{"query":"Reconstruction Alignment","filters":{"category":null,"platform":null,"track":null,"safety":null,"include_blocked":false,"min_stars":0},"total":10,"skills":[{"rank":1,"match_score":99,"raw_match_score":764,"slug":"horizonwind2004-reconstruction-alignment","name":"Reconstruction Alignment","description":"[ICLR 2026] Official repo of paper \"Reconstruction Alignment Improves Unified Multimodal Models\". Unlocking the Massive Zero-shot Potential in Unified Multimodal Models through Self-supervised Learning.","tagline":"[ICLR 2026] Official repo of paper \"Reconstruction Alignment Improves Unified Multimodal Models\". Unlocking the Massive Zero-shot Potential in Unified Multimodal Models through Self-supervised Learning.","category":"media-automation","tags":["image-generation","media","ml-media","aigc","bagel","comfy","comfyui","diffusion","image-editing","image-to-text"],"author":{"name":"HorizonWind2004","verified":false,"url":"https://github.com/HorizonWind2004"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"HorizonWind2004/reconstruction-alignment","creatorName":"HorizonWind2004","creatorUrl":"https://github.com/HorizonWind2004","sourceUrl":"https://github.com/HorizonWind2004/reconstruction-alignment","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/horizonwind2004-reconstruction-alignment#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":406,"forks":17,"downloads":0,"rating":0,"review_count":0,"quality_score":51.97},"quality":{"score":80,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"406","tone":"neutral"},{"label":"Freshness","value":"1mo 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":80,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"406 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"406 stars, 17 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"1mo 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":90,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow 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 HorizonWind2004/reconstruction-alignment"},{"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/HorizonWind2004/reconstruction-alignment"},{"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":"406 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"406 stars, 17 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"1mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow 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 HorizonWind2004/reconstruction-alignment"},{"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/HorizonWind2004/reconstruction-alignment"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Stars/forks activity: 406 stars, 17 forks; issue activity unavailable in current metadata"],"evidence":{"stars":"406 GitHub stars","repoActivity":"406 stars, 17 forks","lastPushed":"1mo since push","license":"Apache-2.0","repository":"https://github.com/HorizonWind2004/reconstruction-alignment","install":"npx skills add HorizonWind2004/reconstruction-alignment","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add HorizonWind2004/reconstruction-alignment","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","1mo since push"]},"agentCompatibility":["Python","Image Generation","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Stars/forks activity: 406 stars, 17 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":["media-automation","image-generation","media","ml-media","aigc","bagel"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Stars/forks activity: 406 stars, 17 forks; issue activity unavailable in current metadata"]},"safety":{"score":68,"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","68/100 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","68/100 agent safety score"]},"supply_profile":{"track":{"slug":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Multimodal media","description":"I need my agent to process images, video, or audio and extract useful information.","useCases":[{"slug":"github-automation","title":"GitHub automation"},{"slug":"multimodal-media","title":"Multimodal media"},{"slug":"coding-agents","title":"Coding agents"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","Python"],"install":{"ready":true,"command":"npx skills add HorizonWind2004/reconstruction-alignment","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":406,"starsLabel":"406","forks":17,"license":"Apache-2.0","qualityScore":80,"trustScore":80,"auditScore":84},"maintenance":{"status":"active","label":"1mo since push","daysSincePush":41,"lastPushedAt":"2026-05-23T07:30:41+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Quality score needs review","Stars/forks activity: 406 stars, 17 forks; issue activity unavailable in current metadata"]},"coverageTags":["Design","Multimodal media","media-automation","image-generation","media","ml-media","aigc","bagel"]},"audit":{"audit_score":84,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review","Stars/forks activity: 406 stars, 17 forks; issue activity unavailable in current metadata"]},"decision":{"readiness_score":79,"readiness_label":"Strong shortlist","headline":"Companion skill for GitHub automation","role":"Companion skill","primary_fit":"GitHub automation","best_for":["GitHub automation 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 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":"horizonwind2004-reconstruction-alignment","name":"Reconstruction Alignment","description":"[ICLR 2026] Official repo of paper \"Reconstruction Alignment Improves Unified Multimodal Models\". Unlocking the Massive Zero-shot Potential in Unified Multimodal Models through Self-supervised Learning.","category":"media-automation","url":"https://www.openagentskill.com/skills/horizonwind2004-reconstruction-alignment","repository":"https://github.com/HorizonWind2004/reconstruction-alignment","github_repo":"HorizonWind2004/reconstruction-alignment"},"suited_tasks":["GitHub automation workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Read media metadata","Convert formats"],"suited_agents":["Python","Image Generation","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add HorizonWind2004/reconstruction-alignment","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add HorizonWind2004/reconstruction-alignment"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Reconstruction Alignment\" agent skill from https://github.com/HorizonWind2004/reconstruction-alignment. 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: [ICLR 2026] Official repo of paper \"Reconstruction Alignment Improves Unified Multimodal Models\". Unlocking the Massive Zero-shot Potential in Unified Multimodal Models through Self-supervised Learning."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Reconstruction Alignment\" as a Claude Code skill from https://github.com/HorizonWind2004/reconstruction-alignment. 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: [ICLR 2026] Official repo of paper \"Reconstruction Alignment Improves Unified Multimodal Models\". Unlocking the Massive Zero-shot Potential in Unified Multimodal Models through Self-supervised Learning."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Reconstruction Alignment\" from https://github.com/HorizonWind2004/reconstruction-alignment 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: [ICLR 2026] Official repo of paper \"Reconstruction Alignment Improves Unified Multimodal Models\". Unlocking the Massive Zero-shot Potential in Unified Multimodal Models through Self-supervised Learning."}],"handoff_url":"https://www.openagentskill.com/api/skills/horizonwind2004-reconstruction-alignment/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/horizonwind2004-reconstruction-alignment"},"trust":{"score":80,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"406 GitHub stars","repoActivity":"406 stars, 17 forks","lastPushed":"1mo since push","license":"Apache-2.0","repository":"https://github.com/HorizonWind2004/reconstruction-alignment","install":"npx skills add HorizonWind2004/reconstruction-alignment","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","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":["media-automation","image-generation","media","ml-media","aigc","bagel"],"known_risks":["Quality score needs review","Stars/forks activity: 406 stars, 17 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":84,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review","Stars/forks activity: 406 stars, 17 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":80,"label":"Strong"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"1mo 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","Stars/forks activity: 406 stars, 17 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 Reconstruction Alignment 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: 80/100 Strong shortlist","Audit: 84/100 Safe to try","Safety: 68/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"horizonwind2004-reconstruction-alignment (Reconstruction Alignment)","install_command":"npx skills add HorizonWind2004/reconstruction-alignment","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":"horizonwind2004-reconstruction-alignment","task":"Use Reconstruction Alignment 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/horizonwind2004-reconstruction-alignment","api":"https://www.openagentskill.com/api/agent/skills/horizonwind2004-reconstruction-alignment","audit":"https://www.openagentskill.com/skills/horizonwind2004-reconstruction-alignment/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=horizonwind2004-reconstruction-alignment&task=Use%20Reconstruction%20Alignment%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Reconstruction%20Alignment%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Reconstruction%20Alignment%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/horizonwind2004-reconstruction-alignment/install","manifest":"https://www.openagentskill.com/api/registry/manifest/horizonwind2004-reconstruction-alignment"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"horizonwind2004-reconstruction-alignment","name":"Reconstruction Alignment","description":"[ICLR 2026] Official repo of paper \"Reconstruction Alignment Improves Unified Multimodal Models\". Unlocking the Massive Zero-shot Potential in Unified Multimodal Models through Self-supervised Learning.","category":"media-automation","url":"https://www.openagentskill.com/skills/horizonwind2004-reconstruction-alignment","repository":"https://github.com/HorizonWind2004/reconstruction-alignment","github_repo":"HorizonWind2004/reconstruction-alignment"},"suited_tasks":["GitHub automation workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Read media metadata","Convert formats"],"suited_agents":["Python","Image Generation","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add HorizonWind2004/reconstruction-alignment","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add HorizonWind2004/reconstruction-alignment"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Reconstruction Alignment\" agent skill from https://github.com/HorizonWind2004/reconstruction-alignment. 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: [ICLR 2026] Official repo of paper \"Reconstruction Alignment Improves Unified Multimodal Models\". Unlocking the Massive Zero-shot Potential in Unified Multimodal Models through Self-supervised Learning."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Reconstruction Alignment\" as a Claude Code skill from https://github.com/HorizonWind2004/reconstruction-alignment. 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: [ICLR 2026] Official repo of paper \"Reconstruction Alignment Improves Unified Multimodal Models\". Unlocking the Massive Zero-shot Potential in Unified Multimodal Models through Self-supervised Learning."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Reconstruction Alignment\" from https://github.com/HorizonWind2004/reconstruction-alignment 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: [ICLR 2026] Official repo of paper \"Reconstruction Alignment Improves Unified Multimodal Models\". Unlocking the Massive Zero-shot Potential in Unified Multimodal Models through Self-supervised Learning."}],"handoff_url":"https://www.openagentskill.com/api/skills/horizonwind2004-reconstruction-alignment/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/horizonwind2004-reconstruction-alignment"},"trust":{"score":80,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"406 GitHub stars","repoActivity":"406 stars, 17 forks","lastPushed":"1mo since push","license":"Apache-2.0","repository":"https://github.com/HorizonWind2004/reconstruction-alignment","install":"npx skills add HorizonWind2004/reconstruction-alignment","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","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":["media-automation","image-generation","media","ml-media","aigc","bagel"],"known_risks":["Quality score needs review","Stars/forks activity: 406 stars, 17 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":84,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review","Stars/forks activity: 406 stars, 17 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":80,"label":"Strong"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"1mo 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","Stars/forks activity: 406 stars, 17 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 Reconstruction Alignment 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: 80/100 Strong shortlist","Audit: 84/100 Safe to try","Safety: 68/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"horizonwind2004-reconstruction-alignment (Reconstruction Alignment)","install_command":"npx skills add HorizonWind2004/reconstruction-alignment","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":"horizonwind2004-reconstruction-alignment","task":"Use Reconstruction Alignment 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/horizonwind2004-reconstruction-alignment","api":"https://www.openagentskill.com/api/agent/skills/horizonwind2004-reconstruction-alignment","audit":"https://www.openagentskill.com/skills/horizonwind2004-reconstruction-alignment/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=horizonwind2004-reconstruction-alignment&task=Use%20Reconstruction%20Alignment%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Reconstruction%20Alignment%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Reconstruction%20Alignment%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/horizonwind2004-reconstruction-alignment/install","manifest":"https://www.openagentskill.com/api/registry/manifest/horizonwind2004-reconstruction-alignment"}},"platforms":["Python","Image Generation","Claude Code"],"use_cases":[{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"}],"install":"npx skills add HorizonWind2004/reconstruction-alignment","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add HorizonWind2004/reconstruction-alignment","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Reconstruction Alignment\" agent skill from https://github.com/HorizonWind2004/reconstruction-alignment. 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: [ICLR 2026] Official repo of paper \"Reconstruction Alignment Improves Unified Multimodal Models\". Unlocking the Massive Zero-shot Potential in Unified Multimodal Models through Self-supervised Learning.","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 \"Reconstruction Alignment\" as a Claude Code skill from https://github.com/HorizonWind2004/reconstruction-alignment. 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: [ICLR 2026] Official repo of paper \"Reconstruction Alignment Improves Unified Multimodal Models\". Unlocking the Massive Zero-shot Potential in Unified Multimodal Models through Self-supervised Learning.","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 \"Reconstruction Alignment\" from https://github.com/HorizonWind2004/reconstruction-alignment 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: [ICLR 2026] Official repo of paper \"Reconstruction Alignment Improves Unified Multimodal Models\". Unlocking the Massive Zero-shot Potential in Unified Multimodal Models through Self-supervised Learning.