{"task":"Use Browsers Benchmark","agent":"codex","constraints":{"max_risk":"medium","needs_install_command":true,"min_stars":0},"feedback":{"event_id":"resolve_97c4e8f9-7e44-4e8d-897c-29fca969b42e","outcome_api":"https://www.openagentskill.com/api/agent/outcome","method":"POST","selected_skill_slug":"techinz-browsers-benchmark","selected_skill_name":"Browsers Benchmark","alternative_skill_slugs":["dhamaniasad-headlessbrowsers","jeinlee1991-chinese-llm-benchmark","clovaai-deep-text-recognition-benchmark","embeddings-benchmark-mteb"],"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_97c4e8f9-7e44-4e8d-897c-29fca969b42e","skill_slug":"techinz-browsers-benchmark","task":"Use Browsers 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_97c4e8f9-7e44-4e8d-897c-29fca969b42e\" --skill \"techinz-browsers-benchmark\" --task \"Use Browsers 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_97c4e8f9-7e44-4e8d-897c-29fca969b42e","selected_skill_slug":"techinz-browsers-benchmark","selected_skill_name":"Browsers 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_97c4e8f9-7e44-4e8d-897c-29fca969b42e","skill_slug":"techinz-browsers-benchmark","task":"Use Browsers 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_97c4e8f9-7e44-4e8d-897c-29fca969b42e\" --skill \"techinz-browsers-benchmark\" --task \"Use Browsers 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_97c4e8f9-7e44-4e8d-897c-29fca969b42e","resolve_event_id":"resolve_97c4e8f9-7e44-4e8d-897c-29fca969b42e","generated_at":"2026-08-22T14:34:52.837Z","task":"Use Browsers Benchmark","agent":"codex","constraints":{"max_risk":"medium","needs_install_command":true,"min_stars":0},"urls":{"web":"https://www.openagentskill.com/resolve?task=Use+Browsers+Benchmark&agent=codex&max_risk=medium","json":"https://www.openagentskill.com/api/agent/receipt?task=Use+Browsers+Benchmark&agent=codex&max_risk=medium","text":"https://www.openagentskill.com/api/agent/receipt?task=Use+Browsers+Benchmark&agent=codex&max_risk=medium&format=text","resolve_json":"https://www.openagentskill.com/api/agent/resolve?task=Use+Browsers+Benchmark&agent=codex&max_risk=medium","resolve_text":"https://www.openagentskill.com/api/agent/resolve?task=Use+Browsers+Benchmark&agent=codex&max_risk=medium&format=text"},"selected_skill":{"slug":"techinz-browsers-benchmark","name":"Browsers Benchmark","description":"Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX  and other bot detection systems. Find the best browser for scraping.","category":"browser-automation","url":"https://www.openagentskill.com/skills/techinz-browsers-benchmark","api_url":"https://www.openagentskill.com/api/agent/skills/techinz-browsers-benchmark","audit_url":"https://www.openagentskill.com/skills/techinz-browsers-benchmark/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=techinz-browsers-benchmark&task=Use%20Browsers%20Benchmark&max_risk=medium","install_api_url":"https://www.openagentskill.com/api/skills/techinz-browsers-benchmark/install","repository":"https://github.com/techinz/browsers-benchmark"},"install":{"command":"npx skills add techinz/browsers-benchmark","target":"codex","label":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Browsers Benchmark\" agent skill from https://github.com/techinz/browsers-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: Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot detection systems. Find the best browser for scraping. 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\":\"techinz-browsers-benchmark\",\"task\":\"Install Browsers 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: browsers, benchmark","Install handoff is available","Repository freshness signal is available","Registry match score 42","Fallback candidate for Browser automation","69/100 Trust Score","0/100 Agent Proven Score","80/100 audit score"],"suited_tasks":["Browser automation workflows","Browser agents teams","builders willing to evaluate younger projects","Navigate pages","Click and type safely","Check visual and DOM state","Run test suites","Capture failures"],"suited_agents":["Python","Playwright","Codex","Claude Code","Cursor","OpenAgentSkill CLI","Browser agents","CLI"]},"trust":{"score":69,"label":"Sandbox only","version":"trust-score-v5","base_score":77,"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":["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"]},"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":64,"audit_score":80,"notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 forks; issue activity unavailable in current metadata","64/100 agent safety score"],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 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: 77/100 Strong shortlist","Audit: 80/100 Needs review","Safety: 64/100 Review before install","Review repository, license, install command, and permission surface before production use."]},"alternatives":[{"slug":"dhamaniasad-headlessbrowsers","name":"HeadlessBrowsers","url":"https://www.openagentskill.com/skills/dhamaniasad-headlessbrowsers","audit_url":"https://www.openagentskill.com/skills/dhamaniasad-headlessbrowsers/audit","install_command":"npx skills add dhamaniasad/HeadlessBrowsers","trust_score":82,"audit_score":82,"safety_score":66,"reason":"Matches task terms: browsers","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"},{"slug":"clovaai-deep-text-recognition-benchmark","name":"Deep Text Recognition Benchmark","url":"https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark","audit_url":"https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark/audit","install_command":"npx skills add clovaai/deep-text-recognition-benchmark","trust_score":80,"audit_score":71,"safety_score":55,"reason":"Matches task terms: benchmark","policy":"review"},{"slug":"embeddings-benchmark-mteb","name":"Mteb","url":"https://www.openagentskill.com/skills/embeddings-benchmark-mteb","audit_url":"https://www.openagentskill.com/skills/embeddings-benchmark-mteb/audit","install_command":"npx skills add embeddings-benchmark/mteb","trust_score":86,"audit_score":89,"safety_score":77,"reason":"Matches task terms: benchmark","policy":"review"}],"outcome_feedback":{"event_id":"resolve_97c4e8f9-7e44-4e8d-897c-29fca969b42e","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_97c4e8f9-7e44-4e8d-897c-29fca969b42e","skill_slug":"techinz-browsers-benchmark","task":"Use Browsers 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_97c4e8f9-7e44-4e8d-897c-29fca969b42e","skill_slug":"techinz-browsers-benchmark","task":"Use Browsers 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_97c4e8f9-7e44-4e8d-897c-29fca969b42e\" --skill \"techinz-browsers-benchmark\" --task \"Use Browsers 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/techinz-browsers-benchmark/audit","Fetch the pre-install eval: https://www.openagentskill.com/api/agent/evals?slug=techinz-browsers-benchmark&task=Use%20Browsers%20Benchmark&max_risk=medium","Do not auto-install yet. Ask for human review before running: npx skills add techinz/browsers-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_97c4e8f9-7e44-4e8d-897c-29fca969b42e."],"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 Browsers Benchmark","agent":"codex","best_skill":{"slug":"techinz-browsers-benchmark","name":"Browsers Benchmark","description":"Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX  and other bot detection systems. Find the best browser for scraping.","category":"browser-automation","url":"https://www.openagentskill.com/skills/techinz-browsers-benchmark","api_url":"https://www.openagentskill.com/api/agent/skills/techinz-browsers-benchmark","audit_url":"https://www.openagentskill.com/skills/techinz-browsers-benchmark/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=techinz-browsers-benchmark&task=Use%20Browsers%20Benchmark&max_risk=medium","repository":"https://github.com/techinz/browsers-benchmark"},"install":{"command":"npx skills add techinz/browsers-benchmark","target":"codex","label":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Browsers Benchmark\" agent skill from https://github.com/techinz/browsers-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: Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot detection systems. Find the best browser for scraping. 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\":\"techinz-browsers-benchmark\",\"task\":\"Install Browsers 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/techinz-browsers-benchmark/install","ready":true,"review_required":true,"auto_install_allowed":false,"policy":"review"},"why_recommended":["Matches task terms: browsers, benchmark","Install handoff is available","Repository freshness signal is available","Registry match score 42","Fallback candidate for Browser automation","69/100 OpenAgentSkill Trust Score v5","80/100 audit score","64/100 safety score"],"trust_score_v5":{"score":69,"base_score":77,"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":["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"]},"evidence":{"stars":"335 GitHub stars","repoActivity":"335 stars, 10 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/techinz/browsers-benchmark","install":"npx skills add techinz/browsers-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"agent_compatibility":["Python","Playwright","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: 335 stars, 10 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":["browser-automation","browser","testing","automation","anti-detect","antidetect-browser"],"suited_agents":["Python","Playwright","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add techinz/browsers-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."]},"best_for":["browser-automation","browser","testing","automation","anti-detect","antidetect-browser"],"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: 335 stars, 10 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."}}},"trust_score_v4":{"score":77,"tier":"strong","label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"335 GitHub stars","repoActivity":"335 stars, 10 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/techinz/browsers-benchmark","install":"npx skills add techinz/browsers-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"agent_compatibility":["Python","Playwright","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: 335 stars, 10 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":["browser-automation","browser","testing","automation","anti-detect","antidetect-browser"],"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: 335 stars, 10 forks; issue activity unavailable in current metadata"]},"trust_score_v3":{"score":77,"tier":"strong","label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"335 GitHub stars","repoActivity":"335 stars, 10 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/techinz/browsers-benchmark","install":"npx skills add techinz/browsers-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"agent_compatibility":["Python","Playwright","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: 335 stars, 10 forks; issue activity unavailable in current metadata"]}},"trust_score_v2":{"score":77,"tier":"strong","label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"335 GitHub stars","repoActivity":"335 stars, 10 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/techinz/browsers-benchmark","install":"npx skills add techinz/browsers-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"agent_compatibility":["Python","Playwright","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: 335 stars, 10 forks; issue activity unavailable in current metadata"]}},"risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"64/100 Review before install","trust":"77/100 Strong shortlist","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 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":["Quality score needs review","64/100 agent safety score"]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"techinz-browsers-benchmark","name":"Browsers Benchmark","description":"Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX  and other bot detection systems. Find the best browser for scraping.","category":"browser-automation","url":"https://www.openagentskill.com/skills/techinz-browsers-benchmark","repository":"https://github.com/techinz/browsers-benchmark","github_repo":"techinz/browsers-benchmark"},"suited_tasks":["Browser automation workflows","Browser agents teams","builders willing to evaluate younger projects","Navigate pages","Click and type safely","Check visual and DOM state","Run test suites","Capture failures"],"suited_agents":["Python","Playwright","Codex","Claude Code","Cursor","OpenAgentSkill CLI","Browser agents","CLI"],"install":{"command":"npx skills add techinz/browsers-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 techinz-browsers-benchmark"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Browsers Benchmark\" agent skill from https://github.com/techinz/browsers-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: Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot detection systems. Find the best browser for scraping. 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\":\"techinz-browsers-benchmark\",\"task\":\"Install Browsers 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 \"Browsers Benchmark\" as a Claude Code skill from https://github.com/techinz/browsers-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: Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot detection systems. Find the best browser for scraping. 