{"query":"Agents Failure Attribution","filters":{"category":null,"platform":null,"track":null,"safety":null,"include_blocked":false,"min_stars":0},"total":10,"skills":[{"rank":1,"match_type":"exact","match_score":99,"raw_match_score":719.1,"semantic_relevance":100,"slug":"ag2ai-agents-failure-attribution","name":"Agents Failure Attribution","description":"Benchmark for automated failure attributions in agentic systems (🏆 ICML 2025 Spotlight)","tagline":"Benchmark for automated failure attributions in agentic systems (🏆 ICML 2025 Spotlight)","category":"agent-frameworks","tags":["multi-agent","orchestration","agent","autogen","llm","multiagent-systems","python","github"],"author":{"name":"ag2ai","verified":false,"url":"https://github.com/ag2ai"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"ag2ai/Agents_Failure_Attribution","creatorName":"ag2ai","creatorUrl":"https://github.com/ag2ai","sourceUrl":"https://github.com/ag2ai/Agents_Failure_Attribution","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/ag2ai-agents-failure-attribution#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":381,"forks":29,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":40.77},"quality":{"score":59,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"381","tone":"neutral"},{"label":"Freshness","value":"6mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":75,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"381 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"381 stars, 29 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":62,"weight":0.14,"status":"info","detail":"6mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add ag2ai/Agents_Failure_Attribution"},{"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/ag2ai/Agents_Failure_Attribution"},{"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":"381 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"381 stars, 29 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"6mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add ag2ai/Agents_Failure_Attribution"},{"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/ag2ai/Agents_Failure_Attribution"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 381 stars, 29 forks; issue activity unavailable in current metadata"],"evidence":{"stars":"381 GitHub stars","repoActivity":"381 stars, 29 forks","lastPushed":"6mo since push","license":"MIT","repository":"https://github.com/ag2ai/Agents_Failure_Attribution","install":"npx skills add ag2ai/Agents_Failure_Attribution","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 ag2ai/Agents_Failure_Attribution","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","6mo since push"]},"agentCompatibility":["Python","Multi-Agent","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: 381 stars, 29 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":["agent-frameworks","multi-agent","orchestration","agent","autogen","llm"],"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: 381 stars, 29 forks; issue activity unavailable in current metadata"]},"safety":{"score":61,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Documentation summary is thin","61/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Documentation summary is thin","61/100 agent safety score"]},"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":"web-scraping","title":"Web scraping"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add ag2ai/Agents_Failure_Attribution","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":381,"starsLabel":"381","forks":29,"license":"MIT","qualityScore":59,"trustScore":75,"auditScore":73},"maintenance":{"status":"stable","label":"6mo since push","daysSincePush":192,"lastPushedAt":"2026-02-11T17:30:51+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 381 stars, 29 forks; issue activity unavailable in current metadata","Needs review"]},"coverageTags":["Coding","GitHub automation","agent-frameworks","multi-agent","orchestration","agent","autogen","llm"]},"audit":{"audit_score":73,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 381 stars, 29 forks; issue activity unavailable in current metadata"]},"decision":{"readiness_score":49,"readiness_label":"Needs manual review","headline":"Needs validation for GitHub automation","role":"Needs validation","primary_fit":"GitHub automation","best_for":["GitHub automation workflows","general agent builders","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one GitHub automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"ag2ai-agents-failure-attribution","name":"Agents Failure Attribution","description":"Benchmark for automated failure attributions in agentic systems (🏆 ICML 2025 Spotlight)","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/ag2ai-agents-failure-attribution","repository":"https://github.com/ag2ai/Agents_Failure_Attribution","github_repo":"ag2ai/Agents_Failure_Attribution"},"suited_tasks":["GitHub automation workflows","general agent builders","builders willing to evaluate younger projects","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Python","Multi-Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add ag2ai/Agents_Failure_Attribution","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 ag2ai-agents-failure-attribution"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Agents Failure Attribution\" agent skill from https://github.com/ag2ai/Agents_Failure_Attribution. 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: Benchmark for automated failure attributions in agentic systems (🏆 ICML 2025 Spotlight) 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\":\"ag2ai-agents-failure-attribution\",\"task\":\"Install Agents Failure Attribution\",\"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 \"Agents Failure Attribution\" as a Claude Code skill from https://github.com/ag2ai/Agents_Failure_Attribution. 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: Benchmark for automated failure attributions in agentic systems (🏆 ICML 2025 Spotlight) 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\":\"ag2ai-agents-failure-attribution\",\"task\":\"Install Agents Failure Attribution\",\"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 \"Agents Failure Attribution\" from https://github.com/ag2ai/Agents_Failure_Attribution 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: Benchmark for automated failure attributions in agentic systems (🏆 ICML 2025 Spotlight) 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\":\"ag2ai-agents-failure-attribution\",\"task\":\"Install Agents Failure Attribution\",\"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/ag2ai-agents-failure-attribution/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/ag2ai-agents-failure-attribution"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"381 GitHub stars","repoActivity":"381 stars, 29 forks","lastPushed":"6mo since push","license":"MIT","repository":"https://github.com/ag2ai/Agents_Failure_Attribution","install":"npx skills add ag2ai/Agents_Failure_Attribution","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","multi-agent","orchestration","agent","autogen","llm"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 381 stars, 29 forks; issue activity unavailable in current metadata"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":73,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 381 stars, 29 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":59,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"6mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Quality score needs review","Stars/forks activity: 381 stars, 29 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 Agents Failure Attribution in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 73/100 Needs review","Safety: 61/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"ag2ai-agents-failure-attribution (Agents Failure Attribution)","install_command":"npx skills add ag2ai/Agents_Failure_Attribution","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":"ag2ai-agents-failure-attribution","task":"Use Agents Failure Attribution in an agent workflow","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/ag2ai-agents-failure-attribution","api":"https://www.openagentskill.com/api/agent/skills/ag2ai-agents-failure-attribution","audit":"https://www.openagentskill.com/skills/ag2ai-agents-failure-attribution/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=ag2ai-agents-failure-attribution&task=Use%20Agents%20Failure%20Attribution%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Agents%20Failure%20Attribution%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Agents%20Failure%20Attribution%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/ag2ai-agents-failure-attribution/install","manifest":"https://www.openagentskill.com/api/registry/manifest/ag2ai-agents-failure-attribution"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"ag2ai-agents-failure-attribution","name":"Agents Failure Attribution","description":"Benchmark for automated failure attributions in agentic systems (🏆 ICML 2025 Spotlight)","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/ag2ai-agents-failure-attribution","repository":"https://github.com/ag2ai/Agents_Failure_Attribution","github_repo":"ag2ai/Agents_Failure_Attribution"},"suited_tasks":["GitHub automation workflows","general agent builders","builders willing to evaluate younger projects","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Python","Multi-Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add ag2ai/Agents_Failure_Attribution","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 ag2ai-agents-failure-attribution"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Agents Failure Attribution\" agent skill from https://github.com/ag2ai/Agents_Failure_Attribution. 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: Benchmark for automated failure attributions in agentic systems (🏆 ICML 2025 Spotlight) 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\":\"ag2ai-agents-failure-attribution\",\"task\":\"Install Agents Failure Attribution\",\"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 \"Agents Failure Attribution\" as a Claude Code skill from https://github.com/ag2ai/Agents_Failure_Attribution. 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: Benchmark for automated failure attributions in agentic systems (🏆 ICML 2025 Spotlight) 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\":\"ag2ai-agents-failure-attribution\",\"task\":\"Install Agents Failure Attribution\",\"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 \"Agents Failure Attribution\" from https://github.com/ag2ai/Agents_Failure_Attribution 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: Benchmark for automated failure attributions in agentic systems (🏆 ICML 2025 Spotlight) 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\":\"ag2ai-agents-failure-attribution\",\"task\":\"Install Agents Failure Attribution\",\"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/ag2ai-agents-failure-attribution/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/ag2ai-agents-failure-attribution"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"381 GitHub stars","repoActivity":"381 stars, 29 forks","lastPushed":"6mo since push","license":"MIT","repository":"https://github.com/ag2ai/Agents_Failure_Attribution","install":"npx skills add ag2ai/Agents_Failure_Attribution","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","multi-agent","orchestration","agent","autogen","llm"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 381 stars, 29 forks; issue activity unavailable in current metadata"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":73,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 381 stars, 29 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":59,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"6mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Quality score needs review","Stars/forks activity: 381 stars, 29 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 Agents Failure Attribution in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 73/100 Needs review","Safety: 61/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"ag2ai-agents-failure-attribution (Agents Failure Attribution)","install_command":"npx skills add ag2ai/Agents_Failure_Attribution","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":"ag2ai-agents-failure-attribution","task":"Use Agents Failure Attribution in an agent workflow","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/ag2ai-agents-failure-attribution","api":"https://www.openagentskill.com/api/agent/skills/ag2ai-agents-failure-attribution","audit":"https://www.openagentskill.com/skills/ag2ai-agents-failure-attribution/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=ag2ai-agents-failure-attribution&task=Use%20Agents%20Failure%20Attribution%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Agents%20Failure%20Attribution%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Agents%20Failure%20Attribution%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/ag2ai-agents-failure-attribution/install","manifest":"https://www.openagentskill.com/api/registry/manifest/ag2ai-agents-failure-attribution"}},"platforms":["Python","Multi-Agent"],"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":"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"}],"install":"npx skills add ag2ai/Agents_Failure_Attribution","install_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 ag2ai-agents-failure-attribution","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 \"Agents Failure Attribution\" agent skill from https://github.com/ag2ai/Agents_Failure_Attribution. 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: Benchmark for automated failure attributions in agentic systems (🏆 ICML 2025 Spotlight) 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\":\"ag2ai-agents-failure-attribution\",\"task\":\"Install Agents Failure Attribution\",\"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 \"Agents Failure Attribution\" as a Claude Code skill from https://github.com/ag2ai/Agents_Failure_Attribution. 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: Benchmark for automated failure attributions in agentic systems (🏆 ICML 2025 Spotlight) 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\":\"ag2ai-agents-failure-attribution\",\"task\":\"Install Agents Failure Attribution\",\"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 \"Agents Failure Attribution\" from https://github.com/ag2ai/Agents_Failure_Attribution 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: Benchmark for automated failure attributions in agentic systems (🏆 ICML 2025 Spotlight) 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\":\"ag2ai-agents-failure-attribution\",\"task\":\"Install Agents Failure Attribution\",\"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"}],"repository":"https://github.com/ag2ai/Agents_Failure_Attribution","github_repo":"ag2ai/Agents_Failure_Attribution","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"ag2ai/agents_failure_attribution","recommendation_reasons":["Matches task terms: failure, attribution","Install handoff is available","Repository freshness signal is available","Registry match score 99"],"urls":{"web":"https://www.openagentskill.com/skills/ag2ai-agents-failure-attribution","api":"https://www.openagentskill.com/api/agent/skills/ag2ai-agents-failure-attribution","install_api":"https://www.openagentskill.com/api/skills/ag2ai-agents-failure-attribution/install","audit":"https://www.openagentskill.com/skills/ag2ai-agents-failure-attribution/audit","repository":"https://github.com/ag2ai/Agents_Failure_Attribution"}},{"rank":2,"match_type":"related","match_score":6,"raw_match_score":43.5,"semantic_relevance":30,"slug":"alirezarezvani-agent-designer","name":"agent-designer","description":"Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer).","tagline":"Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research au","category":"research","tags":["agent-skill"],"author":{"name":"alirezarezvani","verified":false,"url":"https://github.com/alirezarezvani"},"attribution":{"status":"registry_indexed","statusLabel":"Registry indexed","shortLabel":"REGISTRY INDEXED","sourceLabel":"recursive skill source sync","sourceDetail":"alirezarezvani/claude-skills","creatorName":"alirezarezvani","creatorUrl":"https://github.com/alirezarezvani","sourceUrl":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-designer","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/alirezarezvani-agent-designer#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":24795,"forks":3494,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":54.31},"quality":{"score":91,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"25K","tone":"positive"},{"label":"Freshness","value":"1d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","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":100,"weight":0.13,"status":"pass","detail":"25K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"25K stars, 3.5K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"1d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":62,"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 alirezarezvani/claude-skills --skill agent-designer"},{"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/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-designer"},{"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":"25K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"25K stars, 3.5K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"1d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add alirezarezvani/claude-skills --skill agent-designer"},{"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/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-designer"},{"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","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review"],"evidence":{"stars":"25K GitHub stars","repoActivity":"25K stars, 3.5K forks","lastPushed":"1d since push","license":"MIT","repository":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-designer","install":"npx skills add alirezarezvani/claude-skills --skill agent-designer","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 alirezarezvani/claude-skills --skill agent-designer","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","1d since push"]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Quality score needs review"]},"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":["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"],"knownRisks":["Quality score needs review"]},"safety":{"score":75,"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","75/100 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"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["Quality score needs review"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"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","75/100 agent safety score"]},"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":"workflow-automation","title":"Workflow automation"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"research-agents","title":"Research agents"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add alirezarezvani/claude-skills --skill agent-designer","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":24795,"starsLabel":"25K","forks":3494,"license":"MIT","qualityScore":91,"trustScore":86,"auditScore":91},"maintenance":{"status":"fresh","label":"1d since push","daysSincePush":1,"lastPushedAt":"2026-08-22T12:31:34+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Quality score needs review"]},"coverageTags":["Research","Research agents","agent-skill"]},"audit":{"audit_score":91,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Workflow automation","role":"Primary pick","primary_fit":"Workflow automation","best_for":["Workflow 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 Workflow 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."