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/HorizonWind2004/reconstruction-alignment","github_repo":"HorizonWind2004/reconstruction-alignment","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-06-21T03:03:23.01599+00:00","canonical_key":"horizonwind2004/reconstruction-alignment","recommendation_reasons":["Matches task terms: reconstruction, alignment","Install handoff is available","Repository freshness signal is available","Registry match score 99"],"urls":{"web":"https://www.openagentskill.com/skills/horizonwind2004-reconstruction-alignment","api":"https://www.openagentskill.com/api/agent/skills/horizonwind2004-reconstruction-alignment","install_api":"https://www.openagentskill.com/api/skills/horizonwind2004-reconstruction-alignment/install","audit":"https://www.openagentskill.com/skills/horizonwind2004-reconstruction-alignment/audit","repository":"https://github.com/HorizonWind2004/reconstruction-alignment"}},{"rank":2,"match_score":10,"raw_match_score":79,"slug":"pandas-dev-pandas","name":"Pandas","description":"Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more","tagline":"Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more","category":"data-analysis","tags":["data-analysis","analytics","data","alignment","data-science","flexible","pandas","python","github"],"author":{"name":"pandas-dev","verified":true,"url":"https://github.com/pandas-dev"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"pandas-dev/pandas","creatorName":"pandas-dev","creatorUrl":"https://github.com/pandas-dev","sourceUrl":"https://github.com/pandas-dev/pandas","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/pandas-dev-pandas#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":48977,"forks":20011,"downloads":0,"rating":0,"review_count":0,"quality_score":76.03},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"49K","tone":"positive"},{"label":"Freshness","value":"19d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"BSD-3-Clause","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":94,"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":"49K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"49K stars, 20K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"19d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"BSD-3-Clause"},{"id":"documentation","label":"README/SKILL.md completeness","score":90,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow 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 pandas-dev/pandas"},{"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/pandas-dev/pandas"},{"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":"49K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"49K stars, 20K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"19d since push"},{"status":"pass","label":"License clarity","detail":"BSD-3-Clause"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow 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 pandas-dev/pandas"},{"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/pandas-dev/pandas"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":[],"evidence":{"stars":"49K GitHub stars","repoActivity":"49K stars, 20K forks","lastPushed":"19d since push","license":"BSD-3-Clause","repository":"https://github.com/pandas-dev/pandas","install":"npx skills add pandas-dev/pandas","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add pandas-dev/pandas","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","19d since push"]},"agentCompatibility":["Python","Data Analysis","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["No major trust warnings detected from available 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":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["data-analysis","analytics","data","alignment","data-science","flexible"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":[]},"safety":{"score":87,"level":"safe_to_install","label":"Safe to install with normal review","safety_tier":{"tier":"verified","label":"Verified","badge":"VERIFIED","summary":"Strong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","auto_install_policy":"allow","reasons":["Verified listing","Safe-to-try audit","87/100 agent safety score"]},"auto_install_allowed":true,"human_review_required":false,"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":[],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"verified","label":"Verified","badge":"VERIFIED","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","reasons":["Verified listing","Safe-to-try audit","87/100 agent safety score"]},"supply_profile":{"track":{"slug":"data","label":"Data, BI, and analytics","shortLabel":"Data","description":"CSV, SQL, notebooks, dashboards, data pipelines, BI, ETL, and spreadsheet analysis."},"scenario":{"label":"Data analysis","description":"I need my agent to analyze CSV data, produce insights, and explain trends.","useCases":[{"slug":"data-analysis","title":"Data analysis"},{"slug":"github-automation","title":"GitHub automation"},{"slug":"coding-agents","title":"Coding agents"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","Python"],"install":{"ready":true,"command":"npx skills add pandas-dev/pandas","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":48977,"starsLabel":"49K","forks":20011,"license":"BSD-3-Clause","qualityScore":100,"trustScore":94,"auditScore":95},"maintenance":{"status":"fresh","label":"19d since push","daysSincePush":19,"lastPushedAt":"2026-06-14T05:49:01+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":false,"notes":["No major risk signals from available metadata"]},"coverageTags":["Data","Data analysis","data-analysis","analytics","alignment","data-science","flexible","pandas"]},"audit":{"audit_score":95,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Data analysis","role":"Primary pick","primary_fit":"Data analysis","best_for":["Data analysis 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 Data analysis 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":"pandas-dev-pandas","name":"Pandas","description":"Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more","category":"data-analysis","url":"https://www.openagentskill.com/skills/pandas-dev-pandas","repository":"https://github.com/pandas-dev/pandas","github_repo":"pandas-dev/pandas"},"suited_tasks":["Data analysis workflows","Claude Code teams","teams that value GitHub adoption signals","Load tabular data","Calculate trends","Summarize findings clearly","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","Data Analysis","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add pandas-dev/pandas","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add pandas-dev/pandas"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Pandas\" agent skill from https://github.com/pandas-dev/pandas. 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: Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Pandas\" as a Claude Code skill from https://github.com/pandas-dev/pandas. 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: Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Pandas\" from https://github.com/pandas-dev/pandas 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: Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more"}],"handoff_url":"https://www.openagentskill.com/api/skills/pandas-dev-pandas/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/pandas-dev-pandas"},"trust":{"score":94,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"49K GitHub stars","repoActivity":"49K stars, 20K forks","lastPushed":"19d since push","license":"BSD-3-Clause","repository":"https://github.com/pandas-dev/pandas","install":"npx skills add pandas-dev/pandas","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","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":["data-analysis","analytics","data","alignment","data-science","flexible"],"known_risks":[]},"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":95,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety_gate":{"tier":"verified","label":"Verified","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Data, BI, and analytics","scenario":"Data analysis","maintenance":"19d 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","No major trust warnings detected from available 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 Pandas in an agent workflow","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","install_policy":"allow","minimum_review_before_use":["Trust: 94/100 Production candidate","Audit: 95/100 Safe to try","Safety: 87/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"pandas-dev-pandas (Pandas)","install_command":"npx skills add pandas-dev/pandas","risk_summary":"Safe to try; Verified; 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":"pandas-dev-pandas","task":"Use Pandas 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/pandas-dev-pandas","api":"https://www.openagentskill.com/api/agent/skills/pandas-dev-pandas","audit":"https://www.openagentskill.com/skills/pandas-dev-pandas/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=pandas-dev-pandas&task=Use%20Pandas%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Pandas%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Pandas%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/pandas-dev-pandas/install","manifest":"https://www.openagentskill.com/api/registry/manifest/pandas-dev-pandas"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"pandas-dev-pandas","name":"Pandas","description":"Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more","category":"data-analysis","url":"https://www.openagentskill.com/skills/pandas-dev-pandas","repository":"https://github.com/pandas-dev/pandas","github_repo":"pandas-dev/pandas"},"suited_tasks":["Data analysis workflows","Claude Code teams","teams that value GitHub adoption signals","Load tabular data","Calculate trends","Summarize findings clearly","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","Data Analysis","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add pandas-dev/pandas","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add pandas-dev/pandas"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Pandas\" agent skill from https://github.com/pandas-dev/pandas. 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: Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Pandas\" as a Claude Code skill from https://github.com/pandas-dev/pandas. 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: Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Pandas\" from https://github.com/pandas-dev/pandas 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: Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more"}],"handoff_url":"https://www.openagentskill.com/api/skills/pandas-dev-pandas/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/pandas-dev-pandas"},"trust":{"score":94,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"49K GitHub stars","repoActivity":"49K stars, 20K forks","lastPushed":"19d since push","license":"BSD-3-Clause","repository":"https://github.com/pandas-dev/pandas","install":"npx skills add pandas-dev/pandas","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","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":["data-analysis","analytics","data","alignment","data-science","flexible"],"known_risks":[]},"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":95,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety_gate":{"tier":"verified","label":"Verified","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Data, BI, and analytics","scenario":"Data analysis","maintenance":"19d 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","No major trust warnings detected from available 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 Pandas in an agent workflow","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","install_policy":"allow","minimum_review_before_use":["Trust: 94/100 Production candidate","Audit: 95/100 Safe to try","Safety: 87/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"pandas-dev-pandas (Pandas)","install_command":"npx skills add pandas-dev/pandas","risk_summary":"Safe to try; Verified; 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":"pandas-dev-pandas","task":"Use Pandas 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/pandas-dev-pandas","api":"https://www.openagentskill.com/api/agent/skills/pandas-dev-pandas","audit":"https://www.openagentskill.com/skills/pandas-dev-pandas/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=pandas-dev-pandas&task=Use%20Pandas%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Pandas%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Pandas%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/pandas-dev-pandas/install","manifest":"https://www.openagentskill.com/api/registry/manifest/pandas-dev-pandas"}},"platforms":["Python","Data Analysis","Claude Code"],"use_cases":[{"slug":"data-analysis","title":"Data analysis","url":"https://www.openagentskill.com/use-cases/data-analysis"},{"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":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"}],"install":"npx skills add pandas-dev/pandas","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add pandas-dev/pandas","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Pandas\" agent skill from https://github.com/pandas-dev/pandas. 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: Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more","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 \"Pandas\" as a Claude Code skill from https://github.com/pandas-dev/pandas. 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: Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more","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 \"Pandas\" from https://github.com/pandas-dev/pandas 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: Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/pandas-dev/pandas","github_repo":"pandas-dev/pandas","version":"1.0.0","license":"BSD-3-Clause","updated_at":"2026-06-14T13:01:07.901151+00:00","canonical_key":"pandas-dev/pandas","recommendation_reasons":["Matches task terms: alignment","Strong GitHub adoption: 48,977 stars","Quality score 76/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/pandas-dev-pandas","api":"https://www.openagentskill.com/api/agent/skills/pandas-dev-pandas","install_api":"https://www.openagentskill.com/api/skills/pandas-dev-pandas/install","audit":"https://www.openagentskill.com/skills/pandas-dev-pandas/audit","repository":"https://github.com/pandas-dev/pandas"}},{"rank":3,"match_score":10,"raw_match_score":77.5,"slug":"emcie-co-parlant","name":"Parlant","description":"Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.","tagline":"Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.","category":"agent-frameworks","tags":["agents","ai-agents","ai-alignment","customer-service","customer-success","gemini","genai","hacktoberfest","llama3","llm"],"author":{"name":"emcie-co","verified":true,"url":"https://github.com/emcie-co"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"emcie-co/parlant","creatorName":"emcie-co","creatorUrl":"https://github.com/emcie-co","sourceUrl":"https://github.com/emcie-co/parlant","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/emcie-co-parlant#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":18113,"forks":1536,"downloads":0,"rating":0,"review_count":0,"quality_score":73.01},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"18K","tone":"positive"},{"label":"Freshness","value":"21d 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":94,"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":"18K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"18K stars, 1.5K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"21d 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":90,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow 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 emcie-co/parlant"},{"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/emcie-co/parlant"},{"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":"18K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"18K stars, 1.5K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"21d since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow 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 emcie-co/parlant"},{"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/emcie-co/parlant"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":[],"evidence":{"stars":"18K