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\":\"techinz-browsers-benchmark\",\"task\":\"Install Browsers 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 \"Browsers Benchmark\" from https://github.com/techinz/browsers-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: Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot detection systems. Find the best browser for scraping. 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\":\"techinz-browsers-benchmark\",\"task\":\"Install Browsers 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/techinz-browsers-benchmark/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/techinz-browsers-benchmark"},"trust":{"score":77,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"335 GitHub stars","repoActivity":"335 stars, 10 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/techinz/browsers-benchmark","install":"npx skills add techinz/browsers-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"network or browser 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":["browser-automation","browser","testing","automation","anti-detect","antidetect-browser"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 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":80,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 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":70,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"Testing and QA","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 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 Browsers 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: 80/100 Needs review","Safety: 64/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"techinz-browsers-benchmark (Browsers Benchmark)","install_command":"npx skills add techinz/browsers-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":"techinz-browsers-benchmark","task":"Use Browsers 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/techinz-browsers-benchmark","api":"https://www.openagentskill.com/api/agent/skills/techinz-browsers-benchmark","audit":"https://www.openagentskill.com/skills/techinz-browsers-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=techinz-browsers-benchmark&task=Use%20Browsers%20Benchmark&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Browsers%20Benchmark&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Browsers%20Benchmark&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/techinz-browsers-benchmark/install","manifest":"https://www.openagentskill.com/api/registry/manifest/techinz-browsers-benchmark"}},"agent_contract":{"version":"openagentskill-resolve-contract-v2","input_task":"Use Browsers Benchmark","recommended_skill_slug":"techinz-browsers-benchmark","recommended_skill_name":"Browsers Benchmark","install_command":"npx skills add techinz/browsers-benchmark","install_policy":"review","auto_install_allowed":false,"human_review_required":true,"audit_url":"https://www.openagentskill.com/skills/techinz-browsers-benchmark/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=techinz-browsers-benchmark&task=Use%20Browsers%20Benchmark&max_risk=medium","skill_api_url":"https://www.openagentskill.com/api/agent/skills/techinz-browsers-benchmark","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: 335 stars, 10 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: 77/100 Strong shortlist","Audit: 80/100 Needs review","Safety: 64/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"techinz-browsers-benchmark (Browsers Benchmark)","install_command":"npx skills add techinz/browsers-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":"Testing and QA","description":"I need my agent to test a web app, reproduce bugs, and verify fixes.","useCases":[{"slug":"browser-automation","title":"Browser automation"},{"slug":"testing-qa","title":"Testing and QA"},{"slug":"web-scraping","title":"Web scraping"}]},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":74,"lastPushedAt":"2026-06-09T11:39:52+00:00"},"github_quality":{"stars":335,"starsLabel":"335","forks":10,"license":"MIT","qualityScore":70,"trustScore":77,"auditScore":80},"coverage_tags":["Coding","Testing and QA","browser-automation","browser","testing","automation","anti-detect","antidetect-browser"]},"alternatives":[{"slug":"dhamaniasad-headlessbrowsers","name":"HeadlessBrowsers","url":"https://www.openagentskill.com/skills/dhamaniasad-headlessbrowsers","install_command":"npx skills add dhamaniasad/HeadlessBrowsers","trust_score":82,"audit_score":82,"safety_score":66,"why_consider":"Matches task terms: browsers","risk":{"level":"Safe to try","safety_tier":"Reviewed with permission notes","safety":"66/100 Review before install","trust":"82/100 Strong shortlist","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},{"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"]}},{"slug":"clovaai-deep-text-recognition-benchmark","name":"Deep Text Recognition Benchmark","url":"https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark","install_command":"npx skills add clovaai/deep-text-recognition-benchmark","trust_score":80,"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":"80/100 Strong shortlist","notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 2y since push"]}},{"slug":"embeddings-benchmark-mteb","name":"Mteb","url":"https://www.openagentskill.com/skills/embeddings-benchmark-mteb","install_command":"npx skills add embeddings-benchmark/mteb","trust_score":86,"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":"86/100 Production candidate","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}}],"decision_packet":{"version":"openagentskill-agent-decision-packet-v1","task":"Use Browsers Benchmark","agent":"codex","selected_skill":{"slug":"techinz-browsers-benchmark","name":"Browsers Benchmark","url":"https://www.openagentskill.com/skills/techinz-browsers-benchmark","api_url":"https://www.openagentskill.com/api/agent/skills/techinz-browsers-benchmark","audit_url":"https://www.openagentskill.com/skills/techinz-browsers-benchmark/audit","repository":"https://github.com/techinz/browsers-benchmark"},"suited_tasks":["Browser automation workflows","Browser agents teams","builders willing to evaluate younger projects","Navigate pages","Click and type safely","Check visual and DOM state","Run test suites","Capture failures"],"suited_agents":["Python","Playwright","Codex","Claude Code","Cursor","OpenAgentSkill CLI","Browser agents","CLI"],"install":{"command":"npx skills add techinz/browsers-benchmark","target":"codex","label":"Codex install prompt","policy":"review","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true},"trust":{"score":69,"label":"Sandbox only","version":"trust-score-v5","base_score":77,"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":["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,"status":"info","detail":"335 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"status":"warn","detail":"335 stars, 10 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":82,"status":"pass","detail":"network or browser surface"},{"id":"installability","label":"Install availability","score":92,"status":"pass","detail":"npx skills add techinz/browsers-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":86,"status":"pass","detail":"network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"status":"pass","detail":"https://github.com/techinz/browsers-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":"64/100 Review before install","trust":"77/100 Strong shortlist","safety_tier":"Reviewed with permission notes","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 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","Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 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: 77/100 Strong shortlist","Audit: 80/100 Needs review","Safety: 64/100 Review before install","Review repository, license, install command, and permission surface before production use."]},"alternatives":[{"slug":"dhamaniasad-headlessbrowsers","name":"HeadlessBrowsers","url":"https://www.openagentskill.com/skills/dhamaniasad-headlessbrowsers","install_command":"npx skills add dhamaniasad/HeadlessBrowsers","trust_score":82,"audit_score":82,"safety_score":66,"why_consider":"Matches task terms: browsers","risk":{"level":"Safe to try","safety_tier":"Reviewed with permission notes","safety":"66/100 Review before install","trust":"82/100 Strong shortlist","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},{"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"]}},{"slug":"clovaai-deep-text-recognition-benchmark","name":"Deep Text Recognition Benchmark","url":"https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark","install_command":"npx skills add clovaai/deep-text-recognition-benchmark","trust_score":80,"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":"80/100 Strong shortlist","notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 2y since push"]}},{"slug":"embeddings-benchmark-mteb","name":"Mteb","url":"https://www.openagentskill.com/skills/embeddings-benchmark-mteb","install_command":"npx skills add embeddings-benchmark/mteb","trust_score":86,"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":"86/100 Production candidate","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}}],"outcome_feedback":{"event_id":"resolve_97c4e8f9-7e44-4e8d-897c-29fca969b42e","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_97c4e8f9-7e44-4e8d-897c-29fca969b42e","skill_slug":"techinz-browsers-benchmark","task":"Use Browsers 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_97c4e8f9-7e44-4e8d-897c-29fca969b42e\" --skill \"techinz-browsers-benchmark\" --task \"Use Browsers 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 Browsers Benchmark for: Use Browsers Benchmark\nReview audit: https://www.openagentskill.com/skills/techinz-browsers-benchmark/audit\nAsk for human approval before installing: npx skills add techinz/browsers-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":287.7,"semantic_relevance":42,"skill":{"slug":"techinz-browsers-benchmark","name":"Browsers Benchmark","description":"Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX  and other bot detection systems. Find the best browser for scraping.","category":"browser-automation","github_stars":335,"created_at":"2026-06-21T03:02:19.539691+00:00","updated_at":"2026-06-09T11:39:52+00:00","repository":"https://github.com/techinz/browsers-benchmark","github_repo":"techinz/browsers-benchmark"},"recommendation_reasons":["Matches task terms: browsers, 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":"Testing and QA","description":"I need my agent to test a web app, reproduce bugs, and verify fixes.","useCases":[{"slug":"browser-automation","title":"Browser automation"},{"slug":"testing-qa","title":"Testing and QA"},{"slug":"web-scraping","title":"Web scraping"}]},"applicableAgents":["Browser agents","CLI","Codex","Claude Code","Cursor"],"install":{"ready":true,"command":"npx skills add techinz/browsers-benchmark","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":335,"starsLabel":"335","forks":10,"license":"MIT","qualityScore":70,"trustScore":77,"auditScore":80},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":74,"lastPushedAt":"2026-06-09T11:39:52+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 forks; issue activity unavailable in current metadata","Needs review"]},"coverageTags":["Coding","Testing and QA","browser-automation","browser","testing","automation","anti-detect","antidetect-browser"]},"quality":{"score":70,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"335","tone":"neutral"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":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":"335 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"335 stars, 10 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":82,"weight":0.12,"status":"pass","detail":"network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add techinz/browsers-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":"network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/techinz/browsers-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":"335 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"335 stars, 10 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add techinz/browsers-benchmark"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/techinz/browsers-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","Recently maintained repository","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 forks; issue activity unavailable in current metadata"],"evidence":{"stars":"335 GitHub stars","repoActivity":"335 stars, 10 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/techinz/browsers-benchmark","install":"npx skills add techinz/browsers-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add techinz/browsers-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","2mo since push"]},"agentCompatibility":["Python","Playwright","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: 335 stars, 10 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":["browser-automation","browser","testing","automation","anti-detect","antidetect-browser"],"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: 