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"alirezarezvani-agent-designer","name":"agent-designer","description":"Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer).","category":"research","url":"https://www.openagentskill.com/skills/alirezarezvani-agent-designer","repository":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-designer","github_repo":"alirezarezvani/claude-skills"},"suited_tasks":["Workflow automation workflows","Claude Code teams","teams that value GitHub adoption signals","Move data between tools","Transform files","Trigger repeatable actions","Navigate pages","Click and type safely"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add alirezarezvani/claude-skills --skill agent-designer","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 alirezarezvani-agent-designer"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"agent-designer\" agent skill from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-designer. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-designer\",\"task\":\"Install agent-designer\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"agent-designer\" as a Claude Code skill from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-designer. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-designer\",\"task\":\"Install agent-designer\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"agent-designer\" from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-designer into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-designer\",\"task\":\"Install agent-designer\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/alirezarezvani-agent-designer/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/alirezarezvani-agent-designer"},"trust":{"score":86,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"25K GitHub stars","repoActivity":"25K stars, 3.5K forks","lastPushed":"1d since push","license":"MIT","repository":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-designer","install":"npx skills add alirezarezvani/claude-skills --skill agent-designer","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":["research","agent-skill"],"known_risks":["Quality score needs review"]},"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":91,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review"]},"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":91,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"1d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Quality score needs review","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 agent-designer in an agent workflow","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: 91/100 Safe to try","Safety: 75/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"alirezarezvani-agent-designer (agent-designer)","install_command":"npx skills add alirezarezvani/claude-skills --skill agent-designer","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":"alirezarezvani-agent-designer","task":"Use agent-designer in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/alirezarezvani-agent-designer","api":"https://www.openagentskill.com/api/agent/skills/alirezarezvani-agent-designer","audit":"https://www.openagentskill.com/skills/alirezarezvani-agent-designer/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=alirezarezvani-agent-designer&task=Use%20agent-designer%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20agent-designer%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20agent-designer%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/alirezarezvani-agent-designer/install","manifest":"https://www.openagentskill.com/api/registry/manifest/alirezarezvani-agent-designer"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"alirezarezvani-agent-designer","name":"agent-designer","description":"Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer).","category":"research","url":"https://www.openagentskill.com/skills/alirezarezvani-agent-designer","repository":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-designer","github_repo":"alirezarezvani/claude-skills"},"suited_tasks":["Workflow automation workflows","Claude Code teams","teams that value GitHub adoption signals","Move data between tools","Transform files","Trigger repeatable actions","Navigate pages","Click and type safely"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add alirezarezvani/claude-skills --skill agent-designer","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 alirezarezvani-agent-designer"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"agent-designer\" agent skill from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-designer. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-designer\",\"task\":\"Install agent-designer\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"agent-designer\" as a Claude Code skill from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-designer. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-designer\",\"task\":\"Install agent-designer\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"agent-designer\" from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-designer into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-designer\",\"task\":\"Install agent-designer\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/alirezarezvani-agent-designer/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/alirezarezvani-agent-designer"},"trust":{"score":86,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"25K GitHub stars","repoActivity":"25K stars, 3.5K forks","lastPushed":"1d since push","license":"MIT","repository":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-designer","install":"npx skills add alirezarezvani/claude-skills --skill agent-designer","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":["research","agent-skill"],"known_risks":["Quality score needs review"]},"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":91,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review"]},"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":91,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"1d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Quality score needs review","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 agent-designer in an agent workflow","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: 91/100 Safe to try","Safety: 75/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"alirezarezvani-agent-designer (agent-designer)","install_command":"npx skills add alirezarezvani/claude-skills --skill agent-designer","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":"alirezarezvani-agent-designer","task":"Use agent-designer in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/alirezarezvani-agent-designer","api":"https://www.openagentskill.com/api/agent/skills/alirezarezvani-agent-designer","audit":"https://www.openagentskill.com/skills/alirezarezvani-agent-designer/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=alirezarezvani-agent-designer&task=Use%20agent-designer%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20agent-designer%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20agent-designer%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/alirezarezvani-agent-designer/install","manifest":"https://www.openagentskill.com/api/registry/manifest/alirezarezvani-agent-designer"}},"platforms":["Claude Code"],"use_cases":[{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"}],"install":"npx skills add alirezarezvani/claude-skills --skill agent-designer","install_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 alirezarezvani-agent-designer","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"agent-designer\" agent skill from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-designer. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-designer\",\"task\":\"Install agent-designer\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"agent-designer\" as a Claude Code skill from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-designer. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-designer\",\"task\":\"Install agent-designer\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"agent-designer\" from https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-designer into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Use when the user asks to design a multi-agent system, pick an orchestration pattern (supervisor/swarm/pipeline), generate tool schemas for agents, or evaluate agent execution logs for cost, latency, and failure bottlenecks. Examples: 'design an agent architecture for research automation', 'generate Anthropic tool schemas from these tool descriptions', 'analyze these agent run logs for bottlenecks'. NOT for Claude Code workflow files (use workflow-builder) or single-agent prompt design (use agent-workflow-designer). After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"alirezarezvani-agent-designer\",\"task\":\"Install agent-designer\",\"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"}],"repository":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-designer","github_repo":"alirezarezvani/claude-skills","version":"1.0.0","license":"MIT","updated_at":"2026-08-22T13:22:36.491413+00:00","canonical_key":"alirezarezvani/claude-skills#.gemini/skills/agent-designer","recommendation_reasons":["Matches task terms: failure","Strong GitHub adoption: 24,795 stars","Install handoff is available","Repository freshness signal is available","Registry match score 6"],"urls":{"web":"https://www.openagentskill.com/skills/alirezarezvani-agent-designer","api":"https://www.openagentskill.com/api/agent/skills/alirezarezvani-agent-designer","install_api":"https://www.openagentskill.com/api/skills/alirezarezvani-agent-designer/install","audit":"https://www.openagentskill.com/skills/alirezarezvani-agent-designer/audit","repository":"https://github.com/alirezarezvani/claude-skills/tree/main/.gemini/skills/agent-designer"}},{"rank":3,"match_type":"related","match_score":6,"raw_match_score":43.4,"semantic_relevance":30,"slug":"uptrain-ai-uptrain","name":"Uptrain","description":"UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them.","tagline":"UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them.","category":"development","tags":["llmops","developer-tools","autoevaluation","evaluation","experimentation","hallucination-detection","jailbreak-detection","llm-eval","llm-prompting","llm-test"],"author":{"name":"uptrain-ai","verified":true,"url":"https://github.com/uptrain-ai"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"uptrain-ai/uptrain","creatorName":"uptrain-ai","creatorUrl":"https://github.com/uptrain-ai","sourceUrl":"https://github.com/uptrain-ai/uptrain","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/uptrain-ai-uptrain#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":2350,"forks":202,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":50.3},"quality":{"score":74,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"2.4K","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":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":86,"weight":0.13,"status":"pass","detail":"2.4K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":77,"weight":0.08,"status":"info","detail":"2.4K stars, 202 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 uptrain-ai/uptrain"},{"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/uptrain-ai/uptrain"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"2.4K GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"2.4K stars, 202 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 uptrain-ai/uptrain"},{"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/uptrain-ai/uptrain"},{"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","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":"2.4K GitHub stars","repoActivity":"2.4K stars, 202 forks","lastPushed":"2y since push","license":"Apache-2.0","repository":"https://github.com/uptrain-ai/uptrain","install":"npx skills add uptrain-ai/uptrain","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 uptrain-ai/uptrain","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":["Python","LLMOps","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":["development","llmops","developer-tools","autoevaluation","evaluation","experimentation"],"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"]},"safety":{"score":61,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Repository appears stale","61/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Repository appears stale"],"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":["Repository appears stale","61/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"research-agents","title":"Research agents"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add uptrain-ai/uptrain","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":2350,"starsLabel":"2.4K","forks":202,"license":"Apache-2.0","qualityScore":74,"trustScore":79,"auditScore":73},"maintenance":{"status":"stale","label":"2y since push","daysSincePush":735,"lastPushedAt":"2024-08-18T13:30:44+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 2y since push"]},"coverageTags":["Coding","Coding agents","development","llmops","developer-tools","autoevaluation","evaluation","experimentation"]},"audit":{"audit_score":73,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 2y since push"]},"decision":{"readiness_score":76,"readiness_label":"Strong shortlist","headline":"Companion skill for Coding agents","role":"Companion skill","primary_fit":"Coding agents","best_for":["Coding 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 Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"uptrain-ai-uptrain","name":"Uptrain","description":"UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them.","category":"development","url":"https://www.openagentskill.com/skills/uptrain-ai-uptrain","repository":"https://github.com/uptrain-ai/uptrain","github_repo":"uptrain-ai/uptrain"},"suited_tasks":["Coding agents workflows","general agent builders","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Navigate pages","Click and type safely"],"suited_agents":["Python","LLMOps","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add uptrain-ai/uptrain","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 uptrain-ai-uptrain"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Uptrain\" agent skill from https://github.com/uptrain-ai/uptrain. 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: UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them. 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\":\"uptrain-ai-uptrain\",\"task\":\"Install Uptrain\",\"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 \"Uptrain\" as a Claude Code skill from https://github.com/uptrain-ai/uptrain. 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: UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them. 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\":\"uptrain-ai-uptrain\",\"task\":\"Install Uptrain\",\"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 \"Uptrain\" from https://github.com/uptrain-ai/uptrain 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: UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them. 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\":\"uptrain-ai-uptrain\",\"task\":\"Install Uptrain\",\"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/uptrain-ai-uptrain/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/uptrain-ai-uptrain"},"trust":{"score":79,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"2.4K GitHub stars","repoActivity":"2.4K stars, 202 forks","lastPushed":"2y since push","license":"Apache-2.0","repository":"https://github.com/uptrain-ai/uptrain","install":"npx skills add uptrain-ai/uptrain","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":["development","llmops","developer-tools","autoevaluation","evaluation","experimentation"],"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":73,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 2y since push"]},"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":74,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","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","No OpenAgentSkill engagement data yet","Repository appears stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 2y since push"],"agent_contract":{"task_input":"Use Uptrain in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 79/100 Strong shortlist","Audit: 73/100 Needs review","Safety: 61/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"uptrain-ai-uptrain (Uptrain)","install_command":"npx skills add uptrain-ai/uptrain","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":"uptrain-ai-uptrain","task":"Use Uptrain in an agent workflow","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/uptrain-ai-uptrain","api":"https://www.openagentskill.com/api/agent/skills/uptrain-ai-uptrain","audit":"https://www.openagentskill.com/skills/uptrain-ai-uptrain/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=uptrain-ai-uptrain&task=Use%20Uptrain%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Uptrain%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Uptrain%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/uptrain-ai-uptrain/install","manifest":"https://www.openagentskill.com/api/registry/manifest/uptrain-ai-uptrain"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"uptrain-ai-uptrain","name":"Uptrain","description":"UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them.","category":"development","url":"https://www.openagentskill.com/skills/uptrain-ai-uptrain","repository":"https://github.com/uptrain-ai/uptrain","github_repo":"uptrain-ai/uptrain"},"suited_tasks":["Coding agents workflows","general agent builders","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Navigate pages","Click and type safely"],"suited_agents":["Python","LLMOps","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add uptrain-ai/uptrain","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 uptrain-ai-uptrain"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Uptrain\" agent skill from https://github.com/uptrain-ai/uptrain. 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: UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them. 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\":\"uptrain-ai-uptrain\",\"task\":\"Install Uptrain\",\"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 \"Uptrain\" as a Claude Code skill from https://github.com/uptrain-ai/uptrain. 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: UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them. 