GitHub stars","repoActivity":"18K stars, 1.5K forks","lastPushed":"21d since push","license":"Apache-2.0","repository":"https://github.com/emcie-co/parlant","install":"npx skills add emcie-co/parlant","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add emcie-co/parlant","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","21d since push"]},"agentCompatibility":["Python","AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["No major trust warnings detected from available 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":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["agent-frameworks","agents","ai-agents","ai-alignment","customer-service","customer-success"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":[]},"safety":{"score":92,"level":"safe_to_install","label":"Safe to install with normal review","safety_tier":{"tier":"verified","label":"Verified","badge":"VERIFIED","summary":"Strong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","auto_install_policy":"allow","reasons":["Verified listing","Safe-to-try audit","92/100 agent safety score"]},"auto_install_allowed":true,"human_review_required":false,"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":[],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"verified","label":"Verified","badge":"VERIFIED","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","reasons":["Verified listing","Safe-to-try audit","92/100 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":"browser-automation","title":"Browser automation"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","Python"],"install":{"ready":true,"command":"npx skills add emcie-co/parlant","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":18113,"starsLabel":"18K","forks":1536,"license":"Apache-2.0","qualityScore":100,"trustScore":94,"auditScore":96},"maintenance":{"status":"fresh","label":"21d since push","daysSincePush":21,"lastPushedAt":"2026-06-12T10:50:18+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":false,"notes":["No major risk signals from available metadata"]},"coverageTags":["Coding","GitHub automation","agent-frameworks","agents","ai-agents","ai-alignment","customer-service","customer-success"]},"audit":{"audit_score":96,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for GitHub automation","role":"Primary pick","primary_fit":"GitHub automation","best_for":["GitHub automation workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one GitHub automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"emcie-co-parlant","name":"Parlant","description":"Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/emcie-co-parlant","repository":"https://github.com/emcie-co/parlant","github_repo":"emcie-co/parlant"},"suited_tasks":["GitHub automation workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Python","AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add emcie-co/parlant","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add emcie-co/parlant"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Parlant\" agent skill from https://github.com/emcie-co/parlant. 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: Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Parlant\" as a Claude Code skill from https://github.com/emcie-co/parlant. 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: Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Parlant\" from https://github.com/emcie-co/parlant 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: Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions."}],"handoff_url":"https://www.openagentskill.com/api/skills/emcie-co-parlant/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/emcie-co-parlant"},"trust":{"score":94,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"18K GitHub stars","repoActivity":"18K stars, 1.5K forks","lastPushed":"21d since push","license":"Apache-2.0","repository":"https://github.com/emcie-co/parlant","install":"npx skills add emcie-co/parlant","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Strong README/SKILL.md context","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":["agent-frameworks","agents","ai-agents","ai-alignment","customer-service","customer-success"],"known_risks":[]},"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":96,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety_gate":{"tier":"verified","label":"Verified","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"21d 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","No major trust warnings detected from available 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 Parlant in an agent workflow","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","install_policy":"allow","minimum_review_before_use":["Trust: 94/100 Production candidate","Audit: 96/100 Safe to try","Safety: 92/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"emcie-co-parlant (Parlant)","install_command":"npx skills add emcie-co/parlant","risk_summary":"Safe to try; Verified; 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":"emcie-co-parlant","task":"Use Parlant 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/emcie-co-parlant","api":"https://www.openagentskill.com/api/agent/skills/emcie-co-parlant","audit":"https://www.openagentskill.com/skills/emcie-co-parlant/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=emcie-co-parlant&task=Use%20Parlant%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Parlant%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Parlant%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/emcie-co-parlant/install","manifest":"https://www.openagentskill.com/api/registry/manifest/emcie-co-parlant"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"emcie-co-parlant","name":"Parlant","description":"Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/emcie-co-parlant","repository":"https://github.com/emcie-co/parlant","github_repo":"emcie-co/parlant"},"suited_tasks":["GitHub automation workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Python","AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add emcie-co/parlant","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add emcie-co/parlant"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Parlant\" agent skill from https://github.com/emcie-co/parlant. 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: Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Parlant\" as a Claude Code skill from https://github.com/emcie-co/parlant. 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: Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Parlant\" from https://github.com/emcie-co/parlant 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: Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions."}],"handoff_url":"https://www.openagentskill.com/api/skills/emcie-co-parlant/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/emcie-co-parlant"},"trust":{"score":94,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"18K GitHub stars","repoActivity":"18K stars, 1.5K forks","lastPushed":"21d since push","license":"Apache-2.0","repository":"https://github.com/emcie-co/parlant","install":"npx skills add emcie-co/parlant","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Strong README/SKILL.md context","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":["agent-frameworks","agents","ai-agents","ai-alignment","customer-service","customer-success"],"known_risks":[]},"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":96,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety_gate":{"tier":"verified","label":"Verified","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"21d 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","No major trust warnings detected from available 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 Parlant in an agent workflow","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","install_policy":"allow","minimum_review_before_use":["Trust: 94/100 Production candidate","Audit: 96/100 Safe to try","Safety: 92/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"emcie-co-parlant (Parlant)","install_command":"npx skills add emcie-co/parlant","risk_summary":"Safe to try; Verified; 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":"emcie-co-parlant","task":"Use Parlant 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/emcie-co-parlant","api":"https://www.openagentskill.com/api/agent/skills/emcie-co-parlant","audit":"https://www.openagentskill.com/skills/emcie-co-parlant/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=emcie-co-parlant&task=Use%20Parlant%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Parlant%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Parlant%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/emcie-co-parlant/install","manifest":"https://www.openagentskill.com/api/registry/manifest/emcie-co-parlant"}},"platforms":["Python","AI Agents","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":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"sports-analytics","title":"Sports analytics","url":"https://www.openagentskill.com/use-cases/sports-analytics"}],"install":"npx skills add emcie-co/parlant","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add emcie-co/parlant","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Parlant\" agent skill from https://github.com/emcie-co/parlant. 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: Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.","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 \"Parlant\" as a Claude Code skill from https://github.com/emcie-co/parlant. 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: Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.","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 \"Parlant\" from https://github.com/emcie-co/parlant 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: Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/emcie-co/parlant","github_repo":"emcie-co/parlant","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-06-13T03:01:54.678991+00:00","canonical_key":"emcie-co/parlant","recommendation_reasons":["Matches task terms: alignment","Strong GitHub adoption: 18,113 stars","Quality score 73/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/emcie-co-parlant","api":"https://www.openagentskill.com/api/agent/skills/emcie-co-parlant","install_api":"https://www.openagentskill.com/api/skills/emcie-co-parlant/install","audit":"https://www.openagentskill.com/skills/emcie-co-parlant/audit","repository":"https://github.com/emcie-co/parlant"}},{"rank":4,"match_score":10,"raw_match_score":76.5,"slug":"alicevision-meshroom","name":"Meshroom","description":"Node-based Visual Programming Toolbox","tagline":"Node-based Visual Programming Toolbox","category":"automation","tags":["workflow","automation","3d-reconstruction","alicevision","camera-tracking","computer-vision","hdr-imaging","image-stitching","meshroom","multi-view-stereo"],"author":{"name":"alicevision","verified":true,"url":"https://github.com/alicevision"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"alicevision/Meshroom","creatorName":"alicevision","creatorUrl":"https://github.com/alicevision","sourceUrl":"https://github.com/alicevision/Meshroom","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/alicevision-meshroom#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":12796,"forks":1212,"downloads":0,"rating":0,"review_count":0,"quality_score":71.95},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"13K","tone":"positive"},{"label":"Freshness","value":"16d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":88,"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":"13K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"13K stars, 1.2K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"16d since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":74,"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 alicevision/Meshroom"},{"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/alicevision/Meshroom"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"13K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"13K stars, 1.2K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"16d 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 alicevision/Meshroom"},{"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/alicevision/Meshroom"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["License is unclear","License clarity: Unknown"],"evidence":{"stars":"13K GitHub stars","repoActivity":"13K stars, 1.2K forks","lastPushed":"16d since push","license":"Unknown","repository":"https://github.com/alicevision/Meshroom","install":"npx skills add alicevision/Meshroom","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add alicevision/Meshroom","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","16d since push"]},"agentCompatibility":["Python","Workflow","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","License clarity: Unknown"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["automation","workflow","3d-reconstruction","alicevision","camera-tracking","computer-vision"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","License clarity: Unknown"]},"safety":{"score":76,"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","76/100 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":["License is unclear"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","76/100 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":"sports-analytics","title":"Sports analytics"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","Python"],"install":{"ready":true,"command":"npx skills add alicevision/Meshroom","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":12796,"starsLabel":"13K","forks":1212,"license":"Unknown","qualityScore":100,"trustScore":88,"auditScore":92},"maintenance":{"status":"fresh","label":"16d since push","daysSincePush":16,"lastPushedAt":"2026-06-17T03:20:41+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["License is unclear","License clarity: Unknown"]},"coverageTags":["Coding","Coding agents","automation","workflow","3d-reconstruction","alicevision","camera-tracking","computer-vision"]},"audit":{"audit_score":92,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","License clarity: Unknown"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Sports analytics","role":"Primary pick","primary_fit":"Sports analytics","best_for":["Sports analytics 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 Sports analytics 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":"alicevision-meshroom","name":"Meshroom","description":"Node-based Visual Programming Toolbox","category":"automation","url":"https://www.openagentskill.com/skills/alicevision-meshroom","repository":"https://github.com/alicevision/Meshroom","github_repo":"alicevision/Meshroom"},"suited_tasks":["Sports analytics workflows","Claude Code teams","teams that value GitHub adoption signals","Load football datasets","Compare teams and players","Explain match and tournament signals","Inspect source files","Explain architecture"],"suited_agents":["Python","Workflow","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add alicevision/Meshroom","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add alicevision/Meshroom"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Meshroom\" agent skill from https://github.com/alicevision/Meshroom. 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: Node-based Visual Programming Toolbox"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Meshroom\" as a Claude Code skill from https://github.com/alicevision/Meshroom. 