335 stars, 10 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":"335 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"335 stars, 10 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":82,"weight":0.12,"status":"pass","detail":"network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add techinz/browsers-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":"network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/techinz/browsers-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":"335 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"335 stars, 10 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add techinz/browsers-benchmark"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/techinz/browsers-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","Recently maintained repository","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 forks; issue activity unavailable in current metadata","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"335 GitHub stars","repoActivity":"335 stars, 10 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/techinz/browsers-benchmark","install":"npx skills add techinz/browsers-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"network or browser 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 techinz/browsers-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","2mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Python","Playwright","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: 335 stars, 10 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":["browser-automation","browser","testing","automation","anti-detect","antidetect-browser"],"suited_agents":["Python","Playwright","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add techinz/browsers-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":["browser-automation","browser","testing","automation","anti-detect","antidetect-browser"],"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: 335 stars, 10 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":80,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 forks; issue activity unavailable in current metadata"]},"safety":{"score":64,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Quality score needs review","64/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"browser","label":"Browser automation","reason":"Skill may drive a browser or interact with web pages.","severity":"medium"},{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Quality score needs review"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Quality score needs review","64/100 agent safety score"]},"decision":{"readiness_score":69,"readiness_label":"Prototype first","headline":"Fallback candidate for Browser automation","role":"Fallback candidate","best_for":["Browser automation workflows","Browser agents teams","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Browser 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 techinz/browsers-benchmark","value":"Install the \"Browsers Benchmark\" agent skill from https://github.com/techinz/browsers-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: Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot detection systems. Find the best browser for scraping. 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\":\"techinz-browsers-benchmark\",\"task\":\"Install Browsers 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 Browsers 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 techinz-browsers-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 \"Browsers Benchmark\" agent skill from https://github.com/techinz/browsers-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: Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot detection systems. Find the best browser for scraping. 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\":\"techinz-browsers-benchmark\",\"task\":\"Install Browsers 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 \"Browsers Benchmark\" as a Claude Code skill from https://github.com/techinz/browsers-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: Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot detection systems. Find the best browser for scraping. 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\":\"techinz-browsers-benchmark\",\"task\":\"Install Browsers 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 \"Browsers Benchmark\" from https://github.com/techinz/browsers-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: Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot detection systems. Find the best browser for scraping. 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\":\"techinz-browsers-benchmark\",\"task\":\"Install Browsers 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":"techinz-browsers-benchmark","name":"Browsers Benchmark","description":"Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX  and other bot detection systems. Find the best browser for scraping.","category":"browser-automation","url":"https://www.openagentskill.com/skills/techinz-browsers-benchmark","repository":"https://github.com/techinz/browsers-benchmark","github_repo":"techinz/browsers-benchmark"},"suited_tasks":["Browser automation workflows","Browser agents teams","builders willing to evaluate younger projects","Navigate pages","Click and type safely","Check visual and DOM state","Run test suites","Capture failures"],"suited_agents":["Python","Playwright","Codex","Claude Code","Cursor","OpenAgentSkill CLI","Browser agents","CLI"],"install":{"command":"npx skills add techinz/browsers-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 techinz-browsers-benchmark"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Browsers Benchmark\" agent skill from https://github.com/techinz/browsers-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: Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot detection systems. Find the best browser for scraping. 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\":\"techinz-browsers-benchmark\",\"task\":\"Install Browsers 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 \"Browsers Benchmark\" as a Claude Code skill from https://github.com/techinz/browsers-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: Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot detection systems. Find the best browser for scraping. 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\":\"techinz-browsers-benchmark\",\"task\":\"Install Browsers 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 \"Browsers Benchmark\" from https://github.com/techinz/browsers-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: Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot detection systems. Find the best browser for scraping. 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\":\"techinz-browsers-benchmark\",\"task\":\"Install Browsers 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/techinz-browsers-benchmark/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/techinz-browsers-benchmark"},"trust":{"score":77,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"335 GitHub stars","repoActivity":"335 stars, 10 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/techinz/browsers-benchmark","install":"npx skills add techinz/browsers-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"network or browser 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":["browser-automation","browser","testing","automation","anti-detect","antidetect-browser"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 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":80,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 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":70,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"Testing and QA","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 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 Browsers 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: 80/100 Needs review","Safety: 64/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"techinz-browsers-benchmark (Browsers Benchmark)","install_command":"npx skills add techinz/browsers-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":"techinz-browsers-benchmark","task":"Use Browsers 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/techinz-browsers-benchmark","api":"https://www.openagentskill.com/api/agent/skills/techinz-browsers-benchmark","audit":"https://www.openagentskill.com/skills/techinz-browsers-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=techinz-browsers-benchmark&task=Use%20Browsers%20Benchmark&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Browsers%20Benchmark&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Browsers%20Benchmark&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/techinz-browsers-benchmark/install","manifest":"https://www.openagentskill.com/api/registry/manifest/techinz-browsers-benchmark"}},"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"testing-qa","title":"Testing and QA","url":"https://www.openagentskill.com/use-cases/testing-qa"},{"slug":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"}],"urls":{"web":"https://www.openagentskill.com/skills/techinz-browsers-benchmark","api":"https://www.openagentskill.com/api/agent/skills/techinz-browsers-benchmark","install_api":"https://www.openagentskill.com/api/skills/techinz-browsers-benchmark/install","audit":"https://www.openagentskill.com/skills/techinz-browsers-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=techinz-browsers-benchmark&task=Use%20Browsers%20Benchmark&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/techinz-browsers-benchmark?metric=audit","repository":"https://github.com/techinz/browsers-benchmark"}},"safer_alternative":{"rank":9,"match_score":30,"raw_match_score":211,"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":65,"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 Browsers 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 Browsers 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%20Browsers%20Benchmark&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Browsers%20Benchmark&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Browsers%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%20Browsers%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":11,"match_score":30,"raw_match_score":207.8,"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":1530,"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 Browsers 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 Browsers 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%20Browsers%20Benchmark&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Browsers%20Benchmark&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Browsers%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%20Browsers%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":6,"match_score":30,"raw_match_score":220.6,"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 Browsers 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 Browsers 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%20Browsers%20Benchmark&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Browsers%20Benchmark&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Browsers%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%20Browsers%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":287.7,"semantic_relevance":42,"skill":{"slug":"techinz-browsers-benchmark","name":"Browsers Benchmark","description":"Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX  and other bot detection systems. Find the best browser for scraping.","category":"browser-automation","github_stars":335,"created_at":"2026-06-21T03:02:19.539691+00:00","updated_at":"2026-06-09T11:39:52+00:00","repository":"https://github.com/techinz/browsers-benchmark","github_repo":"techinz/browsers-benchmark"},"recommendation_reasons":["Matches task terms: browsers, 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":"Testing and QA","description":"I need my agent to test a web app, reproduce bugs, and verify fixes.","useCases":[{"slug":"browser-automation","title":"Browser automation"},{"slug":"testing-qa","title":"Testing and QA"},{"slug":"web-scraping","title":"Web scraping"}]},"applicableAgents":["Browser agents","CLI","Codex","Claude Code","Cursor"],"install":{"ready":true,"command":"npx skills add techinz/browsers-benchmark","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":335,"starsLabel":"335","forks":10,"license":"MIT","qualityScore":70,"trustScore":77,"auditScore":80},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":74,"lastPushedAt":"2026-06-09T11:39:52+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 forks; issue activity unavailable in current metadata","Needs review"]},"coverageTags":["Coding","Testing and QA","browser-automation","browser","testing","automation","anti-detect","antidetect-browser"]},"quality":{"score":70,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"335","tone":"neutral"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":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":"335 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"335 stars, 10 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":82,"weight":0.12,"status":"pass","detail":"network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add