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\":\"uptrain-ai-uptrain\",\"task\":\"Install Uptrain\",\"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 \"Uptrain\" from https://github.com/uptrain-ai/uptrain 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: UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them. 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\":\"uptrain-ai-uptrain\",\"task\":\"Install Uptrain\",\"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/uptrain-ai-uptrain/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/uptrain-ai-uptrain"},"trust":{"score":79,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"2.4K GitHub stars","repoActivity":"2.4K stars, 202 forks","lastPushed":"2y since push","license":"Apache-2.0","repository":"https://github.com/uptrain-ai/uptrain","install":"npx skills add uptrain-ai/uptrain","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":["development","llmops","developer-tools","autoevaluation","evaluation","experimentation"],"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":73,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 2y since push"]},"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":74,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","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","No OpenAgentSkill engagement data yet","Repository appears stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 2y since push"],"agent_contract":{"task_input":"Use Uptrain in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 79/100 Strong shortlist","Audit: 73/100 Needs review","Safety: 61/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"uptrain-ai-uptrain (Uptrain)","install_command":"npx skills add uptrain-ai/uptrain","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":"uptrain-ai-uptrain","task":"Use Uptrain in an agent workflow","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/uptrain-ai-uptrain","api":"https://www.openagentskill.com/api/agent/skills/uptrain-ai-uptrain","audit":"https://www.openagentskill.com/skills/uptrain-ai-uptrain/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=uptrain-ai-uptrain&task=Use%20Uptrain%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Uptrain%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Uptrain%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/uptrain-ai-uptrain/install","manifest":"https://www.openagentskill.com/api/registry/manifest/uptrain-ai-uptrain"}},"platforms":["Python","LLMOps"],"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"testing-qa","title":"Testing and QA","url":"https://www.openagentskill.com/use-cases/testing-qa"}],"install":"npx skills add uptrain-ai/uptrain","install_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 uptrain-ai-uptrain","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 \"Uptrain\" agent skill from https://github.com/uptrain-ai/uptrain. 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: UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them. 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\":\"uptrain-ai-uptrain\",\"task\":\"Install Uptrain\",\"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 \"Uptrain\" as a Claude Code skill from https://github.com/uptrain-ai/uptrain. 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: UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them. 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\":\"uptrain-ai-uptrain\",\"task\":\"Install Uptrain\",\"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 \"Uptrain\" from https://github.com/uptrain-ai/uptrain 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: UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them. 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\":\"uptrain-ai-uptrain\",\"task\":\"Install Uptrain\",\"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"}],"repository":"https://github.com/uptrain-ai/uptrain","github_repo":"uptrain-ai/uptrain","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"uptrain-ai/uptrain","recommendation_reasons":["Matches task terms: failure","Useful GitHub adoption: 2,350 stars","Install handoff is available","Repository freshness signal is available","Registry match score 6"],"urls":{"web":"https://www.openagentskill.com/skills/uptrain-ai-uptrain","api":"https://www.openagentskill.com/api/agent/skills/uptrain-ai-uptrain","install_api":"https://www.openagentskill.com/api/skills/uptrain-ai-uptrain/install","audit":"https://www.openagentskill.com/skills/uptrain-ai-uptrain/audit","repository":"https://github.com/uptrain-ai/uptrain"}},{"rank":4,"match_type":"related","match_score":6,"raw_match_score":40,"semantic_relevance":30,"slug":"aaravkashyap12-advise-project-approach","name":"Advise Project Approach","description":"A portable agent skill that makes AI agents research comparable projects, tradeoffs, costs, and failure conditions before giving build advice.","tagline":"A Claude/Codex skill that makes AI agents research comparable projects, tradeoffs, costs, and failure conditions before giving build advice.","category":"productivity","tags":["agent-skill","project-planning","claude-code","codex","decision-making"],"author":{"name":"AaravKashyap12","verified":true,"url":"https://github.com/AaravKashyap12"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"OpenAgentSkill auto-indexer","sourceDetail":"AaravKashyap12/advise-project-approach","creatorName":"AaravKashyap12","creatorUrl":"https://github.com/AaravKashyap12","sourceUrl":"https://github.com/AaravKashyap12/advise-project-approach","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/aaravkashyap12-advise-project-approach#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":176,"forks":18,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":58.94},"quality":{"score":89,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"176","tone":"neutral"},{"label":"Freshness","value":"11d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","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":62,"weight":0.13,"status":"info","detail":"176 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"176 stars, 18 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"11d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add AaravKashyap12/advise-project-approach"},{"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/AaravKashyap12/advise-project-approach"},{"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":"176 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"176 stars, 18 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"11d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add AaravKashyap12/advise-project-approach"},{"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/AaravKashyap12/advise-project-approach"},{"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","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin","Stars/forks activity: 176 stars, 18 forks; issue activity unavailable in current metadata"],"evidence":{"stars":"176 GitHub stars","repoActivity":"176 stars, 18 forks","lastPushed":"11d since push","license":"MIT","repository":"https://github.com/AaravKashyap12/advise-project-approach","install":"npx skills add AaravKashyap12/advise-project-approach","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 AaravKashyap12/advise-project-approach","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","11d since push"]},"agentCompatibility":["Python","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Documentation summary is thin","Stars/forks activity: 176 stars, 18 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":["productivity","agent-skill","project-planning","claude-code","codex","decision-making"],"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","Stars/forks activity: 176 stars, 18 forks; issue activity unavailable in current metadata"]},"safety":{"score":78,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","78/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["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","78/100 agent safety score"]},"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","OpenAI Agents","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add AaravKashyap12/advise-project-approach","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":176,"starsLabel":"176","forks":18,"license":"MIT","qualityScore":89,"trustScore":85,"auditScore":90},"maintenance":{"status":"fresh","label":"11d since push","daysSincePush":11,"lastPushedAt":"2026-08-11T17:00:46+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin","Stars/forks activity: 176 stars, 18 forks; issue activity unavailable in current metadata"]},"coverageTags":["Research","Research agents","productivity","agent-skill","project-planning","claude-code","codex","decision-making"]},"audit":{"audit_score":90,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","Stars/forks activity: 176 stars, 18 forks; issue activity unavailable in current metadata"]},"decision":{"readiness_score":88,"readiness_label":"Production-ready","headline":"Primary pick for Research agents","role":"Primary pick","primary_fit":"Research agents","best_for":["Research agents workflows","Claude Code teams","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Research agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"aaravkashyap12-advise-project-approach","name":"Advise Project Approach","description":"A portable agent skill that makes AI agents research comparable projects, tradeoffs, costs, and failure conditions before giving build advice.","category":"productivity","url":"https://www.openagentskill.com/skills/aaravkashyap12-advise-project-approach","repository":"https://github.com/AaravKashyap12/advise-project-approach","github_repo":"AaravKashyap12/advise-project-approach"},"suited_tasks":["Research agents workflows","Claude Code teams","builders willing to evaluate younger projects","Search sources","Extract claims","Synthesize findings","Inspect source files","Explain architecture"],"suited_agents":["Python","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add AaravKashyap12/advise-project-approach","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 aaravkashyap12-advise-project-approach"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Advise Project Approach\" agent skill from https://github.com/AaravKashyap12/advise-project-approach. 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 portable agent skill that makes AI agents research comparable projects, tradeoffs, costs, and failure conditions before giving build advice. 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\":\"aaravkashyap12-advise-project-approach\",\"task\":\"Install Advise Project Approach\",\"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 \"Advise Project Approach\" as a Claude Code skill from https://github.com/AaravKashyap12/advise-project-approach. 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 portable agent skill that makes AI agents research comparable projects, tradeoffs, costs, and failure conditions before giving build advice. 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\":\"aaravkashyap12-advise-project-approach\",\"task\":\"Install Advise Project Approach\",\"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 \"Advise Project Approach\" from https://github.com/AaravKashyap12/advise-project-approach 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 portable agent skill that makes AI agents research comparable projects, tradeoffs, costs, and failure conditions before giving build advice. 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\":\"aaravkashyap12-advise-project-approach\",\"task\":\"Install Advise Project Approach\",\"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/aaravkashyap12-advise-project-approach/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/aaravkashyap12-advise-project-approach"},"trust":{"score":85,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"176 GitHub stars","repoActivity":"176 stars, 18 forks","lastPushed":"11d since push","license":"MIT","repository":"https://github.com/AaravKashyap12/advise-project-approach","install":"npx skills add AaravKashyap12/advise-project-approach","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":["productivity","agent-skill","project-planning","claude-code","codex","decision-making"],"known_risks":["Documentation summary is thin","Stars/forks activity: 176 stars, 18 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":90,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","Stars/forks activity: 176 stars, 18 forks; issue activity unavailable in current metadata"]},"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":89,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"11d 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","Stars/forks activity: 176 stars, 18 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","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use Advise Project Approach in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 85/100 Strong shortlist","Audit: 90/100 Safe to try","Safety: 78/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"aaravkashyap12-advise-project-approach (Advise Project Approach)","install_command":"npx skills add AaravKashyap12/advise-project-approach","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":"aaravkashyap12-advise-project-approach","task":"Use Advise Project Approach in an agent workflow","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/aaravkashyap12-advise-project-approach","api":"https://www.openagentskill.com/api/agent/skills/aaravkashyap12-advise-project-approach","audit":"https://www.openagentskill.com/skills/aaravkashyap12-advise-project-approach/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=aaravkashyap12-advise-project-approach&task=Use%20Advise%20Project%20Approach%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Advise%20Project%20Approach%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Advise%20Project%20Approach%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/aaravkashyap12-advise-project-approach/install","manifest":"https://www.openagentskill.com/api/registry/manifest/aaravkashyap12-advise-project-approach"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"aaravkashyap12-advise-project-approach","name":"Advise Project Approach","description":"A portable agent skill that makes AI agents research comparable projects, tradeoffs, costs, and failure conditions before giving build advice.","category":"productivity","url":"https://www.openagentskill.com/skills/aaravkashyap12-advise-project-approach","repository":"https://github.com/AaravKashyap12/advise-project-approach","github_repo":"AaravKashyap12/advise-project-approach"},"suited_tasks":["Research agents workflows","Claude Code teams","builders willing to evaluate younger projects","Search sources","Extract claims","Synthesize findings","Inspect source files","Explain architecture"],"suited_agents":["Python","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add AaravKashyap12/advise-project-approach","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 aaravkashyap12-advise-project-approach"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Advise Project Approach\" agent skill from https://github.com/AaravKashyap12/advise-project-approach. 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 portable agent skill that makes AI agents research comparable projects, tradeoffs, costs, and failure conditions before giving build advice. 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\":\"aaravkashyap12-advise-project-approach\",\"task\":\"Install Advise Project Approach\",\"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 \"Advise Project Approach\" as a Claude Code skill from https://github.com/AaravKashyap12/advise-project-approach. 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 portable agent skill that makes AI agents research comparable projects, tradeoffs, costs, and failure conditions before giving build advice. 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\":\"aaravkashyap12-advise-project-approach\",\"task\":\"Install Advise Project Approach\",\"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 \"Advise Project Approach\" from https://github.com/AaravKashyap12/advise-project-approach 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 portable agent skill that makes AI agents research comparable projects, tradeoffs, costs, and failure conditions before giving build advice. 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\":\"aaravkashyap12-advise-project-approach\",\"task\":\"Install Advise Project Approach\",\"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/aaravkashyap12-advise-project-approach/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/aaravkashyap12-advise-project-approach"},"trust":{"score":85,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"176 GitHub stars","repoActivity":"176 stars, 18 forks","lastPushed":"11d since push","license":"MIT","repository":"https://github.com/AaravKashyap12/advise-project-approach","install":"npx skills add AaravKashyap12/advise-project-approach","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":["productivity","agent-skill","project-planning","claude-code","codex","decision-making"],"known_risks":["Documentation summary is thin","Stars/forks activity: 176 stars, 18 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":90,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","Stars/forks activity: 176 stars, 18 forks; issue activity unavailable in current metadata"]},"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":89,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"11d 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","Stars/forks activity: 176 stars, 18 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","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use Advise Project Approach in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 85/100 Strong shortlist","Audit: 90/100 Safe to try","Safety: 78/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"aaravkashyap12-advise-project-approach (Advise Project Approach)","install_command":"npx skills add AaravKashyap12/advise-project-approach","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":"aaravkashyap12-advise-project-approach","task":"Use Advise Project Approach in an agent workflow","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/aaravkashyap12-advise-project-approach","api":"https://www.openagentskill.com/api/agent/skills/aaravkashyap12-advise-project-approach","audit":"https://www.openagentskill.com/skills/aaravkashyap12-advise-project-approach/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=aaravkashyap12-advise-project-approach&task=Use%20Advise%20Project%20Approach%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Advise%20Project%20Approach%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Advise%20Project%20Approach%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/aaravkashyap12-advise-project-approach/install","manifest":"https://www.openagentskill.com/api/registry/manifest/aaravkashyap12-advise-project-approach"}},"platforms":["Python","Claude Code","OpenAI Agents"],"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"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"install":"npx skills add AaravKashyap12/advise-project-approach","install_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 aaravkashyap12-advise-project-approach","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 \"Advise Project Approach\" agent skill from https://github.com/AaravKashyap12/advise-project-approach. 