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: Node-based Visual Programming Toolbox"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Meshroom\" from https://github.com/alicevision/Meshroom 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: Node-based Visual Programming Toolbox"}],"handoff_url":"https://www.openagentskill.com/api/skills/alicevision-meshroom/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/alicevision-meshroom"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"13K GitHub stars","repoActivity":"13K stars, 1.2K forks","lastPushed":"16d since push","license":"Unknown","repository":"https://github.com/alicevision/Meshroom","install":"npx skills add alicevision/Meshroom","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["automation","workflow","3d-reconstruction","alicevision","camera-tracking","computer-vision"],"known_risks":["License is unclear","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":92,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"16d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use Meshroom 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: 88/100 Production candidate","Audit: 92/100 Safe to try","Safety: 76/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"alicevision-meshroom (Meshroom)","install_command":"npx skills add alicevision/Meshroom","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":"alicevision-meshroom","task":"Use Meshroom 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/alicevision-meshroom","api":"https://www.openagentskill.com/api/agent/skills/alicevision-meshroom","audit":"https://www.openagentskill.com/skills/alicevision-meshroom/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=alicevision-meshroom&task=Use%20Meshroom%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Meshroom%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Meshroom%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/alicevision-meshroom/install","manifest":"https://www.openagentskill.com/api/registry/manifest/alicevision-meshroom"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"alicevision-meshroom","name":"Meshroom","description":"Node-based Visual Programming Toolbox","category":"automation","url":"https://www.openagentskill.com/skills/alicevision-meshroom","repository":"https://github.com/alicevision/Meshroom","github_repo":"alicevision/Meshroom"},"suited_tasks":["Sports analytics workflows","Claude Code teams","teams that value GitHub adoption signals","Load football datasets","Compare teams and players","Explain match and tournament signals","Inspect source files","Explain architecture"],"suited_agents":["Python","Workflow","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add alicevision/Meshroom","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add alicevision/Meshroom"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Meshroom\" agent skill from https://github.com/alicevision/Meshroom. 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: Node-based Visual Programming Toolbox"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Meshroom\" as a Claude Code skill from https://github.com/alicevision/Meshroom. 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: Node-based Visual Programming Toolbox"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Meshroom\" from https://github.com/alicevision/Meshroom 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: Node-based Visual Programming Toolbox"}],"handoff_url":"https://www.openagentskill.com/api/skills/alicevision-meshroom/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/alicevision-meshroom"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"13K GitHub stars","repoActivity":"13K stars, 1.2K forks","lastPushed":"16d since push","license":"Unknown","repository":"https://github.com/alicevision/Meshroom","install":"npx skills add alicevision/Meshroom","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["automation","workflow","3d-reconstruction","alicevision","camera-tracking","computer-vision"],"known_risks":["License is unclear","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":92,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"16d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use Meshroom 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: 88/100 Production candidate","Audit: 92/100 Safe to try","Safety: 76/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"alicevision-meshroom (Meshroom)","install_command":"npx skills add alicevision/Meshroom","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":"alicevision-meshroom","task":"Use Meshroom 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/alicevision-meshroom","api":"https://www.openagentskill.com/api/agent/skills/alicevision-meshroom","audit":"https://www.openagentskill.com/skills/alicevision-meshroom/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=alicevision-meshroom&task=Use%20Meshroom%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Meshroom%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Meshroom%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/alicevision-meshroom/install","manifest":"https://www.openagentskill.com/api/registry/manifest/alicevision-meshroom"}},"platforms":["Python","Workflow","Claude Code"],"use_cases":[{"slug":"sports-analytics","title":"Sports analytics","url":"https://www.openagentskill.com/use-cases/sports-analytics"},{"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":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"install":"npx skills add alicevision/Meshroom","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add alicevision/Meshroom","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Meshroom\" agent skill from https://github.com/alicevision/Meshroom. 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: Node-based Visual Programming Toolbox","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 \"Meshroom\" as a Claude Code skill from https://github.com/alicevision/Meshroom. 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: Node-based Visual Programming Toolbox","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 \"Meshroom\" from https://github.com/alicevision/Meshroom 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: Node-based Visual Programming Toolbox","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/alicevision/Meshroom","github_repo":"alicevision/Meshroom","version":"1.0.0","license":"Unknown","updated_at":"2026-06-18T03:00:59.171823+00:00","canonical_key":"alicevision/meshroom","recommendation_reasons":["Matches task terms: reconstruction","Strong GitHub adoption: 12,796 stars","Quality score 72/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/alicevision-meshroom","api":"https://www.openagentskill.com/api/agent/skills/alicevision-meshroom","install_api":"https://www.openagentskill.com/api/skills/alicevision-meshroom/install","audit":"https://www.openagentskill.com/skills/alicevision-meshroom/audit","repository":"https://github.com/alicevision/Meshroom"}},{"rank":5,"match_score":8,"raw_match_score":59.9,"slug":"crawl4ai","name":"Crawl4AI","description":"Open-source LLM-friendly web crawler and scraper","tagline":"Web crawling built for AI","category":"web-automation","tags":["web-crawling","scraping","llm","data-extraction"],"author":{"name":"unclecode","verified":true,"url":null},"attribution":{"status":"registry_indexed","statusLabel":"Registry indexed","shortLabel":"REGISTRY INDEXED","sourceLabel":"API submitted","sourceDetail":"unclecode/crawl4ai","creatorName":"unclecode","creatorUrl":"https://github.com/unclecode/crawl4ai","sourceUrl":"https://github.com/unclecode/crawl4ai","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/crawl4ai#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":70774,"forks":7270,"downloads":31000,"rating":4.9,"review_count":0,"quality_score":79.45},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"71K","tone":"positive"},{"label":"Freshness","value":"2d 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":93,"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":"71K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"71K stars, 7.3K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"2d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":74,"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 unclecode/crawl4ai"},{"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/unclecode/crawl4ai"},{"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":"71K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"71K stars, 7.3K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2d 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 unclecode/crawl4ai"},{"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/unclecode/crawl4ai"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin"],"evidence":{"stars":"71K GitHub stars","repoActivity":"71K stars, 7.3K forks","lastPushed":"2d since push","license":"Apache-2.0","repository":"https://github.com/unclecode/crawl4ai","install":"npx skills add unclecode/crawl4ai","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 unclecode/crawl4ai","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","2d since push"]},"agentCompatibility":["Claude","GPT-4","LangChain","CrewAI","OpenClaw","Codex"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["web-automation","web-crawling","scraping","llm","data-extraction","Claude"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin"]},"safety":{"score":79,"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","79/100 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":["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","79/100 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":"Document processing","description":"I need my agent to read PDFs, extract tables, and turn documents into structured data.","useCases":[{"slug":"web-scraping","title":"Web scraping"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"document-processing","title":"Document processing"}]},"applicableAgents":["Claude Code","OpenAI Agents","LangChain","CLI","Codex"],"install":{"ready":true,"command":"npx skills add unclecode/crawl4ai","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":70774,"starsLabel":"71K","forks":7270,"license":"Apache-2.0","qualityScore":100,"trustScore":93,"auditScore":95},"maintenance":{"status":"fresh","label":"2d since push","daysSincePush":2,"lastPushedAt":"2026-07-01T10:32:12+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Research","Document processing","web-automation","web-crawling","scraping","llm","data-extraction","Claude"]},"audit":{"audit_score":95,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Web scraping","role":"Primary pick","primary_fit":"Web scraping","best_for":["Web scraping 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 Web scraping 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":"crawl4ai","name":"Crawl4AI","description":"Open-source LLM-friendly web crawler and scraper","category":"web-automation","url":"https://www.openagentskill.com/skills/crawl4ai","repository":"https://github.com/unclecode/crawl4ai","github_repo":"unclecode/crawl4ai"},"suited_tasks":["Web scraping workflows","Claude Code teams","teams that value GitHub adoption signals","Crawl target URLs","Extract tables and metadata","Normalize messy page content","Navigate pages","Click and type safely"],"suited_agents":["Claude","GPT-4","LangChain","CrewAI","OpenClaw","Codex","Claude Code","OpenAI Agents"],"install":{"command":"npx skills add unclecode/crawl4ai","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add unclecode/crawl4ai"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Crawl4AI\" agent skill from https://github.com/unclecode/crawl4ai. 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: Open-source LLM-friendly web crawler and scraper"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Crawl4AI\" as a Claude Code skill from https://github.com/unclecode/crawl4ai. 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: Open-source LLM-friendly web crawler and scraper"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Crawl4AI\" from https://github.com/unclecode/crawl4ai 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: Open-source LLM-friendly web crawler and scraper"}],"handoff_url":"https://www.openagentskill.com/api/skills/crawl4ai/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/crawl4ai"},"trust":{"score":93,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"71K GitHub stars","repoActivity":"71K stars, 7.3K forks","lastPushed":"2d since push","license":"Apache-2.0","repository":"https://github.com/unclecode/crawl4ai","install":"npx skills add unclecode/crawl4ai","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":["web-automation","web-crawling","scraping","llm","data-extraction","Claude"],"known_risks":["Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":95,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"Document processing","maintenance":"2d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Crawl4AI 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: 93/100 Production candidate","Audit: 95/100 Safe to try","Safety: 79/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"crawl4ai (Crawl4AI)","install_command":"npx skills add unclecode/crawl4ai","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":"crawl4ai","task":"Use Crawl4AI 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/crawl4ai","api":"https://www.openagentskill.com/api/agent/skills/crawl4ai","audit":"https://www.openagentskill.com/skills/crawl4ai/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=crawl4ai&task=Use%20Crawl4AI%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Crawl4AI%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Crawl4AI%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/crawl4ai/install","manifest":"https://www.openagentskill.com/api/registry/manifest/crawl4ai"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"crawl4ai","name":"Crawl4AI","description":"Open-source LLM-friendly web crawler and scraper","category":"web-automation","url":"https://www.openagentskill.com/skills/crawl4ai","repository":"https://github.com/unclecode/crawl4ai","github_repo":"unclecode/crawl4ai"},"suited_tasks":["Web scraping workflows","Claude Code teams","teams that value GitHub adoption signals","Crawl target URLs","Extract tables and metadata","Normalize messy page content","Navigate pages","Click and type safely"],"suited_agents":["Claude","GPT-4","LangChain","CrewAI","OpenClaw","Codex","Claude Code","OpenAI Agents"],"install":{"command":"npx skills add unclecode/crawl4ai","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add unclecode/crawl4ai"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Crawl4AI\" agent skill from https://github.com/unclecode/crawl4ai. 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: Open-source LLM-friendly web crawler and scraper"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Crawl4AI\" as a Claude Code skill from https://github.com/unclecode/crawl4ai. 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: Open-source LLM-friendly web crawler and scraper"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Crawl4AI\" from https://github.com/unclecode/crawl4ai 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: Open-source LLM-friendly web crawler and scraper"}],"handoff_url":"https://www.openagentskill.com/api/skills/crawl4ai/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/crawl4ai"},"trust":{"score":93,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"71K GitHub stars","repoActivity":"71K stars, 7.3K forks","lastPushed":"2d since push","license":"Apache-2.0","repository":"https://github.com/unclecode/crawl4ai","install":"npx skills add unclecode/crawl4ai","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":["web-automation","web-crawling","scraping","llm","data-extraction","Claude"],"known_risks":["Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":95,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"Document processing","maintenance":"2d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Crawl4AI 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: 93/100 Production candidate","Audit: 95/100 Safe to try","Safety: 79/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"crawl4ai (Crawl4AI)","install_command":"npx skills add unclecode/crawl4ai","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":"crawl4ai","task":"Use Crawl4AI 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/crawl4ai","api":"https://www.openagentskill.com/api/agent/skills/crawl4ai","audit":"https://www.openagentskill.com/skills/crawl4ai/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=crawl4ai&task=Use%20Crawl4AI%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Crawl4AI%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Crawl4AI%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/crawl4ai/install","manifest":"https://www.openagentskill.com/api/registry/manifest/crawl4ai"}},"platforms":["Claude","GPT-4","LangChain","CrewAI","OpenClaw","Claude Code","OpenAI Agents"],"use_cases":[{"slug":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"document-processing","title":"Document processing","url":"https://www.openagentskill.com/use-cases/document-processing"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"}],"install":"npx skills add unclecode/crawl4ai","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add unclecode/crawl4ai","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Crawl4AI\" agent skill from https://github.com/unclecode/crawl4ai. 