techinz/browsers-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":"network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/techinz/browsers-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":"335 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"335 stars, 10 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add techinz/browsers-benchmark"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/techinz/browsers-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","Recently maintained repository","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 forks; issue activity unavailable in current metadata"],"evidence":{"stars":"335 GitHub stars","repoActivity":"335 stars, 10 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/techinz/browsers-benchmark","install":"npx skills add techinz/browsers-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add techinz/browsers-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","2mo since push"]},"agentCompatibility":["Python","Playwright","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: 335 stars, 10 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":["browser-automation","browser","testing","automation","anti-detect","antidetect-browser"],"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: 335 stars, 10 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":"335 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"335 stars, 10 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":82,"weight":0.12,"status":"pass","detail":"network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add techinz/browsers-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":"network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/techinz/browsers-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":"335 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"335 stars, 10 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add techinz/browsers-benchmark"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/techinz/browsers-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","Recently maintained repository","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 forks; issue activity unavailable in current metadata","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"335 GitHub stars","repoActivity":"335 stars, 10 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/techinz/browsers-benchmark","install":"npx skills add techinz/browsers-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"network or browser 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 techinz/browsers-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","2mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Python","Playwright","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: 335 stars, 10 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":["browser-automation","browser","testing","automation","anti-detect","antidetect-browser"],"suited_agents":["Python","Playwright","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add techinz/browsers-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":["browser-automation","browser","testing","automation","anti-detect","antidetect-browser"],"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: 335 stars, 10 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":80,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 forks; issue activity unavailable in current metadata"]},"safety":{"score":64,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Quality score needs review","64/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"browser","label":"Browser automation","reason":"Skill may drive a browser or interact with web pages.","severity":"medium"},{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Quality score needs review"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Quality score needs review","64/100 agent safety score"]},"decision":{"readiness_score":69,"readiness_label":"Prototype first","headline":"Fallback candidate for Browser automation","role":"Fallback candidate","best_for":["Browser automation workflows","Browser agents teams","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Browser 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 techinz/browsers-benchmark","value":"Install the \"Browsers Benchmark\" agent skill from https://github.com/techinz/browsers-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: Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot detection systems. Find the best browser for scraping. 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\":\"techinz-browsers-benchmark\",\"task\":\"Install Browsers 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 Browsers 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 techinz-browsers-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 \"Browsers Benchmark\" agent skill from https://github.com/techinz/browsers-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: Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot detection systems. Find the best browser for scraping. 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\":\"techinz-browsers-benchmark\",\"task\":\"Install Browsers 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 \"Browsers Benchmark\" as a Claude Code skill from https://github.com/techinz/browsers-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: Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot detection systems. Find the best browser for scraping. 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\":\"techinz-browsers-benchmark\",\"task\":\"Install Browsers 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 \"Browsers Benchmark\" from https://github.com/techinz/browsers-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: Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot detection systems. Find the best browser for scraping. 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\":\"techinz-browsers-benchmark\",\"task\":\"Install Browsers 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":"techinz-browsers-benchmark","name":"Browsers Benchmark","description":"Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX  and other bot detection systems. Find the best browser for scraping.","category":"browser-automation","url":"https://www.openagentskill.com/skills/techinz-browsers-benchmark","repository":"https://github.com/techinz/browsers-benchmark","github_repo":"techinz/browsers-benchmark"},"suited_tasks":["Browser automation workflows","Browser agents teams","builders willing to evaluate younger projects","Navigate pages","Click and type safely","Check visual and DOM state","Run test suites","Capture failures"],"suited_agents":["Python","Playwright","Codex","Claude Code","Cursor","OpenAgentSkill CLI","Browser agents","CLI"],"install":{"command":"npx skills add techinz/browsers-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 techinz-browsers-benchmark"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Browsers Benchmark\" agent skill from https://github.com/techinz/browsers-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: Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot detection systems. Find the best browser for scraping. 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\":\"techinz-browsers-benchmark\",\"task\":\"Install Browsers 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 \"Browsers Benchmark\" as a Claude Code skill from https://github.com/techinz/browsers-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: Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot detection systems. Find the best browser for scraping. 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\":\"techinz-browsers-benchmark\",\"task\":\"Install Browsers 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 \"Browsers Benchmark\" from https://github.com/techinz/browsers-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: Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot detection systems. Find the best browser for scraping. 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\":\"techinz-browsers-benchmark\",\"task\":\"Install Browsers 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/techinz-browsers-benchmark/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/techinz-browsers-benchmark"},"trust":{"score":77,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"335 GitHub stars","repoActivity":"335 stars, 10 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/techinz/browsers-benchmark","install":"npx skills add techinz/browsers-benchmark","installSafety":"standard package or runtime install path","permissionSurface":"network or browser 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":["browser-automation","browser","testing","automation","anti-detect","antidetect-browser"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 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":80,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 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":70,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"Testing and QA","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 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 Browsers 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: 80/100 Needs review","Safety: 64/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"techinz-browsers-benchmark (Browsers Benchmark)","install_command":"npx skills add techinz/browsers-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":"techinz-browsers-benchmark","task":"Use Browsers 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/techinz-browsers-benchmark","api":"https://www.openagentskill.com/api/agent/skills/techinz-browsers-benchmark","audit":"https://www.openagentskill.com/skills/techinz-browsers-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=techinz-browsers-benchmark&task=Use%20Browsers%20Benchmark&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Browsers%20Benchmark&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Browsers%20Benchmark&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/techinz-browsers-benchmark/install","manifest":"https://www.openagentskill.com/api/registry/manifest/techinz-browsers-benchmark"}},"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"testing-qa","title":"Testing and QA","url":"https://www.openagentskill.com/use-cases/testing-qa"},{"slug":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"}],"urls":{"web":"https://www.openagentskill.com/skills/techinz-browsers-benchmark","api":"https://www.openagentskill.com/api/agent/skills/techinz-browsers-benchmark","install_api":"https://www.openagentskill.com/api/skills/techinz-browsers-benchmark/install","audit":"https://www.openagentskill.com/skills/techinz-browsers-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=techinz-browsers-benchmark&task=Use%20Browsers%20Benchmark&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/techinz-browsers-benchmark?metric=audit","repository":"https://github.com/techinz/browsers-benchmark"}},"alternatives":[{"rank":2,"match_score":30,"raw_match_score":262.5,"semantic_relevance":30,"skill":{"slug":"dhamaniasad-headlessbrowsers","name":"HeadlessBrowsers","description":"A list of (almost) all headless web browsers in existence","category":"automation","github_stars":6587,"created_at":"2026-06-16T09:45:56.95857+00:00","updated_at":"2025-10-12T07:30:27+00:00","repository":"https://github.com/dhamaniasad/HeadlessBrowsers","github_repo":"dhamaniasad/HeadlessBrowsers"},"recommendation_reasons":["Matches task terms: browsers","Useful GitHub adoption: 6,587 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":"Testing and QA","description":"I need my agent to test a web app, reproduce bugs, and verify fixes.","useCases":[{"slug":"browser-automation","title":"Browser automation"},{"slug":"testing-qa","title":"Testing and QA"},{"slug":"coding-agents","title":"Coding agents"}]},"applicableAgents":["Browser agents","CLI","Codex","Claude Code","Cursor"],"install":{"ready":true,"command":"npx skills add dhamaniasad/HeadlessBrowsers","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":6587,"starsLabel":"6.6K","forks":448,"license":"CC0-1.0","qualityScore":86,"trustScore":82,"auditScore":82},"maintenance":{"status":"stable","label":"10mo since push","daysSincePush":314,"lastPushedAt":"2025-10-12T07:30:27+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"coverageTags":["Coding","Testing and QA","automation","workflow","browser","headless-browsers","testing","github"]},"quality":{"score":86,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"6.6K","tone":"positive"},{"label":"Freshness","value":"10mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"CC0-1.