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 portable agent skill that makes AI agents research comparable projects, tradeoffs, costs, and failure conditions before giving build advice. 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\":\"aaravkashyap12-advise-project-approach\",\"task\":\"Install Advise Project Approach\",\"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 \"Advise Project Approach\" as a Claude Code skill from https://github.com/AaravKashyap12/advise-project-approach. 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 portable agent skill that makes AI agents research comparable projects, tradeoffs, costs, and failure conditions before giving build advice. 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\":\"aaravkashyap12-advise-project-approach\",\"task\":\"Install Advise Project Approach\",\"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 \"Advise Project Approach\" from https://github.com/AaravKashyap12/advise-project-approach 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 portable agent skill that makes AI agents research comparable projects, tradeoffs, costs, and failure conditions before giving build advice. 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\":\"aaravkashyap12-advise-project-approach\",\"task\":\"Install Advise Project Approach\",\"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"}],"repository":"https://github.com/AaravKashyap12/advise-project-approach","github_repo":"AaravKashyap12/advise-project-approach","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"aaravkashyap12/advise-project-approach","recommendation_reasons":["Matches task terms: failure","Install handoff is available","Repository freshness signal is available","Registry match score 6"],"urls":{"web":"https://www.openagentskill.com/skills/aaravkashyap12-advise-project-approach","api":"https://www.openagentskill.com/api/agent/skills/aaravkashyap12-advise-project-approach","install_api":"https://www.openagentskill.com/api/skills/aaravkashyap12-advise-project-approach/install","audit":"https://www.openagentskill.com/skills/aaravkashyap12-advise-project-approach/audit","repository":"https://github.com/AaravKashyap12/advise-project-approach"}},{"rank":5,"match_type":"related","match_score":5,"raw_match_score":35,"semantic_relevance":30,"slug":"amelnagdy-guard-skills","name":"Guard Skills","description":"Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs","tagline":"Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs","category":"agent-skills","tags":["agent-skills","skills","ai","claude","claude-code","code-review","codex","skills-sh","woocommerce","wordpress"],"author":{"name":"amElnagdy","verified":false,"url":"https://github.com/amElnagdy"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"amElnagdy/guard-skills","creatorName":"amElnagdy","creatorUrl":"https://github.com/amElnagdy","sourceUrl":"https://github.com/amElnagdy/guard-skills","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/amelnagdy-guard-skills#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":717,"forks":81,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":50.69},"quality":{"score":74,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"717","tone":"positive"},{"label":"Freshness","value":"3mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":81,"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":76,"weight":0.13,"status":"info","detail":"717 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":71,"weight":0.08,"status":"info","detail":"717 stars, 81 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":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add amElnagdy/guard-skills"},{"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/amElnagdy/guard-skills"},{"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":"717 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"717 stars, 81 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add amElnagdy/guard-skills"},{"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/amElnagdy/guard-skills"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin"],"evidence":{"stars":"717 GitHub stars","repoActivity":"717 stars, 81 forks","lastPushed":"3mo since push","license":"MIT","repository":"https://github.com/amElnagdy/guard-skills","install":"npx skills add amElnagdy/guard-skills","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 amElnagdy/guard-skills","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","3mo since push"]},"agentCompatibility":["AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["agent-skills","skills","ai","claude","claude-code","code-review"],"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"]},"safety":{"score":70,"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","70/100 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","70/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"github-automation","title":"GitHub automation"}]},"applicableAgents":["Claude Code","OpenAI Agents","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add amElnagdy/guard-skills","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":717,"starsLabel":"717","forks":81,"license":"MIT","qualityScore":74,"trustScore":81,"auditScore":82},"maintenance":{"status":"active","label":"3mo since push","daysSincePush":77,"lastPushedAt":"2026-06-07T11:46:54+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin","Quality score needs review"]},"coverageTags":["Coding","Coding agents","agent-skills","skills","ai","claude","claude-code","code-review"]},"audit":{"audit_score":82,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","Quality score needs review"]},"decision":{"readiness_score":85,"readiness_label":"Production-ready","headline":"Primary pick for Coding agents","role":"Primary pick","primary_fit":"Coding agents","best_for":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"amelnagdy-guard-skills","name":"Guard Skills","description":"Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs","category":"agent-skills","url":"https://www.openagentskill.com/skills/amelnagdy-guard-skills","repository":"https://github.com/amElnagdy/guard-skills","github_repo":"amElnagdy/guard-skills"},"suited_tasks":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Navigate pages","Click and type safely"],"suited_agents":["AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add amElnagdy/guard-skills","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 amelnagdy-guard-skills"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Guard Skills\" agent skill from https://github.com/amElnagdy/guard-skills. 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: Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs 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\":\"amelnagdy-guard-skills\",\"task\":\"Install Guard Skills\",\"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 \"Guard Skills\" as a Claude Code skill from https://github.com/amElnagdy/guard-skills. 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: Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs 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\":\"amelnagdy-guard-skills\",\"task\":\"Install Guard Skills\",\"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 \"Guard Skills\" from https://github.com/amElnagdy/guard-skills 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: Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs 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\":\"amelnagdy-guard-skills\",\"task\":\"Install Guard Skills\",\"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/amelnagdy-guard-skills/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/amelnagdy-guard-skills"},"trust":{"score":81,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"717 GitHub stars","repoActivity":"717 stars, 81 forks","lastPushed":"3mo since push","license":"MIT","repository":"https://github.com/amElnagdy/guard-skills","install":"npx skills add amElnagdy/guard-skills","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-skills","skills","ai","claude","claude-code","code-review"],"known_risks":["Quality score needs review","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":82,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","Quality score needs review"]},"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":74,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","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","Documentation summary is thin","Quality score needs 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"],"agent_contract":{"task_input":"Use Guard Skills in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 81/100 Strong shortlist","Audit: 82/100 Safe to try","Safety: 70/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"amelnagdy-guard-skills (Guard Skills)","install_command":"npx skills add amElnagdy/guard-skills","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":"amelnagdy-guard-skills","task":"Use Guard Skills in an agent workflow","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/amelnagdy-guard-skills","api":"https://www.openagentskill.com/api/agent/skills/amelnagdy-guard-skills","audit":"https://www.openagentskill.com/skills/amelnagdy-guard-skills/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=amelnagdy-guard-skills&task=Use%20Guard%20Skills%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Guard%20Skills%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Guard%20Skills%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/amelnagdy-guard-skills/install","manifest":"https://www.openagentskill.com/api/registry/manifest/amelnagdy-guard-skills"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"amelnagdy-guard-skills","name":"Guard Skills","description":"Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs","category":"agent-skills","url":"https://www.openagentskill.com/skills/amelnagdy-guard-skills","repository":"https://github.com/amElnagdy/guard-skills","github_repo":"amElnagdy/guard-skills"},"suited_tasks":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Navigate pages","Click and type safely"],"suited_agents":["AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add amElnagdy/guard-skills","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 amelnagdy-guard-skills"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Guard Skills\" agent skill from https://github.com/amElnagdy/guard-skills. 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: Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs 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\":\"amelnagdy-guard-skills\",\"task\":\"Install Guard Skills\",\"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 \"Guard Skills\" as a Claude Code skill from https://github.com/amElnagdy/guard-skills. 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: Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs 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\":\"amelnagdy-guard-skills\",\"task\":\"Install Guard Skills\",\"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 \"Guard Skills\" from https://github.com/amElnagdy/guard-skills 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: Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs 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\":\"amelnagdy-guard-skills\",\"task\":\"Install Guard Skills\",\"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/amelnagdy-guard-skills/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/amelnagdy-guard-skills"},"trust":{"score":81,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"717 GitHub stars","repoActivity":"717 stars, 81 forks","lastPushed":"3mo since push","license":"MIT","repository":"https://github.com/amElnagdy/guard-skills","install":"npx skills add amElnagdy/guard-skills","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-skills","skills","ai","claude","claude-code","code-review"],"known_risks":["Quality score needs review","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":82,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","Quality score needs review"]},"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":74,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","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","Documentation summary is thin","Quality score needs 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"],"agent_contract":{"task_input":"Use Guard Skills in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 81/100 Strong shortlist","Audit: 82/100 Safe to try","Safety: 70/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"amelnagdy-guard-skills (Guard Skills)","install_command":"npx skills add amElnagdy/guard-skills","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":"amelnagdy-guard-skills","task":"Use Guard Skills in an agent workflow","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/amelnagdy-guard-skills","api":"https://www.openagentskill.com/api/agent/skills/amelnagdy-guard-skills","audit":"https://www.openagentskill.com/skills/amelnagdy-guard-skills/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=amelnagdy-guard-skills&task=Use%20Guard%20Skills%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Guard%20Skills%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Guard%20Skills%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/amelnagdy-guard-skills/install","manifest":"https://www.openagentskill.com/api/registry/manifest/amelnagdy-guard-skills"}},"platforms":["AI Agents","Claude Code","OpenAI Agents"],"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"testing-qa","title":"Testing and QA","url":"https://www.openagentskill.com/use-cases/testing-qa"}],"install":"npx skills add amElnagdy/guard-skills","install_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 amelnagdy-guard-skills","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 \"Guard Skills\" agent skill from https://github.com/amElnagdy/guard-skills. 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: Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs 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\":\"amelnagdy-guard-skills\",\"task\":\"Install Guard Skills\",\"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 \"Guard Skills\" as a Claude Code skill from https://github.com/amElnagdy/guard-skills. 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: Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs 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\":\"amelnagdy-guard-skills\",\"task\":\"Install Guard Skills\",\"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 \"Guard Skills\" from https://github.com/amElnagdy/guard-skills 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: Guard skills for coding agents, quality gates that catch AI-generated failure modes in code, tests, and docs 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\":\"amelnagdy-guard-skills\",\"task\":\"Install Guard Skills\",\"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"}],"repository":"https://github.com/amElnagdy/guard-skills","github_repo":"amElnagdy/guard-skills","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"amelnagdy/guard-skills","recommendation_reasons":["Matches task terms: failure","Useful GitHub adoption: 717 stars","Install handoff is available","Repository freshness signal is available","Registry match score 5"],"urls":{"web":"https://www.openagentskill.com/skills/amelnagdy-guard-skills","api":"https://www.openagentskill.com/api/agent/skills/amelnagdy-guard-skills","install_api":"https://www.openagentskill.com/api/skills/amelnagdy-guard-skills/install","audit":"https://www.openagentskill.com/skills/amelnagdy-guard-skills/audit","repository":"https://github.com/amElnagdy/guard-skills"}},{"rank":6,"match_type":"related","match_score":5,"raw_match_score":33.7,"semantic_relevance":30,"slug":"krkn-chaos-krkn","name":"Krkn","description":"Chaos and resiliency testing tool for Kubernetes with a focus on improving performance under failure conditions. A CNCF sandbox project.","tagline":"Chaos and resiliency testing tool for Kubernetes with a focus on improving performance under failure conditions. A CNCF sandbox project.","category":"devops","tags":["kubernetes","devops","chaos-engineering","containers","performance","reliability","resiliency","scalability","testing","python"],"author":{"name":"krkn-chaos","verified":false,"url":"https://github.com/krkn-chaos"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"krkn-chaos/krkn","creatorName":"krkn-chaos","creatorUrl":"https://github.com/krkn-chaos","sourceUrl":"https://github.com/krkn-chaos/krkn","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/krkn-chaos-krkn#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":465,"forks":207,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":49.38},"quality":{"score":72,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"465","tone":"neutral"},{"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":78,"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":"465 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":62,"weight":0.08,"status":"info","detail":"465 stars, 207 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 krkn-chaos/krkn"},{"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/krkn-chaos/krkn"},{"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":"465 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"465 stars, 207 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 krkn-chaos/krkn"},{"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/krkn-chaos/krkn"},{"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"],"evidence":{"stars":"465 GitHub stars","repoActivity":"465 stars, 207 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/krkn-chaos/krkn","install":"npx skills add krkn-chaos/krkn","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 krkn-chaos/krkn","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","Kubernetes","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["devops","kubernetes","chaos-engineering","containers","performance","reliability"],"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"]},"safety":{"score":69,"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","69/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Quality score needs review"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Quality score needs review","69/100 agent safety score"]},"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":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add krkn-chaos/krkn","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":465,"starsLabel":"465","forks":207,"license":"Apache-2.0","qualityScore":72,"trustScore":78,"auditScore":81},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":68,"lastPushedAt":"2026-06-16T11:40:17+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Quality score needs review","Documentation summary is thin","Needs review"]},"coverageTags":["Coding","Testing and QA","devops","kubernetes","chaos-engineering","containers","performance","reliability"]},"audit":{"audit_score":81,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Documentation summary is thin"]},"decision":{"readiness_score":71,"readiness_label":"Prototype first","headline":"Fallback candidate for Browser automation","role":"Fallback candidate","primary_fit":"Browser automation","best_for":["Browser automation workflows","general agent builders","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one 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."