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: Open-source LLM-friendly web crawler and scraper","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 \"Crawl4AI\" as a Claude Code skill from https://github.com/unclecode/crawl4ai. 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: Open-source LLM-friendly web crawler and scraper","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 \"Crawl4AI\" from https://github.com/unclecode/crawl4ai 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: Open-source LLM-friendly web crawler and scraper","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/unclecode/crawl4ai","github_repo":"unclecode/crawl4ai","version":"0.4.0","license":"Apache-2.0","updated_at":"2026-07-03T03:01:36.181958+00:00","canonical_key":"unclecode/crawl4ai","recommendation_reasons":["Strong GitHub adoption: 70,774 stars","Quality score 79/100","Install handoff is available","Repository freshness signal is available","Registry match score 8"],"urls":{"web":"https://www.openagentskill.com/skills/crawl4ai","api":"https://www.openagentskill.com/api/agent/skills/crawl4ai","install_api":"https://www.openagentskill.com/api/skills/crawl4ai/install","audit":"https://www.openagentskill.com/skills/crawl4ai/audit","repository":"https://github.com/unclecode/crawl4ai"}},{"rank":6,"match_score":8,"raw_match_score":58.9,"slug":"firecrawl","name":"Firecrawl","description":"Turn any website into LLM-ready markdown or structured data","tagline":"Web data for AI applications","category":"web-automation","tags":["web-crawling","markdown","structured-data","api"],"author":{"name":"mendableai","verified":true,"url":null},"attribution":{"status":"registry_indexed","statusLabel":"Registry indexed","shortLabel":"REGISTRY INDEXED","sourceLabel":"API submitted","sourceDetail":"firecrawl/firecrawl","creatorName":"mendableai","creatorUrl":"https://github.com/firecrawl/firecrawl","sourceUrl":"https://github.com/firecrawl/firecrawl","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/firecrawl#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":134190,"forks":7845,"downloads":25000,"rating":4.8,"review_count":0,"quality_score":75.5},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"134K","tone":"positive"},{"label":"Freshness","value":"15d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"AGPL-3.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":88,"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":"134K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"134K stars, 7.8K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"15d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"AGPL-3.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":82,"weight":0.12,"status":"pass","detail":"network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add firecrawl/firecrawl"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/firecrawl/firecrawl"},{"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":"134K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"134K stars, 7.8K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"15d since push"},{"status":"pass","label":"License clarity","detail":"AGPL-3.0"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add firecrawl/firecrawl"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/firecrawl/firecrawl"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"134K GitHub stars","repoActivity":"134K stars, 7.8K forks","lastPushed":"15d since push","license":"AGPL-3.0","repository":"https://github.com/firecrawl/firecrawl","install":"npx skills add firecrawl/firecrawl","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add firecrawl/firecrawl","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","15d since push"]},"agentCompatibility":["Claude","GPT-4","LangChain","OpenClaw","Codex","Claude Code"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["web-automation","web-crawling","markdown","structured-data","api","Claude"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":77,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","77/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","77/100 agent safety score"]},"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"Document processing","description":"I need my agent to read PDFs, extract tables, and turn documents into structured data.","useCases":[{"slug":"web-scraping","title":"Web scraping"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"local-desktop","title":"Local desktop"}]},"applicableAgents":["Claude Code","OpenAI Agents","LangChain","CLI","Codex"],"install":{"ready":true,"command":"npx skills add firecrawl/firecrawl","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":134190,"starsLabel":"134K","forks":7845,"license":"AGPL-3.0","qualityScore":100,"trustScore":88,"auditScore":93},"maintenance":{"status":"fresh","label":"15d since push","daysSincePush":15,"lastPushedAt":"2026-06-17T23:53:37+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"coverageTags":["Research","Document processing","web-automation","web-crawling","markdown","structured-data","api","Claude"]},"audit":{"audit_score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Web scraping","role":"Primary pick","primary_fit":"Web scraping","best_for":["Web scraping 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 Web scraping 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":"firecrawl","name":"Firecrawl","description":"Turn any website into LLM-ready markdown or structured data","category":"web-automation","url":"https://www.openagentskill.com/skills/firecrawl","repository":"https://github.com/firecrawl/firecrawl","github_repo":"firecrawl/firecrawl"},"suited_tasks":["Web scraping workflows","Claude Code teams","teams that value GitHub adoption signals","Crawl target URLs","Extract tables and metadata","Normalize messy page content","Navigate pages","Click and type safely"],"suited_agents":["Claude","GPT-4","LangChain","OpenClaw","Codex","Claude Code","OpenAI Agents","CLI"],"install":{"command":"npx skills add firecrawl/firecrawl","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add firecrawl/firecrawl"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Firecrawl\" agent skill from https://github.com/firecrawl/firecrawl. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Turn any website into LLM-ready markdown or structured data"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Firecrawl\" as a Claude Code skill from https://github.com/firecrawl/firecrawl. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Turn any website into LLM-ready markdown or structured data"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Firecrawl\" from https://github.com/firecrawl/firecrawl into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Turn any website into LLM-ready markdown or structured data"}],"handoff_url":"https://www.openagentskill.com/api/skills/firecrawl/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/firecrawl"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"134K GitHub stars","repoActivity":"134K stars, 7.8K forks","lastPushed":"15d since push","license":"AGPL-3.0","repository":"https://github.com/firecrawl/firecrawl","install":"npx skills add firecrawl/firecrawl","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["web-automation","web-crawling","markdown","structured-data","api","Claude"],"known_risks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"Document processing","maintenance":"15d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Firecrawl 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: 88/100 Production candidate","Audit: 93/100 Safe to try","Safety: 77/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"firecrawl (Firecrawl)","install_command":"npx skills add firecrawl/firecrawl","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":"firecrawl","task":"Use Firecrawl 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/firecrawl","api":"https://www.openagentskill.com/api/agent/skills/firecrawl","audit":"https://www.openagentskill.com/skills/firecrawl/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=firecrawl&task=Use%20Firecrawl%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Firecrawl%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Firecrawl%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/firecrawl/install","manifest":"https://www.openagentskill.com/api/registry/manifest/firecrawl"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"firecrawl","name":"Firecrawl","description":"Turn any website into LLM-ready markdown or structured data","category":"web-automation","url":"https://www.openagentskill.com/skills/firecrawl","repository":"https://github.com/firecrawl/firecrawl","github_repo":"firecrawl/firecrawl"},"suited_tasks":["Web scraping workflows","Claude Code teams","teams that value GitHub adoption signals","Crawl target URLs","Extract tables and metadata","Normalize messy page content","Navigate pages","Click and type safely"],"suited_agents":["Claude","GPT-4","LangChain","OpenClaw","Codex","Claude Code","OpenAI Agents","CLI"],"install":{"command":"npx skills add firecrawl/firecrawl","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add firecrawl/firecrawl"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Firecrawl\" agent skill from https://github.com/firecrawl/firecrawl. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Turn any website into LLM-ready markdown or structured data"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Firecrawl\" as a Claude Code skill from https://github.com/firecrawl/firecrawl. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Turn any website into LLM-ready markdown or structured data"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Firecrawl\" from https://github.com/firecrawl/firecrawl into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Turn any website into LLM-ready markdown or structured data"}],"handoff_url":"https://www.openagentskill.com/api/skills/firecrawl/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/firecrawl"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"134K GitHub stars","repoActivity":"134K stars, 7.8K forks","lastPushed":"15d since push","license":"AGPL-3.0","repository":"https://github.com/firecrawl/firecrawl","install":"npx skills add firecrawl/firecrawl","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["web-automation","web-crawling","markdown","structured-data","api","Claude"],"known_risks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"Document processing","maintenance":"15d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Firecrawl 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: 88/100 Production candidate","Audit: 93/100 Safe to try","Safety: 77/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"firecrawl (Firecrawl)","install_command":"npx skills add firecrawl/firecrawl","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":"firecrawl","task":"Use Firecrawl 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/firecrawl","api":"https://www.openagentskill.com/api/agent/skills/firecrawl","audit":"https://www.openagentskill.com/skills/firecrawl/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=firecrawl&task=Use%20Firecrawl%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Firecrawl%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Firecrawl%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/firecrawl/install","manifest":"https://www.openagentskill.com/api/registry/manifest/firecrawl"}},"platforms":["Claude","GPT-4","LangChain","OpenClaw","Claude Code","OpenAI Agents"],"use_cases":[{"slug":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"install":"npx skills add firecrawl/firecrawl","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add firecrawl/firecrawl","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Firecrawl\" agent skill from https://github.com/firecrawl/firecrawl. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Turn any website into LLM-ready markdown or structured data","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 \"Firecrawl\" as a Claude Code skill from https://github.com/firecrawl/firecrawl. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Turn any website into LLM-ready markdown or structured data","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 \"Firecrawl\" from https://github.com/firecrawl/firecrawl into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Turn any website into LLM-ready markdown or structured data","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/firecrawl/firecrawl","github_repo":"firecrawl/firecrawl","version":"1.5.0","license":"AGPL-3.0","updated_at":"2026-06-18T03:00:52.832358+00:00","canonical_key":"firecrawl/firecrawl","recommendation_reasons":["Strong GitHub adoption: 134,190 stars","Quality score 76/100","Install handoff is available","Repository freshness signal is available","Registry match score 8"],"urls":{"web":"https://www.openagentskill.com/skills/firecrawl","api":"https://www.openagentskill.com/api/agent/skills/firecrawl","install_api":"https://www.openagentskill.com/api/skills/firecrawl/install","audit":"https://www.openagentskill.com/skills/firecrawl/audit","repository":"https://github.com/firecrawl/firecrawl"}},{"rank":7,"match_score":8,"raw_match_score":58.9,"slug":"browser-use","name":"Browser Use","description":"Make AI agents interact with websites using natural language","tagline":"Give your AI agent a web browser","category":"web-automation","tags":["browser","automation","web-scraping","playwright"],"author":{"name":"browser-use","verified":true,"url":null},"attribution":{"status":"registry_indexed","statusLabel":"Registry indexed","shortLabel":"REGISTRY INDEXED","sourceLabel":"API submitted","sourceDetail":"browser-use/browser-use","creatorName":"browser-use","creatorUrl":"https://github.com/browser-use/browser-use","sourceUrl":"https://github.com/browser-use/browser-use","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/browser-use#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":100530,"forks":11186,"downloads":28000,"rating":4.9,"review_count":0,"quality_score":75.5},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"101K","tone":"positive"},{"label":"Freshness","value":"13d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":88,"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":"101K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"101K stars, 11K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"13d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":82,"weight":0.12,"status":"pass","detail":"network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add browser-use/browser-use"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/browser-use/browser-use"},{"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":"101K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"101K stars, 11K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"13d 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":"network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add browser-use/browser-use"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/browser-use/browser-use"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"101K GitHub stars","repoActivity":"101K stars, 11K forks","lastPushed":"13d since push","license":"MIT","repository":"https://github.com/browser-use/browser-use","install":"npx skills add browser-use/browser-use","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add browser-use/browser-use","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","13d since push"]},"agentCompatibility":["Claude","GPT-4","LangChain","OpenClaw","Codex","Claude Code"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["web-automation","browser","automation","web-scraping","playwright","Claude"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":77,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","77/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"browser","label":"Browser automation","reason":"Skill may drive a browser or interact with web pages.","severity":"medium"},{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","77/100 agent safety score"]},"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":"web-scraping","title":"Web scraping"},{"slug":"testing-qa","title":"Testing and QA"}]},"applicableAgents":["Claude Code","OpenAI Agents","LangChain","Browser agents","CLI"],"install":{"ready":true,"command":"npx skills add browser-use/browser-use","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":100530,"starsLabel":"101K","forks":11186,"license":"MIT","qualityScore":100,"trustScore":88,"auditScore":93},"maintenance":{"status":"fresh","label":"13d since push","daysSincePush":13,"lastPushedAt":"2026-06-20T18:21:29+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"coverageTags":["Coding","Testing and QA","web-automation","browser","automation","web-scraping","playwright","Claude"]},"audit":{"audit_score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Browser automation","role":"Primary pick","primary_fit":"Browser automation","best_for":["Browser 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 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":"browser-use","name":"Browser Use","description":"Make AI agents interact with websites using natural language","category":"web-automation","url":"https://www.openagentskill.com/skills/browser-use","repository":"https://github.com/browser-use/browser-use","github_repo":"browser-use/browser-use"},"suited_tasks":["Browser automation workflows","Claude Code teams","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Crawl target URLs","Extract tables and metadata"],"suited_agents":["Claude","GPT-4","LangChain","OpenClaw","Codex","Claude Code","OpenAI Agents","Browser agents"],"install":{"command":"npx skills add browser-use/browser-use","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add browser-use/browser-use"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Browser Use\" agent skill from https://github.com/browser-use/browser-use. 