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":82,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"weight":0.13,"status":"pass","detail":"6.6K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"6.6K stars, 448 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":62,"weight":0.14,"status":"info","detail":"10mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"CC0-1.0"},{"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":"network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add dhamaniasad/HeadlessBrowsers"},{"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":"network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/dhamaniasad/HeadlessBrowsers"},{"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":"6.6K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"6.6K stars, 448 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"10mo since push"},{"status":"pass","label":"License clarity","detail":"CC0-1.0"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add dhamaniasad/HeadlessBrowsers"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/dhamaniasad/HeadlessBrowsers"},{"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":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"6.6K GitHub stars","repoActivity":"6.6K stars, 448 forks","lastPushed":"10mo since push","license":"CC0-1.0","repository":"https://github.com/dhamaniasad/HeadlessBrowsers","install":"npx skills add dhamaniasad/HeadlessBrowsers","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add dhamaniasad/HeadlessBrowsers","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","10mo since push"]},"agentCompatibility":["Automation","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["automation","workflow","browser","headless-browsers","testing","github"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":74,"base_score":82,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["74/100 Trust Score v5","82/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"weight":0.13,"status":"pass","detail":"6.6K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"6.6K stars, 448 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":62,"weight":0.14,"status":"info","detail":"10mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"CC0-1.0"},{"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":"network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add dhamaniasad/HeadlessBrowsers"},{"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":"network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/dhamaniasad/HeadlessBrowsers"},{"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":"6.6K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"6.6K stars, 448 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"10mo since push"},{"status":"pass","label":"License clarity","detail":"CC0-1.0"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add dhamaniasad/HeadlessBrowsers"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/dhamaniasad/HeadlessBrowsers"},{"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":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"6.6K GitHub stars","repoActivity":"6.6K stars, 448 forks","lastPushed":"10mo since push","license":"CC0-1.0","repository":"https://github.com/dhamaniasad/HeadlessBrowsers","install":"npx skills add dhamaniasad/HeadlessBrowsers","installSafety":"standard package or runtime install path","permissionSurface":"network or browser 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 dhamaniasad/HeadlessBrowsers","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","10mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Automation","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-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":["automation","workflow","browser","headless-browsers","testing","github"],"suited_agents":["Automation","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add dhamaniasad/HeadlessBrowsers","trust_score":74,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["automation","workflow","browser","headless-browsers","testing","github"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":82,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":82,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":66,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Documentation summary is thin","66/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"browser","label":"Browser automation","reason":"Skill may drive a browser or interact with web pages.","severity":"medium"},{"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","66/100 agent safety score"]},"decision":{"readiness_score":88,"readiness_label":"Production-ready","headline":"Primary pick for Browser automation","role":"Primary pick","best_for":["Browser automation workflows","Browser agents teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Browser 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 dhamaniasad/HeadlessBrowsers","value":"Install the \"HeadlessBrowsers\" agent skill from https://github.com/dhamaniasad/HeadlessBrowsers. 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 list of (almost) all headless web browsers in existence 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\":\"dhamaniasad-headlessbrowsers\",\"task\":\"Install HeadlessBrowsers\",\"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 HeadlessBrowsers 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 dhamaniasad-headlessbrowsers","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 \"HeadlessBrowsers\" agent skill from https://github.com/dhamaniasad/HeadlessBrowsers. 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 list of (almost) all headless web browsers in existence 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\":\"dhamaniasad-headlessbrowsers\",\"task\":\"Install HeadlessBrowsers\",\"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 \"HeadlessBrowsers\" as a Claude Code skill from https://github.com/dhamaniasad/HeadlessBrowsers. 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 list of (almost) all headless web browsers in existence 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\":\"dhamaniasad-headlessbrowsers\",\"task\":\"Install HeadlessBrowsers\",\"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 \"HeadlessBrowsers\" from https://github.com/dhamaniasad/HeadlessBrowsers 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 list of (almost) all headless web browsers in existence 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\":\"dhamaniasad-headlessbrowsers\",\"task\":\"Install HeadlessBrowsers\",\"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":"dhamaniasad-headlessbrowsers","name":"HeadlessBrowsers","description":"A list of (almost) all headless web browsers in existence","category":"automation","url":"https://www.openagentskill.com/skills/dhamaniasad-headlessbrowsers","repository":"https://github.com/dhamaniasad/HeadlessBrowsers","github_repo":"dhamaniasad/HeadlessBrowsers"},"suited_tasks":["Browser automation workflows","Browser agents teams","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Run test suites","Capture failures"],"suited_agents":["Automation","Codex","Claude Code","Cursor","OpenAgentSkill CLI","Browser agents","CLI"],"install":{"command":"npx skills add dhamaniasad/HeadlessBrowsers","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 dhamaniasad-headlessbrowsers"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"HeadlessBrowsers\" agent skill from https://github.com/dhamaniasad/HeadlessBrowsers. 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 list of (almost) all headless web browsers in existence 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\":\"dhamaniasad-headlessbrowsers\",\"task\":\"Install HeadlessBrowsers\",\"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 \"HeadlessBrowsers\" as a Claude Code skill from https://github.com/dhamaniasad/HeadlessBrowsers. 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 list of (almost) all headless web browsers in existence 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\":\"dhamaniasad-headlessbrowsers\",\"task\":\"Install HeadlessBrowsers\",\"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 \"HeadlessBrowsers\" from https://github.com/dhamaniasad/HeadlessBrowsers 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 list of (almost) all headless web browsers in existence 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\":\"dhamaniasad-headlessbrowsers\",\"task\":\"Install HeadlessBrowsers\",\"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/dhamaniasad-headlessbrowsers/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/dhamaniasad-headlessbrowsers"},"trust":{"score":82,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"6.6K GitHub stars","repoActivity":"6.6K stars, 448 forks","lastPushed":"10mo since push","license":"CC0-1.0","repository":"https://github.com/dhamaniasad/HeadlessBrowsers","install":"npx skills add dhamaniasad/HeadlessBrowsers","installSafety":"standard package or runtime install path","permissionSurface":"network or browser 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":["automation","workflow","browser","headless-browsers","testing","github"],"known_risks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":82,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","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":86,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Testing and QA","maintenance":"10mo 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","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use Browsers Benchmark","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 82/100 Strong shortlist","Audit: 82/100 Safe to try","Safety: 66/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"dhamaniasad-headlessbrowsers (HeadlessBrowsers)","install_command":"npx skills add dhamaniasad/HeadlessBrowsers","risk_summary":"Safe to try; 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":"dhamaniasad-headlessbrowsers","task":"Use Browsers 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/dhamaniasad-headlessbrowsers","api":"https://www.openagentskill.com/api/agent/skills/dhamaniasad-headlessbrowsers","audit":"https://www.openagentskill.com/skills/dhamaniasad-headlessbrowsers/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=dhamaniasad-headlessbrowsers&task=Use%20Browsers%20Benchmark&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Browsers%20Benchmark&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Browsers%20Benchmark&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/dhamaniasad-headlessbrowsers/install","manifest":"https://www.openagentskill.com/api/registry/manifest/dhamaniasad-headlessbrowsers"}},"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"testing-qa","title":"Testing and QA","url":"https://www.openagentskill.com/use-cases/testing-qa"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"}],"urls":{"web":"https://www.openagentskill.com/skills/dhamaniasad-headlessbrowsers","api":"https://www.openagentskill.com/api/agent/skills/dhamaniasad-headlessbrowsers","install_api":"https://www.openagentskill.com/api/skills/dhamaniasad-headlessbrowsers/install","audit":"https://www.openagentskill.com/skills/dhamaniasad-headlessbrowsers/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=dhamaniasad-headlessbrowsers&task=Use%20Browsers%20Benchmark&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/dhamaniasad-headlessbrowsers?metric=audit","repository":"https://github.com/dhamaniasad/HeadlessBrowsers"}},{"rank":3,"match_score":30,"raw_match_score":240.3,"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 Browsers 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 Browsers 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%20Browsers%20Benchmark&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Browsers%20Benchmark&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Browsers%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%20Browsers%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"}},{"rank":4,"match_score":30,"raw_match_score":235.9,"semantic_relevance":30,"skill":{"slug":"clovaai-deep-text-recognition-benchmark","name":"Deep Text Recognition Benchmark","description":"Text recognition (optical character recognition) with deep learning methods, ICCV 2019","category":"document-processing","github_stars":3937,"created_at":"2026-06-05T13:01:08.962553+00:00","updated_at":"2024-03-04T10:24:54+00:00","repository":"https://github.com/clovaai/deep-text-recognition-benchmark","github_repo":"clovaai/deep-text-recognition-benchmark"},"recommendation_reasons":["Matches task terms: benchmark","Useful GitHub adoption: 3,937 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":"Document processing","description":"I need my agent to read PDFs, extract tables, and turn documents into structured data.","useCases":[{"slug":"document-processing","title":"Document processing"},{"slug":"web-scraping","title":"Web scraping"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Jupyter Notebook"],"install":{"ready":true,"command":"npx skills add clovaai/deep-text-recognition-benchmark","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":3937,"starsLabel":"3.9K","forks":1133,"license":"Apache-2.0","qualityScore":70,"trustScore":80,"auditScore":71},"maintenance":{"status":"stale","label":"2y since push","daysSincePush":901,"lastPushedAt":"2024-03-04T10:24:54+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: 2y since push"]},"coverageTags":["Research","Document processing","document-processing","ocr","documents","extraction","crnn","deep-learning"]},"quality":{"score":70,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"3.9K","tone":"positive"},{"label":"Freshness","value":"2y 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":80,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"3.9K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"3.9K