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"krkn-chaos-krkn","name":"Krkn","description":"Chaos and resiliency testing tool for Kubernetes with a focus on improving performance under failure conditions. A CNCF sandbox project.","category":"devops","url":"https://www.openagentskill.com/skills/krkn-chaos-krkn","repository":"https://github.com/krkn-chaos/krkn","github_repo":"krkn-chaos/krkn"},"suited_tasks":["Browser automation workflows","general agent builders","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","Kubernetes","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add krkn-chaos/krkn","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 krkn-chaos-krkn"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Krkn\" agent skill from https://github.com/krkn-chaos/krkn. 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: Chaos and resiliency testing tool for Kubernetes with a focus on improving performance under failure conditions. A CNCF sandbox project. 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\":\"krkn-chaos-krkn\",\"task\":\"Install Krkn\",\"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 \"Krkn\" as a Claude Code skill from https://github.com/krkn-chaos/krkn. 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: Chaos and resiliency testing tool for Kubernetes with a focus on improving performance under failure conditions. A CNCF sandbox project. 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\":\"krkn-chaos-krkn\",\"task\":\"Install Krkn\",\"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 \"Krkn\" from https://github.com/krkn-chaos/krkn 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: Chaos and resiliency testing tool for Kubernetes with a focus on improving performance under failure conditions. A CNCF sandbox project. 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\":\"krkn-chaos-krkn\",\"task\":\"Install Krkn\",\"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/krkn-chaos-krkn/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/krkn-chaos-krkn"},"trust":{"score":78,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"465 GitHub stars","repoActivity":"465 stars, 207 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/krkn-chaos/krkn","install":"npx skills add krkn-chaos/krkn","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":["devops","kubernetes","chaos-engineering","containers","performance","reliability"],"known_risks":["Quality score needs review","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":81,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":72,"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","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 Krkn in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 78/100 Strong shortlist","Audit: 81/100 Needs review","Safety: 69/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"krkn-chaos-krkn (Krkn)","install_command":"npx skills add krkn-chaos/krkn","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":"krkn-chaos-krkn","task":"Use Krkn in an agent workflow","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/krkn-chaos-krkn","api":"https://www.openagentskill.com/api/agent/skills/krkn-chaos-krkn","audit":"https://www.openagentskill.com/skills/krkn-chaos-krkn/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=krkn-chaos-krkn&task=Use%20Krkn%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Krkn%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Krkn%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/krkn-chaos-krkn/install","manifest":"https://www.openagentskill.com/api/registry/manifest/krkn-chaos-krkn"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"krkn-chaos-krkn","name":"Krkn","description":"Chaos and resiliency testing tool for Kubernetes with a focus on improving performance under failure conditions. A CNCF sandbox project.","category":"devops","url":"https://www.openagentskill.com/skills/krkn-chaos-krkn","repository":"https://github.com/krkn-chaos/krkn","github_repo":"krkn-chaos/krkn"},"suited_tasks":["Browser automation workflows","general agent builders","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","Kubernetes","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add krkn-chaos/krkn","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 krkn-chaos-krkn"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Krkn\" agent skill from https://github.com/krkn-chaos/krkn. 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: Chaos and resiliency testing tool for Kubernetes with a focus on improving performance under failure conditions. A CNCF sandbox project. 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\":\"krkn-chaos-krkn\",\"task\":\"Install Krkn\",\"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 \"Krkn\" as a Claude Code skill from https://github.com/krkn-chaos/krkn. 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: Chaos and resiliency testing tool for Kubernetes with a focus on improving performance under failure conditions. A CNCF sandbox project. 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\":\"krkn-chaos-krkn\",\"task\":\"Install Krkn\",\"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 \"Krkn\" from https://github.com/krkn-chaos/krkn 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: Chaos and resiliency testing tool for Kubernetes with a focus on improving performance under failure conditions. A CNCF sandbox project. 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\":\"krkn-chaos-krkn\",\"task\":\"Install Krkn\",\"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/krkn-chaos-krkn/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/krkn-chaos-krkn"},"trust":{"score":78,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"465 GitHub stars","repoActivity":"465 stars, 207 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/krkn-chaos/krkn","install":"npx skills add krkn-chaos/krkn","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":["devops","kubernetes","chaos-engineering","containers","performance","reliability"],"known_risks":["Quality score needs review","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":81,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":72,"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","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 Krkn in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 78/100 Strong shortlist","Audit: 81/100 Needs review","Safety: 69/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"krkn-chaos-krkn (Krkn)","install_command":"npx skills add krkn-chaos/krkn","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":"krkn-chaos-krkn","task":"Use Krkn in an agent workflow","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/krkn-chaos-krkn","api":"https://www.openagentskill.com/api/agent/skills/krkn-chaos-krkn","audit":"https://www.openagentskill.com/skills/krkn-chaos-krkn/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=krkn-chaos-krkn&task=Use%20Krkn%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Krkn%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Krkn%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/krkn-chaos-krkn/install","manifest":"https://www.openagentskill.com/api/registry/manifest/krkn-chaos-krkn"}},"platforms":["Python","Kubernetes"],"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"},{"slug":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"}],"install":"npx skills add krkn-chaos/krkn","install_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 krkn-chaos-krkn","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 \"Krkn\" agent skill from https://github.com/krkn-chaos/krkn. 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: Chaos and resiliency testing tool for Kubernetes with a focus on improving performance under failure conditions. A CNCF sandbox project. 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\":\"krkn-chaos-krkn\",\"task\":\"Install Krkn\",\"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 \"Krkn\" as a Claude Code skill from https://github.com/krkn-chaos/krkn. 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: Chaos and resiliency testing tool for Kubernetes with a focus on improving performance under failure conditions. A CNCF sandbox project. 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\":\"krkn-chaos-krkn\",\"task\":\"Install Krkn\",\"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 \"Krkn\" from https://github.com/krkn-chaos/krkn 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: Chaos and resiliency testing tool for Kubernetes with a focus on improving performance under failure conditions. A CNCF sandbox project. 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\":\"krkn-chaos-krkn\",\"task\":\"Install Krkn\",\"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"}],"repository":"https://github.com/krkn-chaos/krkn","github_repo":"krkn-chaos/krkn","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"krkn-chaos/krkn","recommendation_reasons":["Matches task terms: failure","Install handoff is available","Repository freshness signal is available","Registry match score 5"],"urls":{"web":"https://www.openagentskill.com/skills/krkn-chaos-krkn","api":"https://www.openagentskill.com/api/agent/skills/krkn-chaos-krkn","install_api":"https://www.openagentskill.com/api/skills/krkn-chaos-krkn/install","audit":"https://www.openagentskill.com/skills/krkn-chaos-krkn/audit","repository":"https://github.com/krkn-chaos/krkn"}},{"rank":7,"match_type":"related","match_score":5,"raw_match_score":33,"semantic_relevance":30,"slug":"rhesis-ai-rhesis","name":"Rhesis","description":"The testing platform for AI teams. Bring engineers, PMs, and domain experts together to generate tests, simulate (adversarial) conversations, and trace every failure to its root cause.","tagline":"The testing platform for AI teams. Bring engineers, PMs, and domain experts together to generate tests, simulate (adversarial) conversations, and trace every failure to its root cause.","category":"testing-qa","tags":["test-generation","qa","developer-tools","coding","generative-ai","llm-evaluation","llm-evaluation-framework","llmops","open-source","quality-assessment"],"author":{"name":"rhesis-ai","verified":false,"url":"https://github.com/rhesis-ai"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"rhesis-ai/rhesis","creatorName":"rhesis-ai","creatorUrl":"https://github.com/rhesis-ai","sourceUrl":"https://github.com/rhesis-ai/rhesis","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/rhesis-ai-rhesis#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":367,"forks":24,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":48.66},"quality":{"score":66,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"367","tone":"neutral"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":75,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"367 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"367 stars, 24 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":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 rhesis-ai/rhesis"},{"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/rhesis-ai/rhesis"},{"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":"367 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"367 stars, 24 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo 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 rhesis-ai/rhesis"},{"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/rhesis-ai/rhesis"},{"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":["License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 367 stars, 24 forks; issue activity unavailable in current metadata","License clarity: Unknown"],"evidence":{"stars":"367 GitHub stars","repoActivity":"367 stars, 24 forks","lastPushed":"2mo since push","license":"Unknown","repository":"https://github.com/rhesis-ai/rhesis","install":"npx skills add rhesis-ai/rhesis","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 rhesis-ai/rhesis","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","2mo since push"]},"agentCompatibility":["Python","Testing","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 367 stars, 24 forks; issue activity unavailable in current metadata","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":["testing-qa","test-generation","qa","developer-tools","coding","generative-ai"],"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","Quality score needs review","Documentation summary is thin","Stars/forks activity: 367 stars, 24 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"safety":{"score":65,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["License is unclear","65/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["License is unclear"],"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":["License is unclear","65/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"testing-qa","title":"Testing and QA"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add rhesis-ai/rhesis","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":367,"starsLabel":"367","forks":24,"license":"Unknown","qualityScore":66,"trustScore":75,"auditScore":77},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":68,"lastPushedAt":"2026-06-16T09:15:26+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 367 stars, 24 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"coverageTags":["Coding","Coding agents","testing-qa","test-generation","qa","developer-tools","generative-ai","llm-evaluation"]},"audit":{"audit_score":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 367 stars, 24 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"decision":{"readiness_score":65,"readiness_label":"Prototype first","headline":"Fallback candidate for Coding agents","role":"Fallback candidate","primary_fit":"Coding agents","best_for":["Coding agents workflows","general agent builders","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"rhesis-ai-rhesis","name":"Rhesis","description":"The testing platform for AI teams. Bring engineers, PMs, and domain experts together to generate tests, simulate (adversarial) conversations, and trace every failure to its root cause.","category":"testing-qa","url":"https://www.openagentskill.com/skills/rhesis-ai-rhesis","repository":"https://github.com/rhesis-ai/rhesis","github_repo":"rhesis-ai/rhesis"},"suited_tasks":["Coding agents workflows","general agent builders","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Run test suites","Capture failures"],"suited_agents":["Python","Testing","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add rhesis-ai/rhesis","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 rhesis-ai-rhesis"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Rhesis\" agent skill from https://github.com/rhesis-ai/rhesis. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: The testing platform for AI teams. Bring engineers, PMs, and domain experts together to generate tests, simulate (adversarial) conversations, and trace every failure to its root cause. 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\":\"rhesis-ai-rhesis\",\"task\":\"Install Rhesis\",\"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 \"Rhesis\" as a Claude Code skill from https://github.com/rhesis-ai/rhesis. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: The testing platform for AI teams. Bring engineers, PMs, and domain experts together to generate tests, simulate (adversarial) conversations, and trace every failure to its root cause. 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\":\"rhesis-ai-rhesis\",\"task\":\"Install Rhesis\",\"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 \"Rhesis\" from https://github.com/rhesis-ai/rhesis into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: The testing platform for AI teams. Bring engineers, PMs, and domain experts together to generate tests, simulate (adversarial) conversations, and trace every failure to its root cause. 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\":\"rhesis-ai-rhesis\",\"task\":\"Install Rhesis\",\"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/rhesis-ai-rhesis/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/rhesis-ai-rhesis"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"367 GitHub stars","repoActivity":"367 stars, 24 forks","lastPushed":"2mo since push","license":"Unknown","repository":"https://github.com/rhesis-ai/rhesis","install":"npx skills add rhesis-ai/rhesis","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":["testing-qa","test-generation","qa","developer-tools","coding","generative-ai"],"known_risks":["License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 367 stars, 24 forks; issue activity unavailable in current metadata","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":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 367 stars, 24 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"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":66,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 367 stars, 24 forks; issue activity unavailable in current metadata","License clarity: Unknown"],"agent_contract":{"task_input":"Use Rhesis in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 77/100 Needs review","Safety: 65/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"rhesis-ai-rhesis (Rhesis)","install_command":"npx skills add rhesis-ai/rhesis","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":"rhesis-ai-rhesis","task":"Use Rhesis in an agent workflow","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/rhesis-ai-rhesis","api":"https://www.openagentskill.com/api/agent/skills/rhesis-ai-rhesis","audit":"https://www.openagentskill.com/skills/rhesis-ai-rhesis/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=rhesis-ai-rhesis&task=Use%20Rhesis%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Rhesis%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Rhesis%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/rhesis-ai-rhesis/install","manifest":"https://www.openagentskill.com/api/registry/manifest/rhesis-ai-rhesis"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"rhesis-ai-rhesis","name":"Rhesis","description":"The testing platform for AI teams. Bring engineers, PMs, and domain experts together to generate tests, simulate (adversarial) conversations, and trace every failure to its root cause.","category":"testing-qa","url":"https://www.openagentskill.com/skills/rhesis-ai-rhesis","repository":"https://github.com/rhesis-ai/rhesis","github_repo":"rhesis-ai/rhesis"},"suited_tasks":["Coding agents workflows","general agent builders","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Run test suites","Capture failures"],"suited_agents":["Python","Testing","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add rhesis-ai/rhesis","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 rhesis-ai-rhesis"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Rhesis\" agent skill from https://github.com/rhesis-ai/rhesis. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: The testing platform for AI teams. Bring engineers, PMs, and domain experts together to generate tests, simulate (adversarial) conversations, and trace every failure to its root cause. 