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: Make AI agents interact with websites using natural language"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Browser Use\" as a Claude Code skill from https://github.com/browser-use/browser-use. 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: Make AI agents interact with websites using natural language"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Browser Use\" from https://github.com/browser-use/browser-use 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: Make AI agents interact with websites using natural language"}],"handoff_url":"https://www.openagentskill.com/api/skills/browser-use/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/browser-use"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"101K GitHub stars","repoActivity":"101K stars, 11K forks","lastPushed":"13d since push","license":"MIT","repository":"https://github.com/browser-use/browser-use","install":"npx skills add browser-use/browser-use","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["web-automation","browser","automation","web-scraping","playwright","Claude"],"known_risks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Testing and QA","maintenance":"13d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Browser Use 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: 88/100 Production candidate","Audit: 93/100 Safe to try","Safety: 77/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"browser-use (Browser Use)","install_command":"npx skills add browser-use/browser-use","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":"browser-use","task":"Use Browser Use 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/browser-use","api":"https://www.openagentskill.com/api/agent/skills/browser-use","audit":"https://www.openagentskill.com/skills/browser-use/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=browser-use&task=Use%20Browser%20Use%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Browser%20Use%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Browser%20Use%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/browser-use/install","manifest":"https://www.openagentskill.com/api/registry/manifest/browser-use"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"browser-use","name":"Browser Use","description":"Make AI agents interact with websites using natural language","category":"web-automation","url":"https://www.openagentskill.com/skills/browser-use","repository":"https://github.com/browser-use/browser-use","github_repo":"browser-use/browser-use"},"suited_tasks":["Browser automation workflows","Claude Code teams","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Crawl target URLs","Extract tables and metadata"],"suited_agents":["Claude","GPT-4","LangChain","OpenClaw","Codex","Claude Code","OpenAI Agents","Browser agents"],"install":{"command":"npx skills add browser-use/browser-use","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add browser-use/browser-use"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Browser Use\" agent skill from https://github.com/browser-use/browser-use. 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: Make AI agents interact with websites using natural language"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Browser Use\" as a Claude Code skill from https://github.com/browser-use/browser-use. 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: Make AI agents interact with websites using natural language"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Browser Use\" from https://github.com/browser-use/browser-use 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: Make AI agents interact with websites using natural language"}],"handoff_url":"https://www.openagentskill.com/api/skills/browser-use/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/browser-use"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"101K GitHub stars","repoActivity":"101K stars, 11K forks","lastPushed":"13d since push","license":"MIT","repository":"https://github.com/browser-use/browser-use","install":"npx skills add browser-use/browser-use","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["web-automation","browser","automation","web-scraping","playwright","Claude"],"known_risks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Testing and QA","maintenance":"13d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Browser Use 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: 88/100 Production candidate","Audit: 93/100 Safe to try","Safety: 77/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"browser-use (Browser Use)","install_command":"npx skills add browser-use/browser-use","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":"browser-use","task":"Use Browser Use 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/browser-use","api":"https://www.openagentskill.com/api/agent/skills/browser-use","audit":"https://www.openagentskill.com/skills/browser-use/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=browser-use&task=Use%20Browser%20Use%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Browser%20Use%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Browser%20Use%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/browser-use/install","manifest":"https://www.openagentskill.com/api/registry/manifest/browser-use"}},"platforms":["Claude","GPT-4","LangChain","OpenClaw","Claude Code","OpenAI Agents","Browser agents"],"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"},{"slug":"testing-qa","title":"Testing and QA","url":"https://www.openagentskill.com/use-cases/testing-qa"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"install":"npx skills add browser-use/browser-use","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add browser-use/browser-use","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Browser Use\" agent skill from https://github.com/browser-use/browser-use. 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: Make AI agents interact with websites using natural language","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 \"Browser Use\" as a Claude Code skill from https://github.com/browser-use/browser-use. 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: Make AI agents interact with websites using natural language","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 \"Browser Use\" from https://github.com/browser-use/browser-use 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: Make AI agents interact with websites using natural language","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/browser-use/browser-use","github_repo":"browser-use/browser-use","version":"0.2.0","license":"MIT","updated_at":"2026-06-25T03:04:30.310904+00:00","canonical_key":"browser-use/browser-use","recommendation_reasons":["Strong GitHub adoption: 100,530 stars","Quality score 76/100","Install handoff is available","Repository freshness signal is available","Registry match score 8"],"urls":{"web":"https://www.openagentskill.com/skills/browser-use","api":"https://www.openagentskill.com/api/agent/skills/browser-use","install_api":"https://www.openagentskill.com/api/skills/browser-use/install","audit":"https://www.openagentskill.com/skills/browser-use/audit","repository":"https://github.com/browser-use/browser-use"}},{"rank":8,"match_score":8,"raw_match_score":58.3,"slug":"openclaw-skills","name":"OpenClaw Core Skills","description":"Core skill set for the OpenClaw autonomous agent platform","tagline":"Essential skills for autonomous agents","category":"agent-frameworks","tags":["openclaw","autonomous","agent","multi-step"],"author":{"name":"OpenClaw","verified":true,"url":null},"attribution":{"status":"registry_indexed","statusLabel":"Registry indexed","shortLabel":"REGISTRY INDEXED","sourceLabel":"API submitted","sourceDetail":"anthropics/anthropic-cookbook","creatorName":"OpenClaw","creatorUrl":"https://github.com/anthropics/anthropic-cookbook","sourceUrl":"https://github.com/anthropics/anthropic-cookbook","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/openclaw-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":45771,"forks":5372,"downloads":18000,"rating":4.8,"review_count":0,"quality_score":73.12},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"46K","tone":"positive"},{"label":"Freshness","value":"24d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":87,"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":"46K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"46K stars, 5.4K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"24d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":82,"weight":0.12,"status":"pass","detail":"network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add anthropics/anthropic-cookbook"},{"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":72,"weight":0.07,"status":"info","detail":"filesystem or document access, network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/anthropics/anthropic-cookbook"},{"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":"46K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"46K stars, 5.4K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"24d 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":"network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add anthropics/anthropic-cookbook"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"filesystem or document access, network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/anthropics/anthropic-cookbook"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"46K GitHub stars","repoActivity":"46K stars, 5.4K forks","lastPushed":"24d since push","license":"MIT","repository":"https://github.com/anthropics/anthropic-cookbook","install":"npx skills add anthropics/anthropic-cookbook","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access, network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add anthropics/anthropic-cookbook","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","24d since push"]},"agentCompatibility":["OpenClaw","Claude","LangChain","Codex","Claude Code","Cursor"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["agent-frameworks","openclaw","autonomous","agent","multi-step","Claude"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":77,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","77/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","77/100 agent safety score"]},"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":"workflow-automation","title":"Workflow automation"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["Claude Code","LangChain","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add anthropics/anthropic-cookbook","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":45771,"starsLabel":"46K","forks":5372,"license":"MIT","qualityScore":100,"trustScore":87,"auditScore":93},"maintenance":{"status":"fresh","label":"24d since push","daysSincePush":24,"lastPushedAt":"2026-06-09T20:53:20+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"coverageTags":["Coding","Coding agents","agent-frameworks","openclaw","autonomous","agent","multi-step","Claude"]},"audit":{"audit_score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"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":"openclaw-skills","name":"OpenClaw Core Skills","description":"Core skill set for the OpenClaw autonomous agent platform","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/openclaw-skills","repository":"https://github.com/anthropics/anthropic-cookbook","github_repo":"anthropics/anthropic-cookbook"},"suited_tasks":["Workflow automation workflows","Claude Code teams","teams that value GitHub adoption signals","Move data between tools","Transform files","Trigger repeatable actions","Inspect source files","Explain architecture"],"suited_agents":["OpenClaw","Claude","LangChain","Codex","Claude Code","Cursor","CLI"],"install":{"command":"npx skills add anthropics/anthropic-cookbook","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add anthropics/anthropic-cookbook"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"OpenClaw Core Skills\" agent skill from https://github.com/anthropics/anthropic-cookbook. 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: Core skill set for the OpenClaw autonomous agent platform"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"OpenClaw Core Skills\" as a Claude Code skill from https://github.com/anthropics/anthropic-cookbook. 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: Core skill set for the OpenClaw autonomous agent platform"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"OpenClaw Core Skills\" from https://github.com/anthropics/anthropic-cookbook 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: Core skill set for the OpenClaw autonomous agent platform"}],"handoff_url":"https://www.openagentskill.com/api/skills/openclaw-skills/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/openclaw-skills"},"trust":{"score":87,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"46K GitHub stars","repoActivity":"46K stars, 5.4K forks","lastPushed":"24d since push","license":"MIT","repository":"https://github.com/anthropics/anthropic-cookbook","install":"npx skills add anthropics/anthropic-cookbook","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access, network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["agent-frameworks","openclaw","autonomous","agent","multi-step","Claude"],"known_risks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"24d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use OpenClaw Core 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: 87/100 Production candidate","Audit: 93/100 Safe to try","Safety: 77/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"openclaw-skills (OpenClaw Core Skills)","install_command":"npx skills add anthropics/anthropic-cookbook","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":"openclaw-skills","task":"Use OpenClaw Core 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/openclaw-skills","api":"https://www.openagentskill.com/api/agent/skills/openclaw-skills","audit":"https://www.openagentskill.com/skills/openclaw-skills/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=openclaw-skills&task=Use%20OpenClaw%20Core%20Skills%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20OpenClaw%20Core%20Skills%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20OpenClaw%20Core%20Skills%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/openclaw-skills/install","manifest":"https://www.openagentskill.com/api/registry/manifest/openclaw-skills"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"openclaw-skills","name":"OpenClaw Core Skills","description":"Core skill set for the OpenClaw autonomous agent platform","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/openclaw-skills","repository":"https://github.com/anthropics/anthropic-cookbook","github_repo":"anthropics/anthropic-cookbook"},"suited_tasks":["Workflow automation workflows","Claude Code teams","teams that value GitHub adoption signals","Move data between tools","Transform files","Trigger repeatable actions","Inspect source files","Explain architecture"],"suited_agents":["OpenClaw","Claude","LangChain","Codex","Claude Code","Cursor","CLI"],"install":{"command":"npx skills add anthropics/anthropic-cookbook","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add anthropics/anthropic-cookbook"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"OpenClaw Core Skills\" agent skill from https://github.com/anthropics/anthropic-cookbook. 