stars, 1.1K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":22,"weight":0.14,"status":"fail","detail":"2y 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 clovaai/deep-text-recognition-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/clovaai/deep-text-recognition-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":"3.9K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"3.9K stars, 1.1K forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"2y 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 clovaai/deep-text-recognition-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/clovaai/deep-text-recognition-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":"pass","label":"OpenAgentSkill usage","detail":"3 views, 0 install copies"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 2y since push"],"evidence":{"stars":"3.9K GitHub stars","repoActivity":"3.9K stars, 1.1K forks","lastPushed":"2y since push","license":"Apache-2.0","repository":"https://github.com/clovaai/deep-text-recognition-benchmark","install":"npx skills add clovaai/deep-text-recognition-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 clovaai/deep-text-recognition-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","2y since push"]},"agentCompatibility":["Jupyter Notebook","OCR","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: 2y 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":["document-processing","ocr","documents","extraction","crnn","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":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 2y since push"]},"trust_v5":{"version":"trust-score-v5","score":72,"base_score":80,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["72/100 Trust Score v5","80/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"3.9K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"3.9K stars, 1.1K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":22,"weight":0.14,"status":"fail","detail":"2y 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 clovaai/deep-text-recognition-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/clovaai/deep-text-recognition-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":"3.9K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"3.9K stars, 1.1K forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"2y 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 clovaai/deep-text-recognition-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/clovaai/deep-text-recognition-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":"pass","label":"OpenAgentSkill usage","detail":"3 views, 0 install copies"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Meaningful 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","Quality score needs review","Documentation summary is thin","Recent maintenance: 2y since push","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"3.9K GitHub stars","repoActivity":"3.9K stars, 1.1K forks","lastPushed":"2y since push","license":"Apache-2.0","repository":"https://github.com/clovaai/deep-text-recognition-benchmark","install":"npx skills add clovaai/deep-text-recognition-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 clovaai/deep-text-recognition-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","2y since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Jupyter Notebook","OCR","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: 2y 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":["document-processing","ocr","documents","extraction","crnn","deep-learning"],"suited_agents":["Jupyter Notebook","OCR","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add clovaai/deep-text-recognition-benchmark","trust_score":72,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"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":["document-processing","ocr","documents","extraction","crnn","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":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 2y since push"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":80,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"audit_score":71,"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: 2y since push"]},"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":["Documentation summary is thin","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":["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","55/100 agent safety score"]},"decision":{"readiness_score":74,"readiness_label":"Strong shortlist","headline":"Companion skill for Document processing","role":"Companion skill","best_for":["Document processing workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["Repository looks stale"],"next_steps":["Install it in a sandbox agent and run one Document processing 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 clovaai/deep-text-recognition-benchmark","value":"Install the \"Deep Text Recognition Benchmark\" agent skill from https://github.com/clovaai/deep-text-recognition-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: Text recognition (optical character recognition) with deep learning methods, ICCV 2019 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\":\"clovaai-deep-text-recognition-benchmark\",\"task\":\"Install Deep Text Recognition 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 Text Recognition 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 clovaai-deep-text-recognition-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 Text Recognition Benchmark\" agent skill from https://github.com/clovaai/deep-text-recognition-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: Text recognition (optical character recognition) with deep learning methods, ICCV 2019 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\":\"clovaai-deep-text-recognition-benchmark\",\"task\":\"Install Deep Text Recognition 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 Text Recognition Benchmark\" as a Claude Code skill from https://github.com/clovaai/deep-text-recognition-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: Text recognition (optical character recognition) with deep learning methods, ICCV 2019 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\":\"clovaai-deep-text-recognition-benchmark\",\"task\":\"Install Deep Text Recognition 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 Text Recognition Benchmark\" from https://github.com/clovaai/deep-text-recognition-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: Text recognition (optical character recognition) with deep learning methods, ICCV 2019 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\":\"clovaai-deep-text-recognition-benchmark\",\"task\":\"Install Deep Text Recognition 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":"clovaai-deep-text-recognition-benchmark","name":"Deep Text Recognition Benchmark","description":"Text recognition (optical character recognition) with deep learning methods, ICCV 2019","category":"document-processing","url":"https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark","repository":"https://github.com/clovaai/deep-text-recognition-benchmark","github_repo":"clovaai/deep-text-recognition-benchmark"},"suited_tasks":["Document processing workflows","general agent builders","teams that value GitHub adoption signals","Read uploaded files","Extract structured fields","Prepare clean context for downstream agents","Crawl target URLs","Extract tables and metadata"],"suited_agents":["Jupyter Notebook","OCR","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add clovaai/deep-text-recognition-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 clovaai-deep-text-recognition-benchmark"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Deep Text Recognition Benchmark\" agent skill from https://github.com/clovaai/deep-text-recognition-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: Text recognition (optical character recognition) with deep learning methods, ICCV 2019 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\":\"clovaai-deep-text-recognition-benchmark\",\"task\":\"Install Deep Text Recognition 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 Text Recognition Benchmark\" as a Claude Code skill from https://github.com/clovaai/deep-text-recognition-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: Text recognition (optical character recognition) with deep learning methods, ICCV 2019 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\":\"clovaai-deep-text-recognition-benchmark\",\"task\":\"Install Deep Text Recognition 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 Text Recognition Benchmark\" from https://github.com/clovaai/deep-text-recognition-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: Text recognition (optical character recognition) with deep learning methods, ICCV 2019 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\":\"clovaai-deep-text-recognition-benchmark\",\"task\":\"Install Deep Text Recognition 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/clovaai-deep-text-recognition-benchmark/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/clovaai-deep-text-recognition-benchmark"},"trust":{"score":80,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"3.9K GitHub stars","repoActivity":"3.9K stars, 1.1K forks","lastPushed":"2y since push","license":"Apache-2.0","repository":"https://github.com/clovaai/deep-text-recognition-benchmark","install":"npx skills add clovaai/deep-text-recognition-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":["document-processing","ocr","documents","extraction","crnn","deep-learning"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 2y 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":71,"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: 2y 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":70,"label":"Strong"},"supply":{"track":"Research and knowledge work","scenario":"Document processing","maintenance":"2y 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","Documentation summary is thin","Repository appears stale","Quality score needs review","Recent maintenance: 2y since push","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use Browsers Benchmark","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 80/100 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":"clovaai-deep-text-recognition-benchmark (Deep Text Recognition Benchmark)","install_command":"npx skills add clovaai/deep-text-recognition-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":"clovaai-deep-text-recognition-benchmark","task":"Use Browsers 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/clovaai-deep-text-recognition-benchmark","api":"https://www.openagentskill.com/api/agent/skills/clovaai-deep-text-recognition-benchmark","audit":"https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=clovaai-deep-text-recognition-benchmark&task=Use%20Browsers%20Benchmark&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Browsers%20Benchmark&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Browsers%20Benchmark&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/clovaai-deep-text-recognition-benchmark/install","manifest":"https://www.openagentskill.com/api/registry/manifest/clovaai-deep-text-recognition-benchmark"}},"use_cases":[{"slug":"document-processing","title":"Document processing","url":"https://www.openagentskill.com/use-cases/document-processing"},{"slug":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"}],"urls":{"web":"https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark","api":"https://www.openagentskill.com/api/agent/skills/clovaai-deep-text-recognition-benchmark","install_api":"https://www.openagentskill.com/api/skills/clovaai-deep-text-recognition-benchmark/install","audit":"https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=clovaai-deep-text-recognition-benchmark&task=Use%20Browsers%20Benchmark&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/clovaai-deep-text-recognition-benchmark?metric=audit","repository":"https://github.com/clovaai/deep-text-recognition-benchmark"}},{"rank":5,"match_score":30,"raw_match_score":232.4,"semantic_relevance":30,"skill":{"slug":"embeddings-benchmark-mteb","name":"Mteb","description":"MTEB: Massive Text Embedding Benchmark","category":"rag-knowledge","github_stars":3309,"created_at":"2026-06-05T06:01:49.882433+00:00","updated_at":"2026-06-19T21:00:15+00:00","repository":"https://github.com/embeddings-benchmark/mteb","github_repo":"embeddings-benchmark/mteb"},"recommendation_reasons":["Matches task terms: benchmark","Useful GitHub adoption: 3,309 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"RAG and knowledge","description":"I need my agent to build a RAG workflow over documents and retrieve reliable context.","useCases":[{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"research-agents","title":"Research agents"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add embeddings-benchmark/mteb","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":3309,"starsLabel":"3.3K","forks":627,"license":"Apache-2.0","qualityScore":95,"trustScore":86,"auditScore":89},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":63,"lastPushedAt":"2026-06-19T21:00:15+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"coverageTags":["Research","RAG and