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\":\"rhesis-ai-rhesis\",\"task\":\"Install Rhesis\",\"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 \"Rhesis\" as a Claude Code skill from https://github.com/rhesis-ai/rhesis. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: The testing platform for AI teams. Bring engineers, PMs, and domain experts together to generate tests, simulate (adversarial) conversations, and trace every failure to its root cause. 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\":\"rhesis-ai-rhesis\",\"task\":\"Install Rhesis\",\"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 \"Rhesis\" from https://github.com/rhesis-ai/rhesis into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: The testing platform for AI teams. Bring engineers, PMs, and domain experts together to generate tests, simulate (adversarial) conversations, and trace every failure to its root cause. 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\":\"rhesis-ai-rhesis\",\"task\":\"Install Rhesis\",\"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/rhesis-ai-rhesis/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/rhesis-ai-rhesis"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"367 GitHub stars","repoActivity":"367 stars, 24 forks","lastPushed":"2mo since push","license":"Unknown","repository":"https://github.com/rhesis-ai/rhesis","install":"npx skills add rhesis-ai/rhesis","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":["testing-qa","test-generation","qa","developer-tools","coding","generative-ai"],"known_risks":["License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 367 stars, 24 forks; issue activity unavailable in current metadata","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":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 367 stars, 24 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"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":66,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 367 stars, 24 forks; issue activity unavailable in current metadata","License clarity: Unknown"],"agent_contract":{"task_input":"Use Rhesis in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 77/100 Needs review","Safety: 65/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"rhesis-ai-rhesis (Rhesis)","install_command":"npx skills add rhesis-ai/rhesis","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":"rhesis-ai-rhesis","task":"Use Rhesis in an agent workflow","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/rhesis-ai-rhesis","api":"https://www.openagentskill.com/api/agent/skills/rhesis-ai-rhesis","audit":"https://www.openagentskill.com/skills/rhesis-ai-rhesis/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=rhesis-ai-rhesis&task=Use%20Rhesis%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Rhesis%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Rhesis%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/rhesis-ai-rhesis/install","manifest":"https://www.openagentskill.com/api/registry/manifest/rhesis-ai-rhesis"}},"platforms":["Python","Testing"],"use_cases":[{"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"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"}],"install":"npx skills add rhesis-ai/rhesis","install_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 rhesis-ai-rhesis","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 \"Rhesis\" agent skill from https://github.com/rhesis-ai/rhesis. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: The testing platform for AI teams. Bring engineers, PMs, and domain experts together to generate tests, simulate (adversarial) conversations, and trace every failure to its root cause. 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\":\"rhesis-ai-rhesis\",\"task\":\"Install Rhesis\",\"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 \"Rhesis\" as a Claude Code skill from https://github.com/rhesis-ai/rhesis. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: The testing platform for AI teams. Bring engineers, PMs, and domain experts together to generate tests, simulate (adversarial) conversations, and trace every failure to its root cause. 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\":\"rhesis-ai-rhesis\",\"task\":\"Install Rhesis\",\"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 \"Rhesis\" from https://github.com/rhesis-ai/rhesis into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: The testing platform for AI teams. Bring engineers, PMs, and domain experts together to generate tests, simulate (adversarial) conversations, and trace every failure to its root cause. 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\":\"rhesis-ai-rhesis\",\"task\":\"Install Rhesis\",\"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"}],"repository":"https://github.com/rhesis-ai/rhesis","github_repo":"rhesis-ai/rhesis","version":"1.0.0","license":"Unknown","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"rhesis-ai/rhesis","recommendation_reasons":["Matches task terms: failure","Install handoff is available","Repository freshness signal is available","Registry match score 5"],"urls":{"web":"https://www.openagentskill.com/skills/rhesis-ai-rhesis","api":"https://www.openagentskill.com/api/agent/skills/rhesis-ai-rhesis","install_api":"https://www.openagentskill.com/api/skills/rhesis-ai-rhesis/install","audit":"https://www.openagentskill.com/skills/rhesis-ai-rhesis/audit","repository":"https://github.com/rhesis-ai/rhesis"}},{"rank":8,"match_type":"related","match_score":4,"raw_match_score":31.3,"semantic_relevance":30,"slug":"datadog-chaos-controller","name":"Chaos Controller","description":":monkey: :fire: Datadog Failure Injection System for Kubernetes","tagline":":monkey: :fire: Datadog Failure Injection System for Kubernetes","category":"devops","tags":["kubernetes","devops","chaos","chaos-engineering","chaos-monkey","k8s","sre","c","github"],"author":{"name":"DataDog","verified":false,"url":"https://github.com/DataDog"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"DataDog/chaos-controller","creatorName":"DataDog","creatorUrl":"https://github.com/DataDog","sourceUrl":"https://github.com/DataDog/chaos-controller","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/datadog-chaos-controller#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":206,"forks":39,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":46.91},"quality":{"score":68,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"206","tone":"neutral"},{"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":76,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"206 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"206 stars, 39 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 DataDog/chaos-controller"},{"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/DataDog/chaos-controller"},{"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":"206 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"206 stars, 39 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 DataDog/chaos-controller"},{"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/DataDog/chaos-controller"},{"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: 206 stars, 39 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"206 GitHub stars","repoActivity":"206 stars, 39 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/DataDog/chaos-controller","install":"npx skills add DataDog/chaos-controller","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 DataDog/chaos-controller","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":["C","Kubernetes","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: 206 stars, 39 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["devops","kubernetes","chaos","chaos-engineering","chaos-monkey","k8s"],"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: 206 stars, 39 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":67,"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","67/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Documentation summary is thin","67/100 agent safety score"]},"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":"web-scraping","title":"Web scraping"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","C"],"install":{"ready":true,"command":"npx skills add DataDog/chaos-controller","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":206,"starsLabel":"206","forks":39,"license":"Apache-2.0","qualityScore":68,"trustScore":76,"auditScore":79},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":65,"lastPushedAt":"2026-06-19T14:16:45+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 206 stars, 39 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Needs review"]},"coverageTags":["Coding","GitHub automation","devops","kubernetes","chaos","chaos-engineering","chaos-monkey","k8s"]},"audit":{"audit_score":79,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 206 stars, 39 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"decision":{"readiness_score":67,"readiness_label":"Prototype first","headline":"Fallback candidate for GitHub automation","role":"Fallback candidate","primary_fit":"GitHub automation","best_for":["GitHub automation workflows","general agent builders","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one GitHub automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"datadog-chaos-controller","name":"Chaos Controller","description":":monkey: :fire: Datadog Failure Injection System for Kubernetes","category":"devops","url":"https://www.openagentskill.com/skills/datadog-chaos-controller","repository":"https://github.com/DataDog/chaos-controller","github_repo":"DataDog/chaos-controller"},"suited_tasks":["GitHub automation workflows","general agent builders","builders willing to evaluate younger projects","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["C","Kubernetes","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add DataDog/chaos-controller","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 datadog-chaos-controller"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Chaos Controller\" agent skill from https://github.com/DataDog/chaos-controller. 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: :monkey: :fire: Datadog Failure Injection System for Kubernetes 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\":\"datadog-chaos-controller\",\"task\":\"Install Chaos Controller\",\"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 \"Chaos Controller\" as a Claude Code skill from https://github.com/DataDog/chaos-controller. 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: :monkey: :fire: Datadog Failure Injection System for Kubernetes 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\":\"datadog-chaos-controller\",\"task\":\"Install Chaos Controller\",\"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 \"Chaos Controller\" from https://github.com/DataDog/chaos-controller 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: :monkey: :fire: Datadog Failure Injection System for Kubernetes 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\":\"datadog-chaos-controller\",\"task\":\"Install Chaos Controller\",\"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/datadog-chaos-controller/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/datadog-chaos-controller"},"trust":{"score":76,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"206 GitHub stars","repoActivity":"206 stars, 39 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/DataDog/chaos-controller","install":"npx skills add DataDog/chaos-controller","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":["devops","kubernetes","chaos","chaos-engineering","chaos-monkey","k8s"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 206 stars, 39 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":79,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 206 stars, 39 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":68,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","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","Documentation summary is thin","Quality score needs review","Stars/forks activity: 206 stars, 39 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use Chaos Controller in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 76/100 Strong shortlist","Audit: 79/100 Needs review","Safety: 67/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"datadog-chaos-controller (Chaos Controller)","install_command":"npx skills add DataDog/chaos-controller","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":"datadog-chaos-controller","task":"Use Chaos Controller in an agent workflow","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/datadog-chaos-controller","api":"https://www.openagentskill.com/api/agent/skills/datadog-chaos-controller","audit":"https://www.openagentskill.com/skills/datadog-chaos-controller/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=datadog-chaos-controller&task=Use%20Chaos%20Controller%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Chaos%20Controller%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Chaos%20Controller%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/datadog-chaos-controller/install","manifest":"https://www.openagentskill.com/api/registry/manifest/datadog-chaos-controller"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"datadog-chaos-controller","name":"Chaos Controller","description":":monkey: :fire: Datadog Failure Injection System for Kubernetes","category":"devops","url":"https://www.openagentskill.com/skills/datadog-chaos-controller","repository":"https://github.com/DataDog/chaos-controller","github_repo":"DataDog/chaos-controller"},"suited_tasks":["GitHub automation workflows","general agent builders","builders willing to evaluate younger projects","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["C","Kubernetes","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add DataDog/chaos-controller","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 datadog-chaos-controller"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Chaos Controller\" agent skill from https://github.com/DataDog/chaos-controller. 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: :monkey: :fire: Datadog Failure Injection System for Kubernetes 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\":\"datadog-chaos-controller\",\"task\":\"Install Chaos Controller\",\"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 \"Chaos Controller\" as a Claude Code skill from https://github.com/DataDog/chaos-controller. 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: :monkey: :fire: Datadog Failure Injection System for Kubernetes 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\":\"datadog-chaos-controller\",\"task\":\"Install Chaos Controller\",\"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 \"Chaos Controller\" from https://github.com/DataDog/chaos-controller 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: :monkey: :fire: Datadog Failure Injection System for Kubernetes 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\":\"datadog-chaos-controller\",\"task\":\"Install Chaos Controller\",\"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/datadog-chaos-controller/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/datadog-chaos-controller"},"trust":{"score":76,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"206 GitHub stars","repoActivity":"206 stars, 39 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/DataDog/chaos-controller","install":"npx skills add DataDog/chaos-controller","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":["devops","kubernetes","chaos","chaos-engineering","chaos-monkey","k8s"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 206 stars, 39 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":79,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 206 stars, 39 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":68,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","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","Documentation summary is thin","Quality score needs review","Stars/forks activity: 206 stars, 39 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use Chaos Controller in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 76/100 Strong shortlist","Audit: 79/100 Needs review","Safety: 67/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"datadog-chaos-controller (Chaos Controller)","install_command":"npx skills add DataDog/chaos-controller","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":"datadog-chaos-controller","task":"Use Chaos Controller in an agent workflow","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/datadog-chaos-controller","api":"https://www.openagentskill.com/api/agent/skills/datadog-chaos-controller","audit":"https://www.openagentskill.com/skills/datadog-chaos-controller/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=datadog-chaos-controller&task=Use%20Chaos%20Controller%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Chaos%20Controller%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Chaos%20Controller%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/datadog-chaos-controller/install","manifest":"https://www.openagentskill.com/api/registry/manifest/datadog-chaos-controller"}},"platforms":["C","Kubernetes"],"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":"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"}],"install":"npx skills add DataDog/chaos-controller","install_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 datadog-chaos-controller","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 \"Chaos Controller\" agent skill from https://github.com/DataDog/chaos-controller. 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: :monkey: :fire: Datadog Failure Injection System for Kubernetes 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\":\"datadog-chaos-controller\",\"task\":\"Install Chaos Controller\",\"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 \"Chaos Controller\" as a Claude Code skill from https://github.com/DataDog/chaos-controller. 