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: Core skill set for the OpenClaw autonomous agent platform"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"OpenClaw Core Skills\" as a Claude Code skill from https://github.com/anthropics/anthropic-cookbook. 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: Core skill set for the OpenClaw autonomous agent platform"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"OpenClaw Core Skills\" from https://github.com/anthropics/anthropic-cookbook 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: Core skill set for the OpenClaw autonomous agent platform"}],"handoff_url":"https://www.openagentskill.com/api/skills/openclaw-skills/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/openclaw-skills"},"trust":{"score":87,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"46K GitHub stars","repoActivity":"46K stars, 5.4K forks","lastPushed":"24d since push","license":"MIT","repository":"https://github.com/anthropics/anthropic-cookbook","install":"npx skills add anthropics/anthropic-cookbook","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access, network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["agent-frameworks","openclaw","autonomous","agent","multi-step","Claude"],"known_risks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"24d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use OpenClaw Core 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: 87/100 Production candidate","Audit: 93/100 Safe to try","Safety: 77/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"openclaw-skills (OpenClaw Core Skills)","install_command":"npx skills add anthropics/anthropic-cookbook","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":"openclaw-skills","task":"Use OpenClaw Core 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/openclaw-skills","api":"https://www.openagentskill.com/api/agent/skills/openclaw-skills","audit":"https://www.openagentskill.com/skills/openclaw-skills/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=openclaw-skills&task=Use%20OpenClaw%20Core%20Skills%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20OpenClaw%20Core%20Skills%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20OpenClaw%20Core%20Skills%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/openclaw-skills/install","manifest":"https://www.openagentskill.com/api/registry/manifest/openclaw-skills"}},"platforms":["OpenClaw","Claude","LangChain","Claude Code"],"use_cases":[{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-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"},{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"}],"install":"npx skills add anthropics/anthropic-cookbook","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add anthropics/anthropic-cookbook","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"OpenClaw Core Skills\" agent skill from https://github.com/anthropics/anthropic-cookbook. 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: Core skill set for the OpenClaw autonomous agent platform","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 \"OpenClaw Core Skills\" as a Claude Code skill from https://github.com/anthropics/anthropic-cookbook. 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: Core skill set for the OpenClaw autonomous agent platform","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 \"OpenClaw Core Skills\" from https://github.com/anthropics/anthropic-cookbook 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: Core skill set for the OpenClaw autonomous agent platform","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/anthropics/anthropic-cookbook","github_repo":"anthropics/anthropic-cookbook","version":"1.5.0","license":"MIT","updated_at":"2026-06-22T03:00:48.657905+00:00","canonical_key":"anthropics/anthropic-cookbook","recommendation_reasons":["Strong GitHub adoption: 45,771 stars","Quality score 73/100","Install handoff is available","Repository freshness signal is available","Registry match score 8"],"urls":{"web":"https://www.openagentskill.com/skills/openclaw-skills","api":"https://www.openagentskill.com/api/agent/skills/openclaw-skills","install_api":"https://www.openagentskill.com/api/skills/openclaw-skills/install","audit":"https://www.openagentskill.com/skills/openclaw-skills/audit","repository":"https://github.com/anthropics/anthropic-cookbook"}},{"rank":9,"match_score":8,"raw_match_score":57.9,"slug":"composio","name":"Composio","description":"Integration platform for AI agents with 250+ app connectors","tagline":"Connect AI agents to any app","category":"integrations","tags":["integrations","api","connectors","automation"],"author":{"name":"ComposioHQ","verified":true,"url":null},"attribution":{"status":"registry_indexed","statusLabel":"Registry indexed","shortLabel":"REGISTRY INDEXED","sourceLabel":"API submitted","sourceDetail":"ComposioHQ/composio","creatorName":"ComposioHQ","creatorUrl":"https://github.com/ComposioHQ/composio","sourceUrl":"https://github.com/ComposioHQ/composio","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/composio#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":29073,"forks":4641,"downloads":19000,"rating":4.7,"review_count":0,"quality_score":71.74},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"29K","tone":"positive"},{"label":"Freshness","value":"Today","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":88,"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":"29K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"29K stars, 4.6K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"Pushed today"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":82,"weight":0.12,"status":"pass","detail":"network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add ComposioHQ/composio"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/ComposioHQ/composio"},{"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":"29K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"29K stars, 4.6K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"Pushed today"},{"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":"network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add ComposioHQ/composio"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/ComposioHQ/composio"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"29K GitHub stars","repoActivity":"29K stars, 4.6K forks","lastPushed":"Pushed today","license":"MIT","repository":"https://github.com/ComposioHQ/composio","install":"npx skills add ComposioHQ/composio","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add ComposioHQ/composio","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","Pushed today"]},"agentCompatibility":["Claude","GPT-4","LangChain","CrewAI","AutoGPT","OpenClaw"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["integrations","api","connectors","automation","Claude","GPT-4"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":81,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","81/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","81/100 agent safety score"]},"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":"browser-automation","title":"Browser automation"},{"slug":"workflow-automation","title":"Workflow automation"},{"slug":"github-automation","title":"GitHub automation"}]},"applicableAgents":["Claude Code","OpenAI Agents","LangChain","CLI","Codex"],"install":{"ready":true,"command":"npx skills add ComposioHQ/composio","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":29073,"starsLabel":"29K","forks":4641,"license":"MIT","qualityScore":100,"trustScore":88,"auditScore":93},"maintenance":{"status":"fresh","label":"Pushed today","daysSincePush":0,"lastPushedAt":"2026-07-03T02:22:50+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"coverageTags":["Coding","GitHub automation","integrations","api","connectors","automation","Claude","GPT-4"]},"audit":{"audit_score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Browser automation","role":"Primary pick","primary_fit":"Browser automation","best_for":["Browser 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 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":"composio","name":"Composio","description":"Integration platform for AI agents with 250+ app connectors","category":"integrations","url":"https://www.openagentskill.com/skills/composio","repository":"https://github.com/ComposioHQ/composio","github_repo":"ComposioHQ/composio"},"suited_tasks":["Browser automation workflows","Claude Code teams","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Move data between tools","Transform files"],"suited_agents":["Claude","GPT-4","LangChain","CrewAI","AutoGPT","OpenClaw","Claude Code","OpenAI Agents"],"install":{"command":"npx skills add ComposioHQ/composio","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add ComposioHQ/composio"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Composio\" agent skill from https://github.com/ComposioHQ/composio. 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: Integration platform for AI agents with 250+ app connectors"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Composio\" as a Claude Code skill from https://github.com/ComposioHQ/composio. 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: Integration platform for AI agents with 250+ app connectors"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Composio\" from https://github.com/ComposioHQ/composio 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: Integration platform for AI agents with 250+ app connectors"}],"handoff_url":"https://www.openagentskill.com/api/skills/composio/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/composio"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"29K GitHub stars","repoActivity":"29K stars, 4.6K forks","lastPushed":"Pushed today","license":"MIT","repository":"https://github.com/ComposioHQ/composio","install":"npx skills add ComposioHQ/composio","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["integrations","api","connectors","automation","Claude","GPT-4"],"known_risks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"Pushed today","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Composio 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: 88/100 Production candidate","Audit: 93/100 Safe to try","Safety: 81/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"composio (Composio)","install_command":"npx skills add ComposioHQ/composio","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":"composio","task":"Use Composio 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/composio","api":"https://www.openagentskill.com/api/agent/skills/composio","audit":"https://www.openagentskill.com/skills/composio/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=composio&task=Use%20Composio%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Composio%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Composio%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/composio/install","manifest":"https://www.openagentskill.com/api/registry/manifest/composio"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"composio","name":"Composio","description":"Integration platform for AI agents with 250+ app connectors","category":"integrations","url":"https://www.openagentskill.com/skills/composio","repository":"https://github.com/ComposioHQ/composio","github_repo":"ComposioHQ/composio"},"suited_tasks":["Browser automation workflows","Claude Code teams","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Move data between tools","Transform files"],"suited_agents":["Claude","GPT-4","LangChain","CrewAI","AutoGPT","OpenClaw","Claude Code","OpenAI Agents"],"install":{"command":"npx skills add ComposioHQ/composio","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add ComposioHQ/composio"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Composio\" agent skill from https://github.com/ComposioHQ/composio. 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: Integration platform for AI agents with 250+ app connectors"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Composio\" as a Claude Code skill from https://github.com/ComposioHQ/composio. 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: Integration platform for AI agents with 250+ app connectors"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Composio\" from https://github.com/ComposioHQ/composio 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: Integration platform for AI agents with 250+ app connectors"}],"handoff_url":"https://www.openagentskill.com/api/skills/composio/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/composio"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"29K GitHub stars","repoActivity":"29K stars, 4.6K forks","lastPushed":"Pushed today","license":"MIT","repository":"https://github.com/ComposioHQ/composio","install":"npx skills add ComposioHQ/composio","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["integrations","api","connectors","automation","Claude","GPT-4"],"known_risks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"Pushed today","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Composio 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: 88/100 Production candidate","Audit: 93/100 Safe to try","Safety: 81/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"composio (Composio)","install_command":"npx skills add ComposioHQ/composio","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":"composio","task":"Use Composio 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/composio","api":"https://www.openagentskill.com/api/agent/skills/composio","audit":"https://www.openagentskill.com/skills/composio/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=composio&task=Use%20Composio%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Composio%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Composio%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/composio/install","manifest":"https://www.openagentskill.com/api/registry/manifest/composio"}},"platforms":["Claude","GPT-4","LangChain","CrewAI","AutoGPT","OpenClaw","Claude Code","OpenAI Agents"],"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"}],"install":"npx skills add ComposioHQ/composio","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add ComposioHQ/composio","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Composio\" agent skill from https://github.com/ComposioHQ/composio. 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: Integration platform for AI agents with 250+ app connectors","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 \"Composio\" as a Claude Code skill from https://github.com/ComposioHQ/composio. 