knowledge","rag-knowledge","semantic-search","retrieval","knowledge","benchmark","bitext-mining"]},"quality":{"score":95,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"3.3K","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":86,"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":86,"weight":0.13,"status":"pass","detail":"3.3K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"3.3K stars, 627 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":50,"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 embeddings-benchmark/mteb"},{"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/embeddings-benchmark/mteb"},{"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":"3.3K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"3.3K stars, 627 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":"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 embeddings-benchmark/mteb"},{"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/embeddings-benchmark/mteb"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"3.3K GitHub stars","repoActivity":"3.3K stars, 627 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/embeddings-benchmark/mteb","install":"npx skills add embeddings-benchmark/mteb","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 embeddings-benchmark/mteb","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","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["rag-knowledge","semantic-search","retrieval","knowledge","benchmark","bitext-mining"],"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","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":80,"base_score":86,"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":["80/100 Trust Score v5","86/100 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"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"3.3K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"3.3K stars, 627 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":50,"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 embeddings-benchmark/mteb"},{"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/embeddings-benchmark/mteb"},{"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":"3.3K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"3.3K stars, 627 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":"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 embeddings-benchmark/mteb"},{"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/embeddings-benchmark/mteb"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern","Outcome loop is ready but needs first real agent run"],"warnings":["Documentation summary is thin","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":"3.3K GitHub stars","repoActivity":"3.3K stars, 627 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/embeddings-benchmark/mteb","install":"npx skills add embeddings-benchmark/mteb","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":"agent_install_candidate"},"installReadiness":{"ready":true,"command":"npx skills add embeddings-benchmark/mteb","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","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"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":["rag-knowledge","semantic-search","retrieval","knowledge","benchmark","bitext-mining"],"suited_agents":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add embeddings-benchmark/mteb","trust_score":80,"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"],"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":["rag-knowledge","semantic-search","retrieval","knowledge","benchmark","bitext-mining"],"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","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":86,"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":89,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"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":["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","77/100 agent safety score"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for RAG and knowledge","role":"Primary pick","best_for":["RAG and knowledge 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 RAG and knowledge 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 embeddings-benchmark/mteb","value":"Install the \"Mteb\" agent skill from https://github.com/embeddings-benchmark/mteb. 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: MTEB: Massive Text Embedding 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\":\"embeddings-benchmark-mteb\",\"task\":\"Install Mteb\",\"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 Mteb 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 embeddings-benchmark-mteb","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 \"Mteb\" agent skill from https://github.com/embeddings-benchmark/mteb. 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: MTEB: Massive Text Embedding 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\":\"embeddings-benchmark-mteb\",\"task\":\"Install Mteb\",\"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 \"Mteb\" as a Claude Code skill from https://github.com/embeddings-benchmark/mteb. 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: MTEB: Massive Text Embedding 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\":\"embeddings-benchmark-mteb\",\"task\":\"Install Mteb\",\"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 \"Mteb\" from https://github.com/embeddings-benchmark/mteb 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: MTEB: Massive Text Embedding 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\":\"embeddings-benchmark-mteb\",\"task\":\"Install Mteb\",\"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":"embeddings-benchmark-mteb","name":"Mteb","description":"MTEB: Massive Text Embedding Benchmark","category":"rag-knowledge","url":"https://www.openagentskill.com/skills/embeddings-benchmark-mteb","repository":"https://github.com/embeddings-benchmark/mteb","github_repo":"embeddings-benchmark/mteb"},"suited_tasks":["RAG and knowledge workflows","general agent builders","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Search sources","Extract claims"],"suited_agents":["Python","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add embeddings-benchmark/mteb","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 embeddings-benchmark-mteb"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Mteb\" agent skill from https://github.com/embeddings-benchmark/mteb. 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: MTEB: Massive Text Embedding 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\":\"embeddings-benchmark-mteb\",\"task\":\"Install Mteb\",\"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 \"Mteb\" as a Claude Code skill from https://github.com/embeddings-benchmark/mteb. 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: MTEB: Massive Text Embedding 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\":\"embeddings-benchmark-mteb\",\"task\":\"Install Mteb\",\"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 \"Mteb\" from https://github.com/embeddings-benchmark/mteb 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: MTEB: Massive Text Embedding 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\":\"embeddings-benchmark-mteb\",\"task\":\"Install Mteb\",\"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/embeddings-benchmark-mteb/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/embeddings-benchmark-mteb"},"trust":{"score":86,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"3.3K GitHub stars","repoActivity":"3.3K stars, 627 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/embeddings-benchmark/mteb","install":"npx skills add embeddings-benchmark/mteb","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":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["rag-knowledge","semantic-search","retrieval","knowledge","benchmark","bitext-mining"],"known_risks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":89,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":95,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","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","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Browsers Benchmark","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 86/100 Production candidate","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":"embeddings-benchmark-mteb (Mteb)","install_command":"npx skills add embeddings-benchmark/mteb","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":"embeddings-benchmark-mteb","task":"Use Browsers 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/embeddings-benchmark-mteb","api":"https://www.openagentskill.com/api/agent/skills/embeddings-benchmark-mteb","audit":"https://www.openagentskill.com/skills/embeddings-benchmark-mteb/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=embeddings-benchmark-mteb&task=Use%20Browsers%20Benchmark&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Browsers%20Benchmark&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Browsers%20Benchmark&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/embeddings-benchmark-mteb/install","manifest":"https://www.openagentskill.com/api/registry/manifest/embeddings-benchmark-mteb"}},"use_cases":[{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"urls":{"web":"https://www.openagentskill.com/skills/embeddings-benchmark-mteb","api":"https://www.openagentskill.com/api/agent/skills/embeddings-benchmark-mteb","install_api":"https://www.openagentskill.com/api/skills/embeddings-benchmark-mteb/install","audit":"https://www.openagentskill.com/skills/embeddings-benchmark-mteb/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=embeddings-benchmark-mteb&task=Use%20Browsers%20Benchmark&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/embeddings-benchmark-mteb?metric=audit","repository":"https://github.com/embeddings-benchmark/mteb"}}],"blocked_candidates":[],"agent_workflow":{"mode":"resolve_review_install","recommended_action":"Require human approval before installing into a real workspace.","selected_skill":{"slug":"techinz-browsers-benchmark","name":"Browsers Benchmark","url":"https://www.openagentskill.com/skills/techinz-browsers-benchmark","repository":"https://github.com/techinz/browsers-benchmark"},"install":{"target":"codex","label":"Codex install prompt","kind":"agent-prompt","command":"npx skills add techinz/browsers-benchmark","value":"Install the \"Browsers Benchmark\" agent skill from https://github.com/techinz/browsers-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: Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot detection systems. Find the best browser for scraping. 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\":\"techinz-browsers-benchmark\",\"task\":\"Install Browsers 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/techinz-browsers-benchmark/install"},"copy_paste_prompt":"Task: Use Browsers Benchmark\nUse Browsers Benchmark from https://www.openagentskill.com/skills/techinz-browsers-benchmark.\nReview the audit first: https://www.openagentskill.com/skills/techinz-browsers-benchmark/audit\nReview the eval first: https://www.openagentskill.com/api/agent/evals?slug=techinz-browsers-benchmark&task=Use%20Browsers%20Benchmark&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/techinz-browsers-benchmark/install\nInstall command: npx skills add techinz/browsers-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%20Browsers%20Benchmark&agent=codex&max_risk=medium"},{"step":2,"label":"Fetch pre-install eval","method":"GET","url":"https://www.openagentskill.com/api/agent/evals?slug=techinz-browsers-benchmark&task=Use%20Browsers%20Benchmark&max_risk=medium"},{"step":3,"label":"Fetch selected skill profile","method":"GET","url":"https://www.openagentskill.com/api/agent/skills/techinz-browsers-benchmark"},{"step":4,"label":"Fetch install handoff","method":"GET","url":"https://www.openagentskill.com/api/skills/techinz-browsers-benchmark/install"},{"step":5,"label":"Review audit","method":"GET","url":"https://www.openagentskill.com/skills/techinz-browsers-benchmark/audit"},{"step":6,"label":"Report outcome","method":"POST","url":"https://www.openagentskill.com/api/agent/outcome","body":{"event_id":"resolve_97c4e8f9-7e44-4e8d-897c-29fca969b42e","skill_slug":"techinz-browsers-benchmark","task":"Use Browsers 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: 64/100 Review before install","Audit score: 80/100 Needs review","Trust score: 69/100 Sandbox only","Readiness: 69/100 Prototype first","Quality score needs review","Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 forks; issue activity unavailable in current metadata"],"fallback_strategy":[{"slug":"dhamaniasad-headlessbrowsers","name":"HeadlessBrowsers","reason":"Matches task terms: browsers","url":"https://www.openagentskill.com/skills/dhamaniasad-headlessbrowsers","install_api":"https://www.openagentskill.com/api/skills/dhamaniasad-headlessbrowsers/install"},{"slug":"jeinlee1991-chinese-llm-benchmark","name":"Chinese Llm Benchmark","reason":"Matches task terms: benchmark","url":"https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark","install_api":"https://www.openagentskill.com/api/skills/jeinlee1991-chinese-llm-benchmark/install"},{"slug":"clovaai-deep-text-recognition-benchmark","name":"Deep Text Recognition Benchmark","reason":"Matches task terms: benchmark","url":"https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark","install_api":"https://www.openagentskill.com/api/skills/clovaai-deep-text-recognition-benchmark/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_97c4e8f9-7e44-4e8d-897c-29fca969b42e"}},"agent_handoff":{"version":"openagentskill-agent-handoff-v1","mode":"resolve_compare_review_install","task":"Use Browsers Benchmark","agent":"codex","selected_skill":{"slug":"techinz-browsers-benchmark","name":"Browsers Benchmark","url":"https://www.openagentskill.com/skills/techinz-browsers-benchmark","api_url":"https://www.openagentskill.com/api/agent/skills/techinz-browsers-benchmark","audit_url":"https://www.openagentskill.com/skills/techinz-browsers-benchmark/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=techinz-browsers-benchmark&task=Use%20Browsers%20Benchmark&max_risk=medium","repository":"https://github.com/techinz/browsers-benchmark"},"install_plan":{"command":"npx skills add techinz/browsers-benchmark","target":"codex","label":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Browsers Benchmark\" agent skill from https://github.com/techinz/browsers-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: Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot detection systems. Find the best browser for scraping. 