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: :monkey: :fire: Datadog Failure Injection System for Kubernetes 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\":\"datadog-chaos-controller\",\"task\":\"Install Chaos Controller\",\"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 \"Chaos Controller\" from https://github.com/DataDog/chaos-controller 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: :monkey: :fire: Datadog Failure Injection System for Kubernetes 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\":\"datadog-chaos-controller\",\"task\":\"Install Chaos Controller\",\"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"}],"repository":"https://github.com/DataDog/chaos-controller","github_repo":"DataDog/chaos-controller","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"datadog/chaos-controller","recommendation_reasons":["Matches task terms: failure","Install handoff is available","Repository freshness signal is available","Registry match score 4"],"urls":{"web":"https://www.openagentskill.com/skills/datadog-chaos-controller","api":"https://www.openagentskill.com/api/agent/skills/datadog-chaos-controller","install_api":"https://www.openagentskill.com/api/skills/datadog-chaos-controller/install","audit":"https://www.openagentskill.com/skills/datadog-chaos-controller/audit","repository":"https://github.com/DataDog/chaos-controller"}},{"rank":9,"match_type":"related","match_score":4,"raw_match_score":30,"semantic_relevance":30,"slug":"microsoft-analyze-test-run","name":"analyze-test-run","description":"Analyze a GitHub Actions integration test run and produce a skill invocation report with failure root-cause issues. TRIGGERS: analyze test run, skill invocation rate, test run report, compare test runs, skill invocation summary, test failure analysis, run report, test results, action run report","tagline":"Analyze a GitHub Actions integration test run and produce a skill invocation report with failure root-cause issues. TRIGGERS: analyze test run, skill invocation rate, test run report, compare test runs, skill invocation summary, test failure analysis, run report, test results, ac","category":"coding-agents","tags":["agent-skill"],"author":{"name":"microsoft","verified":false,"url":"https://github.com/microsoft"},"attribution":{"status":"registry_indexed","statusLabel":"Registry indexed","shortLabel":"REGISTRY INDEXED","sourceLabel":"recursive skill source sync","sourceDetail":"microsoft/GitHub-Copilot-for-Azure","creatorName":"microsoft","creatorUrl":"https://github.com/microsoft","sourceUrl":"https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/analyze-test-run","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/microsoft-analyze-test-run#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":244,"forks":190,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":40.27},"quality":{"score":71,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"244","tone":"neutral"},{"label":"Freshness","value":"3d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":78,"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":"244 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":62,"weight":0.08,"status":"info","detail":"244 stars, 190 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"3d 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 microsoft/GitHub-Copilot-for-Azure --skill analyze-test-run"},{"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/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/analyze-test-run"},{"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":"244 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"244 stars, 190 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3d 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 microsoft/GitHub-Copilot-for-Azure --skill analyze-test-run"},{"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/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/analyze-test-run"},{"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","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"244 GitHub stars","repoActivity":"244 stars, 190 forks","lastPushed":"3d since push","license":"MIT","repository":"https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/analyze-test-run","install":"npx skills add microsoft/GitHub-Copilot-for-Azure --skill analyze-test-run","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 microsoft/GitHub-Copilot-for-Azure --skill analyze-test-run","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","3d since push"]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["coding-agents","agent-skill"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":71,"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","71/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Quality score needs review"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","71/100 agent safety score"]},"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":"research-agents","title":"Research agents"},{"slug":"github-automation","title":"GitHub automation"},{"slug":"coding-agents","title":"Coding agents"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add microsoft/GitHub-Copilot-for-Azure --skill analyze-test-run","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":244,"starsLabel":"244","forks":190,"license":"MIT","qualityScore":71,"trustScore":78,"auditScore":83},"maintenance":{"status":"fresh","label":"3d since push","daysSincePush":3,"lastPushedAt":"2026-08-19T18:19:30+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"coverageTags":["Coding","GitHub automation","coding-agents","agent-skill"]},"audit":{"audit_score":83,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"decision":{"readiness_score":70,"readiness_label":"Prototype first","headline":"Fallback candidate for Research agents","role":"Fallback candidate","primary_fit":"Research agents","best_for":["Research agents workflows","Claude Code teams","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Research agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"microsoft-analyze-test-run","name":"analyze-test-run","description":"Analyze a GitHub Actions integration test run and produce a skill invocation report with failure root-cause issues. TRIGGERS: analyze test run, skill invocation rate, test run report, compare test runs, skill invocation summary, test failure analysis, run report, test results, action run report","category":"coding-agents","url":"https://www.openagentskill.com/skills/microsoft-analyze-test-run","repository":"https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/analyze-test-run","github_repo":"microsoft/GitHub-Copilot-for-Azure"},"suited_tasks":["Research agents workflows","Claude Code teams","builders willing to evaluate younger projects","Search sources","Extract claims","Synthesize findings","Inspect repository metadata","Compare code changes"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add microsoft/GitHub-Copilot-for-Azure --skill analyze-test-run","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 microsoft-analyze-test-run"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"analyze-test-run\" agent skill from https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/analyze-test-run. 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: Analyze a GitHub Actions integration test run and produce a skill invocation report with failure root-cause issues. TRIGGERS: analyze test run, skill invocation rate, test run report, compare test runs, skill invocation summary, test failure analysis, run report, test results, action run report 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\":\"microsoft-analyze-test-run\",\"task\":\"Install analyze-test-run\",\"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 \"analyze-test-run\" as a Claude Code skill from https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/analyze-test-run. 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: Analyze a GitHub Actions integration test run and produce a skill invocation report with failure root-cause issues. TRIGGERS: analyze test run, skill invocation rate, test run report, compare test runs, skill invocation summary, test failure analysis, run report, test results, action run report 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\":\"microsoft-analyze-test-run\",\"task\":\"Install analyze-test-run\",\"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 \"analyze-test-run\" from https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/analyze-test-run 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: Analyze a GitHub Actions integration test run and produce a skill invocation report with failure root-cause issues. TRIGGERS: analyze test run, skill invocation rate, test run report, compare test runs, skill invocation summary, test failure analysis, run report, test results, action run report 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\":\"microsoft-analyze-test-run\",\"task\":\"Install analyze-test-run\",\"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/microsoft-analyze-test-run/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/microsoft-analyze-test-run"},"trust":{"score":78,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"244 GitHub stars","repoActivity":"244 stars, 190 forks","lastPushed":"3d since push","license":"MIT","repository":"https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/analyze-test-run","install":"npx skills add microsoft/GitHub-Copilot-for-Azure --skill analyze-test-run","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":["coding-agents","agent-skill"],"known_risks":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":83,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":71,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"3d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use analyze-test-run in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 78/100 Strong shortlist","Audit: 83/100 Safe to try","Safety: 71/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"microsoft-analyze-test-run (analyze-test-run)","install_command":"npx skills add microsoft/GitHub-Copilot-for-Azure --skill analyze-test-run","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":"microsoft-analyze-test-run","task":"Use analyze-test-run in an agent workflow","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/microsoft-analyze-test-run","api":"https://www.openagentskill.com/api/agent/skills/microsoft-analyze-test-run","audit":"https://www.openagentskill.com/skills/microsoft-analyze-test-run/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=microsoft-analyze-test-run&task=Use%20analyze-test-run%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20analyze-test-run%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20analyze-test-run%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/microsoft-analyze-test-run/install","manifest":"https://www.openagentskill.com/api/registry/manifest/microsoft-analyze-test-run"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"microsoft-analyze-test-run","name":"analyze-test-run","description":"Analyze a GitHub Actions integration test run and produce a skill invocation report with failure root-cause issues. TRIGGERS: analyze test run, skill invocation rate, test run report, compare test runs, skill invocation summary, test failure analysis, run report, test results, action run report","category":"coding-agents","url":"https://www.openagentskill.com/skills/microsoft-analyze-test-run","repository":"https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/analyze-test-run","github_repo":"microsoft/GitHub-Copilot-for-Azure"},"suited_tasks":["Research agents workflows","Claude Code teams","builders willing to evaluate younger projects","Search sources","Extract claims","Synthesize findings","Inspect repository metadata","Compare code changes"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add microsoft/GitHub-Copilot-for-Azure --skill analyze-test-run","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 microsoft-analyze-test-run"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"analyze-test-run\" agent skill from https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/analyze-test-run. 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: Analyze a GitHub Actions integration test run and produce a skill invocation report with failure root-cause issues. TRIGGERS: analyze test run, skill invocation rate, test run report, compare test runs, skill invocation summary, test failure analysis, run report, test results, action run report 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\":\"microsoft-analyze-test-run\",\"task\":\"Install analyze-test-run\",\"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 \"analyze-test-run\" as a Claude Code skill from https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/analyze-test-run. 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: Analyze a GitHub Actions integration test run and produce a skill invocation report with failure root-cause issues. TRIGGERS: analyze test run, skill invocation rate, test run report, compare test runs, skill invocation summary, test failure analysis, run report, test results, action run report 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\":\"microsoft-analyze-test-run\",\"task\":\"Install analyze-test-run\",\"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 \"analyze-test-run\" from https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/analyze-test-run 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: Analyze a GitHub Actions integration test run and produce a skill invocation report with failure root-cause issues. TRIGGERS: analyze test run, skill invocation rate, test run report, compare test runs, skill invocation summary, test failure analysis, run report, test results, action run report 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\":\"microsoft-analyze-test-run\",\"task\":\"Install analyze-test-run\",\"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/microsoft-analyze-test-run/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/microsoft-analyze-test-run"},"trust":{"score":78,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"244 GitHub stars","repoActivity":"244 stars, 190 forks","lastPushed":"3d since push","license":"MIT","repository":"https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/analyze-test-run","install":"npx skills add microsoft/GitHub-Copilot-for-Azure --skill analyze-test-run","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":["coding-agents","agent-skill"],"known_risks":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":83,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":71,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"3d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use analyze-test-run in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 78/100 Strong shortlist","Audit: 83/100 Safe to try","Safety: 71/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"microsoft-analyze-test-run (analyze-test-run)","install_command":"npx skills add microsoft/GitHub-Copilot-for-Azure --skill analyze-test-run","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":"microsoft-analyze-test-run","task":"Use analyze-test-run in an agent workflow","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/microsoft-analyze-test-run","api":"https://www.openagentskill.com/api/agent/skills/microsoft-analyze-test-run","audit":"https://www.openagentskill.com/skills/microsoft-analyze-test-run/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=microsoft-analyze-test-run&task=Use%20analyze-test-run%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20analyze-test-run%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20analyze-test-run%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/microsoft-analyze-test-run/install","manifest":"https://www.openagentskill.com/api/registry/manifest/microsoft-analyze-test-run"}},"platforms":["Claude Code"],"use_cases":[{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"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":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"install":"npx skills add microsoft/GitHub-Copilot-for-Azure --skill analyze-test-run","install_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 microsoft-analyze-test-run","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 \"analyze-test-run\" agent skill from https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/analyze-test-run. 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: Analyze a GitHub Actions integration test run and produce a skill invocation report with failure root-cause issues. TRIGGERS: analyze test run, skill invocation rate, test run report, compare test runs, skill invocation summary, test failure analysis, run report, test results, action run report 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\":\"microsoft-analyze-test-run\",\"task\":\"Install analyze-test-run\",\"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 \"analyze-test-run\" as a Claude Code skill from https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/analyze-test-run. 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: Analyze a GitHub Actions integration test run and produce a skill invocation report with failure root-cause issues. TRIGGERS: analyze test run, skill invocation rate, test run report, compare test runs, skill invocation summary, test failure analysis, run report, test results, action run report 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\":\"microsoft-analyze-test-run\",\"task\":\"Install analyze-test-run\",\"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 \"analyze-test-run\" from https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/analyze-test-run 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: Analyze a GitHub Actions integration test run and produce a skill invocation report with failure root-cause issues. TRIGGERS: analyze test run, skill invocation rate, test run report, compare test runs, skill invocation summary, test failure analysis, run report, test results, action run report 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\":\"microsoft-analyze-test-run\",\"task\":\"Install analyze-test-run\",\"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"}],"repository":"https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/analyze-test-run","github_repo":"microsoft/GitHub-Copilot-for-Azure","version":"1.0.0","license":"MIT","updated_at":"2026-08-19T19:36:02.247838+00:00","canonical_key":"microsoft/github-copilot-for-azure#.github/skills/analyze-test-run","recommendation_reasons":["Matches task terms: failure","Install handoff is available","Repository freshness signal is available","Registry match score 4"],"urls":{"web":"https://www.openagentskill.com/skills/microsoft-analyze-test-run","api":"https://www.openagentskill.com/api/agent/skills/microsoft-analyze-test-run","install_api":"https://www.openagentskill.com/api/skills/microsoft-analyze-test-run/install","audit":"https://www.openagentskill.com/skills/microsoft-analyze-test-run/audit","repository":"https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/analyze-test-run"}},{"rank":10,"match_type":"related","match_score":4,"raw_match_score":29.9,"semantic_relevance":30,"slug":"microsoft-file-test-bug","name":"file-test-bug","description":"File a GitHub issue for local integration test failures. TRIGGERS: file test bug, report test failure, create bug for test, integration test failed, test failure issue, junit failure","tagline":"File a GitHub issue for local integration test failures. TRIGGERS: file test bug, report test failure, create bug for test, integration test failed, test failure issue, junit failure","category":"coding-agents","tags":["agent-skill"],"author":{"name":"microsoft","verified":false,"url":"https://github.com/microsoft"},"attribution":{"status":"registry_indexed","statusLabel":"Registry indexed","shortLabel":"REGISTRY INDEXED","sourceLabel":"recursive skill source sync","sourceDetail":"microsoft/GitHub-Copilot-for-Azure","creatorName":"microsoft","creatorUrl":"https://github.com/microsoft","sourceUrl":"https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/file-test-bug","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/microsoft-file-test-bug#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":244,"forks":190,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":39.97},"quality":{"score":65,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"244","tone":"neutral"},{"label":"Freshness","value":"3d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":["The skill instructs to include complete agent-metadata.md contents verbatim in the issue body. If these logs contain secrets or sensitive information, they could be exposed publicly. Recommend adding a note to sanitize sensitive data before posting."]