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: Integration platform for AI agents with 250+ app connectors","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 \"Composio\" from https://github.com/ComposioHQ/composio 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: Integration platform for AI agents with 250+ app connectors","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/ComposioHQ/composio","github_repo":"ComposioHQ/composio","version":"0.7.0","license":"MIT","updated_at":"2026-07-03T03:04:03.926076+00:00","canonical_key":"composiohq/composio","recommendation_reasons":["Strong GitHub adoption: 29,073 stars","Quality score 72/100","Install handoff is available","Repository freshness signal is available","Registry match score 8"],"urls":{"web":"https://www.openagentskill.com/skills/composio","api":"https://www.openagentskill.com/api/agent/skills/composio","install_api":"https://www.openagentskill.com/api/skills/composio/install","audit":"https://www.openagentskill.com/skills/composio/audit","repository":"https://github.com/ComposioHQ/composio"}},{"rank":10,"match_score":7,"raw_match_score":52.6,"slug":"owasp-mastg","name":"Mastg","description":"The OWASP Mobile Application Security Testing Guide (MASTG) is a comprehensive manual for mobile app security testing and reverse engineering. It describes technical processes for verifying the OWASP Mobile Security Weakness Enumeration (MASWE) weaknesses, which are in alignment with the OWASP MASVS.","tagline":"The OWASP Mobile Application Security Testing Guide (MASTG) is a comprehensive manual for mobile app security testing and reverse engineering. It describes technical processes for verifying the OWASP Mobile Security Weakness Enumeration (MASWE) weaknesses, which are in alignment with the OWASP MASVS.","category":"development","tags":["static-analysis","code-quality","android","android-application","compliancy-checklist","dynamic-analysis","hacking","ios","ios-app","mast"],"author":{"name":"OWASP","verified":true,"url":"https://github.com/OWASP"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"OWASP/mastg","creatorName":"OWASP","creatorUrl":"https://github.com/OWASP","sourceUrl":"https://github.com/OWASP/mastg","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/owasp-mastg#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":12982,"forks":2757,"downloads":0,"rating":0,"review_count":0,"quality_score":71.99},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"13K","tone":"positive"},{"label":"Freshness","value":"13d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"CC-BY-SA-4.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":93,"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":"13K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"13K stars, 2.8K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"13d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"CC-BY-SA-4.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":90,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow 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 OWASP/mastg"},{"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/OWASP/mastg"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"13K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"13K stars, 2.8K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"13d since push"},{"status":"pass","label":"License clarity","detail":"CC-BY-SA-4.0"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow 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 OWASP/mastg"},{"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/OWASP/mastg"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":[],"evidence":{"stars":"13K GitHub stars","repoActivity":"13K stars, 2.8K forks","lastPushed":"13d since push","license":"CC-BY-SA-4.0","repository":"https://github.com/OWASP/mastg","install":"npx skills add OWASP/mastg","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add OWASP/mastg","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","13d since push"]},"agentCompatibility":["Python","Static Analysis","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["No major trust warnings detected from available 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":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["development","static-analysis","code-quality","android","android-application","compliancy-checklist"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":[]},"safety":{"score":87,"level":"safe_to_install","label":"Safe to install with normal review","safety_tier":{"tier":"verified","label":"Verified","badge":"VERIFIED","summary":"Strong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","auto_install_policy":"allow","reasons":["Verified listing","Safe-to-try audit","87/100 agent safety score"]},"auto_install_allowed":true,"human_review_required":false,"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":[],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"verified","label":"Verified","badge":"VERIFIED","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","reasons":["Verified listing","Safe-to-try audit","87/100 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":"local-desktop","title":"Local desktop"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","Python"],"install":{"ready":true,"command":"npx skills add OWASP/mastg","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":12982,"starsLabel":"13K","forks":2757,"license":"CC-BY-SA-4.0","qualityScore":100,"trustScore":93,"auditScore":95},"maintenance":{"status":"fresh","label":"13d since push","daysSincePush":13,"lastPushedAt":"2026-06-20T13:58:52+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":false,"notes":["No major risk signals from available metadata"]},"coverageTags":["Coding","Coding agents","development","static-analysis","code-quality","android","android-application","compliancy-checklist"]},"audit":{"audit_score":95,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"decision":{"readiness_score":100,"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":"owasp-mastg","name":"Mastg","description":"The OWASP Mobile Application Security Testing Guide (MASTG) is a comprehensive manual for mobile app security testing and reverse engineering. It describes technical processes for verifying the OWASP Mobile Security Weakness Enumeration (MASWE) weaknesses, which are in alignment with the OWASP MASVS.","category":"development","url":"https://www.openagentskill.com/skills/owasp-mastg","repository":"https://github.com/OWASP/mastg","github_repo":"OWASP/mastg"},"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":["Python","Static Analysis","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add OWASP/mastg","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add OWASP/mastg"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Mastg\" agent skill from https://github.com/OWASP/mastg. 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 OWASP Mobile Application Security Testing Guide (MASTG) is a comprehensive manual for mobile app security testing and reverse engineering. It describes technical processes for verifying the OWASP Mobile Security Weakness Enumeration (MASWE) weaknesses, which are in alignment with the OWASP MASVS."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Mastg\" as a Claude Code skill from https://github.com/OWASP/mastg. 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 OWASP Mobile Application Security Testing Guide (MASTG) is a comprehensive manual for mobile app security testing and reverse engineering. It describes technical processes for verifying the OWASP Mobile Security Weakness Enumeration (MASWE) weaknesses, which are in alignment with the OWASP MASVS."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Mastg\" from https://github.com/OWASP/mastg 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 OWASP Mobile Application Security Testing Guide (MASTG) is a comprehensive manual for mobile app security testing and reverse engineering. It describes technical processes for verifying the OWASP Mobile Security Weakness Enumeration (MASWE) weaknesses, which are in alignment with the OWASP MASVS."}],"handoff_url":"https://www.openagentskill.com/api/skills/owasp-mastg/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/owasp-mastg"},"trust":{"score":93,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"13K GitHub stars","repoActivity":"13K stars, 2.8K forks","lastPushed":"13d since push","license":"CC-BY-SA-4.0","repository":"https://github.com/OWASP/mastg","install":"npx skills add OWASP/mastg","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["development","static-analysis","code-quality","android","android-application","compliancy-checklist"],"known_risks":[]},"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":95,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety_gate":{"tier":"verified","label":"Verified","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"13d 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","No major trust warnings detected from available 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 Mastg in an agent workflow","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","install_policy":"allow","minimum_review_before_use":["Trust: 93/100 Production candidate","Audit: 95/100 Safe to try","Safety: 87/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"owasp-mastg (Mastg)","install_command":"npx skills add OWASP/mastg","risk_summary":"Safe to try; Verified; 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":"owasp-mastg","task":"Use Mastg 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/owasp-mastg","api":"https://www.openagentskill.com/api/agent/skills/owasp-mastg","audit":"https://www.openagentskill.com/skills/owasp-mastg/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=owasp-mastg&task=Use%20Mastg%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Mastg%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Mastg%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/owasp-mastg/install","manifest":"https://www.openagentskill.com/api/registry/manifest/owasp-mastg"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"owasp-mastg","name":"Mastg","description":"The OWASP Mobile Application Security Testing Guide (MASTG) is a comprehensive manual for mobile app security testing and reverse engineering. It describes technical processes for verifying the OWASP Mobile Security Weakness Enumeration (MASWE) weaknesses, which are in alignment with the OWASP MASVS.","category":"development","url":"https://www.openagentskill.com/skills/owasp-mastg","repository":"https://github.com/OWASP/mastg","github_repo":"OWASP/mastg"},"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":["Python","Static Analysis","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add OWASP/mastg","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add OWASP/mastg"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Mastg\" agent skill from https://github.com/OWASP/mastg. 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 OWASP Mobile Application Security Testing Guide (MASTG) is a comprehensive manual for mobile app security testing and reverse engineering. It describes technical processes for verifying the OWASP Mobile Security Weakness Enumeration (MASWE) weaknesses, which are in alignment with the OWASP MASVS."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Mastg\" as a Claude Code skill from https://github.com/OWASP/mastg. 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 OWASP Mobile Application Security Testing Guide (MASTG) is a comprehensive manual for mobile app security testing and reverse engineering. It describes technical processes for verifying the OWASP Mobile Security Weakness Enumeration (MASWE) weaknesses, which are in alignment with the OWASP MASVS."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Mastg\" from https://github.com/OWASP/mastg 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 OWASP Mobile Application Security Testing Guide (MASTG) is a comprehensive manual for mobile app security testing and reverse engineering. It describes technical processes for verifying the OWASP Mobile Security Weakness Enumeration (MASWE) weaknesses, which are in alignment with the OWASP MASVS."}],"handoff_url":"https://www.openagentskill.com/api/skills/owasp-mastg/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/owasp-mastg"},"trust":{"score":93,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"13K GitHub stars","repoActivity":"13K stars, 2.8K forks","lastPushed":"13d since push","license":"CC-BY-SA-4.0","repository":"https://github.com/OWASP/mastg","install":"npx skills add OWASP/mastg","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["development","static-analysis","code-quality","android","android-application","compliancy-checklist"],"known_risks":[]},"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":95,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety_gate":{"tier":"verified","label":"Verified","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"13d 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","No major trust warnings detected from available 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 Mastg in an agent workflow","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","install_policy":"allow","minimum_review_before_use":["Trust: 93/100 Production candidate","Audit: 95/100 Safe to try","Safety: 87/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"owasp-mastg (Mastg)","install_command":"npx skills add OWASP/mastg","risk_summary":"Safe to try; Verified; 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":"owasp-mastg","task":"Use Mastg 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/owasp-mastg","api":"https://www.openagentskill.com/api/agent/skills/owasp-mastg","audit":"https://www.openagentskill.com/skills/owasp-mastg/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=owasp-mastg&task=Use%20Mastg%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Mastg%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Mastg%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/owasp-mastg/install","manifest":"https://www.openagentskill.com/api/registry/manifest/owasp-mastg"}},"platforms":["Python","Static Analysis","Claude Code"],"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":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"}],"install":"npx skills add OWASP/mastg","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add OWASP/mastg","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Mastg\" agent skill from https://github.com/OWASP/mastg. 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 OWASP Mobile Application Security Testing Guide (MASTG) is a comprehensive manual for mobile app security testing and reverse engineering. It describes technical processes for verifying the OWASP Mobile Security Weakness Enumeration (MASWE) weaknesses, which are in alignment with the OWASP MASVS.","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 \"Mastg\" as a Claude Code skill from https://github.com/OWASP/mastg. 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 OWASP Mobile Application Security Testing Guide (MASTG) is a comprehensive manual for mobile app security testing and reverse engineering. It describes technical processes for verifying the OWASP Mobile Security Weakness Enumeration (MASWE) weaknesses, which are in alignment with the OWASP MASVS.","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 \"Mastg\" from https://github.com/OWASP/mastg 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 OWASP Mobile Application Security Testing Guide (MASTG) is a comprehensive manual for mobile app security testing and reverse engineering. It describes technical processes for verifying the OWASP Mobile Security Weakness Enumeration (MASWE) weaknesses, which are in alignment with the OWASP MASVS.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/OWASP/mastg","github_repo":"OWASP/mastg","version":"1.0.0","license":"CC-BY-SA-4.0","updated_at":"2026-06-21T03:02:51.038141+00:00","canonical_key":"owasp/mastg","recommendation_reasons":["Matches task terms: alignment","Strong GitHub adoption: 12,982 stars","Quality score 72/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/owasp-mastg","api":"https://www.openagentskill.com/api/agent/skills/owasp-mastg","install_api":"https://www.openagentskill.com/api/skills/owasp-mastg/install","audit":"https://www.openagentskill.com/skills/owasp-mastg/audit","repository":"https://github.com/OWASP/mastg"}}],"meta":{"endpoint":"/api/skills/search","canonical_agent_endpoint":"/api/agent/resolve","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":"2026-07-03T23:34:20.617Z"}}