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\":\"techinz-browsers-benchmark\",\"task\":\"Install Browsers 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/techinz-browsers-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%20Browsers%20Benchmark&agent=codex&max_risk=medium"},{"step":2,"label":"Fetch pre-install eval","method":"GET","url":"https://www.openagentskill.com/api/agent/evals?slug=techinz-browsers-benchmark&task=Use%20Browsers%20Benchmark&max_risk=medium"},{"step":3,"label":"Fetch selected skill profile","method":"GET","url":"https://www.openagentskill.com/api/agent/skills/techinz-browsers-benchmark"},{"step":4,"label":"Fetch install handoff","method":"GET","url":"https://www.openagentskill.com/api/skills/techinz-browsers-benchmark/install"},{"step":5,"label":"Review audit","method":"GET","url":"https://www.openagentskill.com/skills/techinz-browsers-benchmark/audit"},{"step":6,"label":"Report outcome","method":"POST","url":"https://www.openagentskill.com/api/agent/outcome","body":{"event_id":"resolve_97c4e8f9-7e44-4e8d-897c-29fca969b42e","skill_slug":"techinz-browsers-benchmark","task":"Use Browsers 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 Browsers Benchmark\nSelected skill: Browsers Benchmark (techinz-browsers-benchmark)\nSkill URL: https://www.openagentskill.com/skills/techinz-browsers-benchmark\nAudit URL: https://www.openagentskill.com/skills/techinz-browsers-benchmark/audit\nEval URL: https://www.openagentskill.com/api/agent/evals?slug=techinz-browsers-benchmark&task=Use%20Browsers%20Benchmark&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/techinz-browsers-benchmark/install\nInstall command: npx skills add techinz/browsers-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- HeadlessBrowsers (dhamaniasad-headlessbrowsers): https://www.openagentskill.com/skills/dhamaniasad-headlessbrowsers\n- Chinese Llm Benchmark (jeinlee1991-chinese-llm-benchmark): https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark\n- Deep Text Recognition Benchmark (clovaai-deep-text-recognition-benchmark): https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark\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 Browsers Benchmark\nSelected skill: Browsers Benchmark (techinz-browsers-benchmark)\nSkill URL: https://www.openagentskill.com/skills/techinz-browsers-benchmark\nAudit URL: https://www.openagentskill.com/skills/techinz-browsers-benchmark/audit\nEval URL: https://www.openagentskill.com/api/agent/evals?slug=techinz-browsers-benchmark&task=Use%20Browsers%20Benchmark&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/techinz-browsers-benchmark/install\nInstall command: npx skills add techinz/browsers-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- HeadlessBrowsers (dhamaniasad-headlessbrowsers): https://www.openagentskill.com/skills/dhamaniasad-headlessbrowsers\n- Chinese Llm Benchmark (jeinlee1991-chinese-llm-benchmark): https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark\n- Deep Text Recognition Benchmark (clovaai-deep-text-recognition-benchmark): https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark\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 Browsers Benchmark\nSelected skill: Browsers Benchmark (techinz-browsers-benchmark)\nSkill URL: https://www.openagentskill.com/skills/techinz-browsers-benchmark\nAudit URL: https://www.openagentskill.com/skills/techinz-browsers-benchmark/audit\nEval URL: https://www.openagentskill.com/api/agent/evals?slug=techinz-browsers-benchmark&task=Use%20Browsers%20Benchmark&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/techinz-browsers-benchmark/install\nInstall command: npx skills add techinz/browsers-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- HeadlessBrowsers (dhamaniasad-headlessbrowsers): https://www.openagentskill.com/skills/dhamaniasad-headlessbrowsers\n- Chinese Llm Benchmark (jeinlee1991-chinese-llm-benchmark): https://www.openagentskill.com/skills/jeinlee1991-chinese-llm-benchmark\n- Deep Text Recognition Benchmark (clovaai-deep-text-recognition-benchmark): https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark\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: 64/100 Review before install","Audit score: 80/100 Needs review","Trust score: 69/100 Sandbox only","Readiness: 69/100 Prototype first","Quality score needs review","Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 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_97c4e8f9-7e44-4e8d-897c-29fca969b42e"},"feedback":{"event_id":"resolve_97c4e8f9-7e44-4e8d-897c-29fca969b42e","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_97c4e8f9-7e44-4e8d-897c-29fca969b42e\" --skill \"techinz-browsers-benchmark\" --task \"Use Browsers 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 Browsers Benchmark","recommended_skill":{"slug":"techinz-browsers-benchmark","name":"Browsers Benchmark","url":"https://www.openagentskill.com/skills/techinz-browsers-benchmark","audit_url":"https://www.openagentskill.com/skills/techinz-browsers-benchmark/audit","repository":"https://github.com/techinz/browsers-benchmark","safety_tier":"Reviewed with permission notes","auto_install_policy":"review"},"alternative_skills":[{"slug":"dhamaniasad-headlessbrowsers","name":"HeadlessBrowsers","url":"https://www.openagentskill.com/skills/dhamaniasad-headlessbrowsers","install_command":"npx skills add dhamaniasad/HeadlessBrowsers","why_consider":"Matches task terms: browsers","risk":{"level":"Safe to try","safety_tier":"Reviewed with permission notes","safety":"66/100 Review before install","trust":"82/100 Strong shortlist","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},{"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","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"]}},{"slug":"clovaai-deep-text-recognition-benchmark","name":"Deep Text Recognition Benchmark","url":"https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark","install_command":"npx skills add clovaai/deep-text-recognition-benchmark","why_consider":"Matches task terms: benchmark","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"55/100 Review before install","trust":"80/100 Strong shortlist","notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 2y since push"]}}],"install_command":"npx skills add techinz/browsers-benchmark","install_target":"Codex install prompt","why_recommended":["Matches task terms: browsers, benchmark","Install handoff is available","Repository freshness signal is available","Registry match score 42","Fallback candidate for Browser automation","69/100 OpenAgentSkill Trust Score v5"],"risk_summary":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"64/100 Review before install","trust":"77/100 Strong shortlist","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 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_97c4e8f9-7e44-4e8d-897c-29fca969b42e","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_97c4e8f9-7e44-4e8d-897c-29fca969b42e\" --skill \"techinz-browsers-benchmark\" --task \"Use Browsers 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_97c4e8f9-7e44-4e8d-897c-29fca969b42e","selected_skill_slug":"techinz-browsers-benchmark","selected_skill_name":"Browsers 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_97c4e8f9-7e44-4e8d-897c-29fca969b42e","skill_slug":"techinz-browsers-benchmark","task":"Use Browsers 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_97c4e8f9-7e44-4e8d-897c-29fca969b42e\" --skill \"techinz-browsers-benchmark\" --task \"Use Browsers 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 techinz/browsers-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_97c4e8f9-7e44-4e8d-897c-29fca969b42e\" --skill \"techinz-browsers-benchmark\" --task \"Use Browsers 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 Browsers Benchmark","agent":"codex","selected_skill":{"slug":"techinz-browsers-benchmark","name":"Browsers Benchmark","url":"https://www.openagentskill.com/skills/techinz-browsers-benchmark","api_url":"https://www.openagentskill.com/api/agent/skills/techinz-browsers-benchmark","audit_url":"https://www.openagentskill.com/skills/techinz-browsers-benchmark/audit","repository":"https://github.com/techinz/browsers-benchmark"},"suited_tasks":["Browser automation workflows","Browser agents teams","builders willing to evaluate younger projects","Navigate pages","Click and type safely","Check visual and DOM state","Run test suites","Capture failures"],"suited_agents":["Python","Playwright","Codex","Claude Code","Cursor","OpenAgentSkill CLI","Browser agents","CLI"],"install":{"command":"npx skills add techinz/browsers-benchmark","target":"codex","label":"Codex install prompt","policy":"review","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true},"trust":{"score":69,"label":"Sandbox only","version":"trust-score-v5","base_score":77,"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":["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,"status":"info","detail":"335 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"status":"warn","detail":"335 stars, 10 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":82,"status":"pass","detail":"network or browser surface"},{"id":"installability","label":"Install availability","score":92,"status":"pass","detail":"npx skills add techinz/browsers-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":86,"status":"pass","detail":"network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"status":"pass","detail":"https://github.com/techinz/browsers-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":"64/100 Review before install","trust":"77/100 Strong shortlist","safety_tier":"Reviewed with permission notes","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 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","Quality score needs review","Documentation summary is thin","Stars/forks activity: 335 stars, 10 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: 77/100 Strong shortlist","Audit: 80/100 Needs review","Safety: 64/100 Review before install","Review repository, license, install command, and permission surface before production use."]},"alternatives":[{"slug":"dhamaniasad-headlessbrowsers","name":"HeadlessBrowsers","url":"https://www.openagentskill.com/skills/dhamaniasad-headlessbrowsers","install_command":"npx skills add dhamaniasad/HeadlessBrowsers","trust_score":82,"audit_score":82,"safety_score":66,"why_consider":"Matches task terms: browsers","risk":{"level":"Safe to try","safety_tier":"Reviewed with permission notes","safety":"66/100 Review before install","trust":"82/100 Strong shortlist","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},{"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"]}},{"slug":"clovaai-deep-text-recognition-benchmark","name":"Deep Text Recognition Benchmark","url":"https://www.openagentskill.com/skills/clovaai-deep-text-recognition-benchmark","install_command":"npx skills add clovaai/deep-text-recognition-benchmark","trust_score":80,"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":"80/100 Strong shortlist","notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 2y since push"]}},{"slug":"embeddings-benchmark-mteb","name":"Mteb","url":"https://www.openagentskill.com/skills/embeddings-benchmark-mteb","install_command":"npx skills add embeddings-benchmark/mteb","trust_score":86,"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":"86/100 Production candidate","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}}],"outcome_feedback":{"event_id":"resolve_97c4e8f9-7e44-4e8d-897c-29fca969b42e","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_97c4e8f9-7e44-4e8d-897c-29fca969b42e","skill_slug":"techinz-browsers-benchmark","task":"Use Browsers 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_97c4e8f9-7e44-4e8d-897c-29fca969b42e\" --skill \"techinz-browsers-benchmark\" --task \"Use Browsers 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":"2026-08-22T14:34:52.837Z","total_skills_searched":924,"total_candidates":15,"candidate_pool":{"sort":"quality","size":924,"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"}}}