},"trust":{"version":"trust-score-v4","score":73,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"244 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":62,"weight":0.08,"status":"info","detail":"244 stars, 190 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"3d 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 microsoft/GitHub-Copilot-for-Azure --skill file-test-bug"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/file-test-bug"},{"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":"info","label":"GitHub adoption","detail":"244 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"244 stars, 190 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3d 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 microsoft/GitHub-Copilot-for-Azure --skill file-test-bug"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/file-test-bug"},{"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","Install command has no obvious high-risk pattern"],"warnings":["The skill instructs to include complete agent-metadata.md contents verbatim in the issue body. If these logs contain secrets or sensitive information, they could be exposed publicly. Recommend adding a note to sanitize sensitive data before posting.","Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"244 GitHub stars","repoActivity":"244 stars, 190 forks","lastPushed":"3d since push","license":"MIT","repository":"https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/file-test-bug","install":"npx skills add microsoft/GitHub-Copilot-for-Azure --skill file-test-bug","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add microsoft/GitHub-Copilot-for-Azure --skill file-test-bug","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","3d since push"]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["The skill instructs to include complete agent-metadata.md contents verbatim in the issue body. If these logs contain secrets or sensitive information, they could be exposed publicly. Recommend adding a note to sanitize sensitive data before posting.","Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["coding-agents","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 skill instructs to include complete agent-metadata.md contents verbatim in the issue body. If these logs contain secrets or sensitive information, they could be exposed publicly. Recommend adding a note to sanitize sensitive data before posting.","Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":62,"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 skill instructs to include complete agent-metadata.md contents verbatim in the issue body. If these logs contain secrets or sensitive information, they could be exposed publicly. Recommend adding a note to sanitize sensitive data before posting.","62/100 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":["The skill instructs to include complete agent-metadata.md contents verbatim in the issue body. If these logs contain secrets or sensitive information, they could be exposed publicly. Recommend adding a note to sanitize sensitive data before posting."],"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 skill instructs to include complete agent-metadata.md contents verbatim in the issue body. If these logs contain secrets or sensitive information, they could be exposed publicly. Recommend adding a note to sanitize sensitive data before posting.","62/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"GitHub automation","description":"I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.","useCases":[{"slug":"github-automation","title":"GitHub automation"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"workflow-automation","title":"Workflow automation"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add microsoft/GitHub-Copilot-for-Azure --skill file-test-bug","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":244,"starsLabel":"244","forks":190,"license":"MIT","qualityScore":65,"trustScore":73,"auditScore":78},"maintenance":{"status":"fresh","label":"3d since push","daysSincePush":3,"lastPushedAt":"2026-08-19T18:19:30+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["The skill instructs to include complete agent-metadata.md contents verbatim in the issue body. If these logs contain secrets or sensitive information, they could be exposed publicly. Recommend adding a note to sanitize sensitive data before posting.","Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Needs review"]},"coverageTags":["Coding","GitHub automation","coding-agents","agent-skill"]},"audit":{"audit_score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["The skill instructs to include complete agent-metadata.md contents verbatim in the issue body. If these logs contain secrets or sensitive information, they could be exposed publicly. Recommend adding a note to sanitize sensitive data before posting.","Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"decision":{"readiness_score":64,"readiness_label":"Prototype first","headline":"Fallback candidate for GitHub automation","role":"Fallback candidate","primary_fit":"GitHub automation","best_for":["GitHub automation workflows","Claude Code teams","builders willing to evaluate younger projects"],"risks":["The skill instructs to include complete agent-metadata.md contents verbatim in the issue body. If these logs contain secrets or sensitive information, they could be exposed publicly. Recommend adding a note to sanitize sensitive data before posting.","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."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"microsoft-file-test-bug","name":"file-test-bug","description":"File a GitHub issue for local integration test failures. TRIGGERS: file test bug, report test failure, create bug for test, integration test failed, test failure issue, junit failure","category":"coding-agents","url":"https://www.openagentskill.com/skills/microsoft-file-test-bug","repository":"https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/file-test-bug","github_repo":"microsoft/GitHub-Copilot-for-Azure"},"suited_tasks":["GitHub automation workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add microsoft/GitHub-Copilot-for-Azure --skill file-test-bug","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 microsoft-file-test-bug"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"file-test-bug\" agent skill from https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/file-test-bug. 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: File a GitHub issue for local integration test failures. TRIGGERS: file test bug, report test failure, create bug for test, integration test failed, test failure issue, junit failure 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\":\"microsoft-file-test-bug\",\"task\":\"Install file-test-bug\",\"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 \"file-test-bug\" as a Claude Code skill from https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/file-test-bug. 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: File a GitHub issue for local integration test failures. TRIGGERS: file test bug, report test failure, create bug for test, integration test failed, test failure issue, junit failure 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\":\"microsoft-file-test-bug\",\"task\":\"Install file-test-bug\",\"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 \"file-test-bug\" from https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/file-test-bug 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: File a GitHub issue for local integration test failures. TRIGGERS: file test bug, report test failure, create bug for test, integration test failed, test failure issue, junit failure 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\":\"microsoft-file-test-bug\",\"task\":\"Install file-test-bug\",\"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/microsoft-file-test-bug/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/microsoft-file-test-bug"},"trust":{"score":73,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"244 GitHub stars","repoActivity":"244 stars, 190 forks","lastPushed":"3d since push","license":"MIT","repository":"https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/file-test-bug","install":"npx skills add microsoft/GitHub-Copilot-for-Azure --skill file-test-bug","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["coding-agents","agent-skill"],"known_risks":["The skill instructs to include complete agent-metadata.md contents verbatim in the issue body. If these logs contain secrets or sensitive information, they could be exposed publicly. Recommend adding a note to sanitize sensitive data before posting.","Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["The skill instructs to include complete agent-metadata.md contents verbatim in the issue body. If these logs contain secrets or sensitive information, they could be exposed publicly. Recommend adding a note to sanitize sensitive data before posting.","Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":65,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"3d since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","production agents without a repository review","The skill instructs to include complete agent-metadata.md contents verbatim in the issue body. If these logs contain secrets or sensitive information, they could be exposed publicly. Recommend adding a note to sanitize sensitive data before posting.","No OpenAgentSkill engagement data yet","Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use file-test-bug in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 73/100 Strong shortlist","Audit: 78/100 Needs review","Safety: 62/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"microsoft-file-test-bug (file-test-bug)","install_command":"npx skills add microsoft/GitHub-Copilot-for-Azure --skill file-test-bug","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":"microsoft-file-test-bug","task":"Use file-test-bug in an agent workflow","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/microsoft-file-test-bug","api":"https://www.openagentskill.com/api/agent/skills/microsoft-file-test-bug","audit":"https://www.openagentskill.com/skills/microsoft-file-test-bug/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=microsoft-file-test-bug&task=Use%20file-test-bug%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20file-test-bug%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20file-test-bug%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/microsoft-file-test-bug/install","manifest":"https://www.openagentskill.com/api/registry/manifest/microsoft-file-test-bug"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"microsoft-file-test-bug","name":"file-test-bug","description":"File a GitHub issue for local integration test failures. TRIGGERS: file test bug, report test failure, create bug for test, integration test failed, test failure issue, junit failure","category":"coding-agents","url":"https://www.openagentskill.com/skills/microsoft-file-test-bug","repository":"https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/file-test-bug","github_repo":"microsoft/GitHub-Copilot-for-Azure"},"suited_tasks":["GitHub automation workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add microsoft/GitHub-Copilot-for-Azure --skill file-test-bug","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 microsoft-file-test-bug"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"file-test-bug\" agent skill from https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/file-test-bug. 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: File a GitHub issue for local integration test failures. TRIGGERS: file test bug, report test failure, create bug for test, integration test failed, test failure issue, junit failure 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\":\"microsoft-file-test-bug\",\"task\":\"Install file-test-bug\",\"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 \"file-test-bug\" as a Claude Code skill from https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/file-test-bug. 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: File a GitHub issue for local integration test failures. TRIGGERS: file test bug, report test failure, create bug for test, integration test failed, test failure issue, junit failure 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\":\"microsoft-file-test-bug\",\"task\":\"Install file-test-bug\",\"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 \"file-test-bug\" from https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/file-test-bug 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: File a GitHub issue for local integration test failures. TRIGGERS: file test bug, report test failure, create bug for test, integration test failed, test failure issue, junit failure 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\":\"microsoft-file-test-bug\",\"task\":\"Install file-test-bug\",\"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/microsoft-file-test-bug/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/microsoft-file-test-bug"},"trust":{"score":73,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"244 GitHub stars","repoActivity":"244 stars, 190 forks","lastPushed":"3d since push","license":"MIT","repository":"https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/file-test-bug","install":"npx skills add microsoft/GitHub-Copilot-for-Azure --skill file-test-bug","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["coding-agents","agent-skill"],"known_risks":["The skill instructs to include complete agent-metadata.md contents verbatim in the issue body. If these logs contain secrets or sensitive information, they could be exposed publicly. Recommend adding a note to sanitize sensitive data before posting.","Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["The skill instructs to include complete agent-metadata.md contents verbatim in the issue body. If these logs contain secrets or sensitive information, they could be exposed publicly. Recommend adding a note to sanitize sensitive data before posting.","Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":65,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"3d since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","production agents without a repository review","The skill instructs to include complete agent-metadata.md contents verbatim in the issue body. If these logs contain secrets or sensitive information, they could be exposed publicly. Recommend adding a note to sanitize sensitive data before posting.","No OpenAgentSkill engagement data yet","Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use file-test-bug in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 73/100 Strong shortlist","Audit: 78/100 Needs review","Safety: 62/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"microsoft-file-test-bug (file-test-bug)","install_command":"npx skills add microsoft/GitHub-Copilot-for-Azure --skill file-test-bug","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":"microsoft-file-test-bug","task":"Use file-test-bug in an agent workflow","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/microsoft-file-test-bug","api":"https://www.openagentskill.com/api/agent/skills/microsoft-file-test-bug","audit":"https://www.openagentskill.com/skills/microsoft-file-test-bug/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=microsoft-file-test-bug&task=Use%20file-test-bug%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20file-test-bug%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20file-test-bug%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/microsoft-file-test-bug/install","manifest":"https://www.openagentskill.com/api/registry/manifest/microsoft-file-test-bug"}},"platforms":["Claude Code"],"use_cases":[{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"slug":"testing-qa","title":"Testing and QA","url":"https://www.openagentskill.com/use-cases/testing-qa"}],"install":"npx skills add microsoft/GitHub-Copilot-for-Azure --skill file-test-bug","install_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 microsoft-file-test-bug","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 \"file-test-bug\" agent skill from https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/file-test-bug. 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: File a GitHub issue for local integration test failures. TRIGGERS: file test bug, report test failure, create bug for test, integration test failed, test failure issue, junit failure 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\":\"microsoft-file-test-bug\",\"task\":\"Install file-test-bug\",\"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 \"file-test-bug\" as a Claude Code skill from https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/file-test-bug. 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: File a GitHub issue for local integration test failures. TRIGGERS: file test bug, report test failure, create bug for test, integration test failed, test failure issue, junit failure 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\":\"microsoft-file-test-bug\",\"task\":\"Install file-test-bug\",\"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 \"file-test-bug\" from https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/file-test-bug 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: File a GitHub issue for local integration test failures. TRIGGERS: file test bug, report test failure, create bug for test, integration test failed, test failure issue, junit failure 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\":\"microsoft-file-test-bug\",\"task\":\"Install file-test-bug\",\"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"}],"repository":"https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/file-test-bug","github_repo":"microsoft/GitHub-Copilot-for-Azure","version":"1.0.0","license":"MIT","updated_at":"2026-08-19T19:36:11.930036+00:00","canonical_key":"microsoft/github-copilot-for-azure#.github/skills/file-test-bug","recommendation_reasons":["Matches task terms: failure","Install handoff is available","Repository freshness signal is available","Registry match score 4"],"urls":{"web":"https://www.openagentskill.com/skills/microsoft-file-test-bug","api":"https://www.openagentskill.com/api/agent/skills/microsoft-file-test-bug","install_api":"https://www.openagentskill.com/api/skills/microsoft-file-test-bug/install","audit":"https://www.openagentskill.com/skills/microsoft-file-test-bug/audit","repository":"https://github.com/microsoft/GitHub-Copilot-for-Azure/tree/main/.github/skills/file-test-bug"}}],"meta":{"endpoint":"/api/skills/search","canonical_agent_endpoint":"/api/agent/resolve","lookup_intent":false,"exact_match_found":true,"match_counts":{"exact":1,"near":0,"related":9},"no_match_message":null,"safety_policy":"Blocked candidates are excluded by default. Pass include_blocked=true only for manual audit workflows.","agent_friendly":true,"api_version":"1.0","generated_at":"2026-08-23T15:35:20.748Z"}}