":["License is unclear","License clarity: Unknown"]}}],"outcome_feedback":{"event_id":"resolve_a60dbb30-a301-400e-88d0-414f30a86c1c","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_a60dbb30-a301-400e-88d0-414f30a86c1c","skill_slug":"kth-rpl-dynamicmap-benchmark","task":"Use DynamicMap Benchmark","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."},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz outcome \"resolve_a60dbb30-a301-400e-88d0-414f30a86c1c\" --skill \"kth-rpl-dynamicmap-benchmark\" --task \"Use DynamicMap Benchmark\" --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":"2026-08-22T23:19:12.432Z","total_skills_searched":894,"total_candidates":15,"candidate_pool":{"sort":"quality","size":894,"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"}}}