{"query":"Refactor Like A Superhero","filters":{"category":null,"platform":null,"track":null,"safety":null,"include_blocked":false,"min_stars":0},"total":10,"skills":[{"rank":1,"match_type":"exact","match_score":99,"raw_match_score":838.1,"semantic_relevance":100,"slug":"bespoyasov-refactor-like-a-superhero","name":"Refactor Like A Superhero","description":"How to refactor code efficiently and without pain.","tagline":"How to refactor code efficiently and without pain.","category":"document-processing","tags":["pdf","documents","extraction","backend","ebook","education","epub","frontend","javascript","learn-to-code"],"author":{"name":"bespoyasov","verified":true,"url":"https://github.com/bespoyasov"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"bespoyasov/refactor-like-a-superhero","creatorName":"bespoyasov","creatorUrl":"https://github.com/bespoyasov","sourceUrl":"https://github.com/bespoyasov/refactor-like-a-superhero","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/bespoyasov-refactor-like-a-superhero#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":1067,"forks":94,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":47.9},"quality":{"score":60,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"1.1K","tone":"positive"},{"label":"Freshness","value":"1y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":75,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"1.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":77,"weight":0.08,"status":"info","detail":"1.1K stars, 94 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":38,"weight":0.14,"status":"fail","detail":"1y since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add bespoyasov/refactor-like-a-superhero"},{"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/bespoyasov/refactor-like-a-superhero"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"1.1K GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"1.1K stars, 94 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"1y since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add bespoyasov/refactor-like-a-superhero"},{"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/bespoyasov/refactor-like-a-superhero"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["License is unclear","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"1.1K GitHub stars","repoActivity":"1.1K stars, 94 forks","lastPushed":"1y since push","license":"Unknown","repository":"https://github.com/bespoyasov/refactor-like-a-superhero","install":"npx skills add bespoyasov/refactor-like-a-superhero","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add bespoyasov/refactor-like-a-superhero","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","1y since push"]},"agentCompatibility":["PDF","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["document-processing","pdf","documents","extraction","backend","ebook"],"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","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":52,"level":"avoid_auto_install","label":"Avoid automatic install","safety_tier":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","summary":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","auto_install_policy":"review","reasons":["License is unclear","52/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["License is unclear"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","reasons":["License is unclear","52/100 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":"document-processing","title":"Document processing"},{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"web-scraping","title":"Web scraping"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","PDF"],"install":{"ready":true,"command":"npx skills add bespoyasov/refactor-like-a-superhero","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":1067,"starsLabel":"1.1K","forks":94,"license":"Unknown","qualityScore":60,"trustScore":75,"auditScore":68},"maintenance":{"status":"stale","label":"1y since push","daysSincePush":455,"lastPushedAt":"2025-05-25T12:45:19+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["License is unclear","Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review"]},"coverageTags":["Research","Document processing","document-processing","pdf","documents","extraction","backend","ebook"]},"audit":{"audit_score":68,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review"]},"decision":{"readiness_score":62,"readiness_label":"Prototype first","headline":"Fallback candidate for Document processing","role":"Fallback candidate","primary_fit":"Document processing","best_for":["Document processing workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["Repository looks stale","No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Document processing task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"bespoyasov-refactor-like-a-superhero","name":"Refactor Like A Superhero","description":"How to refactor code efficiently and without pain.","category":"document-processing","url":"https://www.openagentskill.com/skills/bespoyasov-refactor-like-a-superhero","repository":"https://github.com/bespoyasov/refactor-like-a-superhero","github_repo":"bespoyasov/refactor-like-a-superhero"},"suited_tasks":["Document processing workflows","general agent builders","teams that value GitHub adoption signals","Read uploaded files","Extract structured fields","Prepare clean context for downstream agents","Chunk documents","Create embeddings"],"suited_agents":["PDF","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add bespoyasov/refactor-like-a-superhero","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install bespoyasov-refactor-like-a-superhero"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Refactor Like A Superhero\" agent skill from https://github.com/bespoyasov/refactor-like-a-superhero. 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: How to refactor code efficiently and without pain. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bespoyasov-refactor-like-a-superhero\",\"task\":\"Install Refactor Like A Superhero\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Refactor Like A Superhero\" as a Claude Code skill from https://github.com/bespoyasov/refactor-like-a-superhero. 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: How to refactor code efficiently and without pain. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bespoyasov-refactor-like-a-superhero\",\"task\":\"Install Refactor Like A Superhero\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Refactor Like A Superhero\" from https://github.com/bespoyasov/refactor-like-a-superhero 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: How to refactor code efficiently and without pain. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bespoyasov-refactor-like-a-superhero\",\"task\":\"Install Refactor Like A Superhero\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/bespoyasov-refactor-like-a-superhero/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/bespoyasov-refactor-like-a-superhero"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"1.1K GitHub stars","repoActivity":"1.1K stars, 94 forks","lastPushed":"1y since push","license":"Unknown","repository":"https://github.com/bespoyasov/refactor-like-a-superhero","install":"npx skills add bespoyasov/refactor-like-a-superhero","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["document-processing","pdf","documents","extraction","backend","ebook"],"known_risks":["License is unclear","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","License clarity: Unknown","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":68,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":60,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"Document processing","maintenance":"1y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","Repository appears stale","Quality score needs review"],"agent_contract":{"task_input":"Use Refactor Like A Superhero in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 68/100 Needs review","Safety: 52/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"bespoyasov-refactor-like-a-superhero (Refactor Like A Superhero)","install_command":"npx skills add bespoyasov/refactor-like-a-superhero","risk_summary":"Needs review; Experimental; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"bespoyasov-refactor-like-a-superhero","task":"Use Refactor Like A Superhero 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/bespoyasov-refactor-like-a-superhero","api":"https://www.openagentskill.com/api/agent/skills/bespoyasov-refactor-like-a-superhero","audit":"https://www.openagentskill.com/skills/bespoyasov-refactor-like-a-superhero/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=bespoyasov-refactor-like-a-superhero&task=Use%20Refactor%20Like%20A%20Superhero%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Refactor%20Like%20A%20Superhero%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Refactor%20Like%20A%20Superhero%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/bespoyasov-refactor-like-a-superhero/install","manifest":"https://www.openagentskill.com/api/registry/manifest/bespoyasov-refactor-like-a-superhero"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"bespoyasov-refactor-like-a-superhero","name":"Refactor Like A Superhero","description":"How to refactor code efficiently and without pain.","category":"document-processing","url":"https://www.openagentskill.com/skills/bespoyasov-refactor-like-a-superhero","repository":"https://github.com/bespoyasov/refactor-like-a-superhero","github_repo":"bespoyasov/refactor-like-a-superhero"},"suited_tasks":["Document processing workflows","general agent builders","teams that value GitHub adoption signals","Read uploaded files","Extract structured fields","Prepare clean context for downstream agents","Chunk documents","Create embeddings"],"suited_agents":["PDF","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add bespoyasov/refactor-like-a-superhero","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install bespoyasov-refactor-like-a-superhero"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Refactor Like A Superhero\" agent skill from https://github.com/bespoyasov/refactor-like-a-superhero. 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: How to refactor code efficiently and without pain. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bespoyasov-refactor-like-a-superhero\",\"task\":\"Install Refactor Like A Superhero\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Refactor Like A Superhero\" as a Claude Code skill from https://github.com/bespoyasov/refactor-like-a-superhero. 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: How to refactor code efficiently and without pain. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bespoyasov-refactor-like-a-superhero\",\"task\":\"Install Refactor Like A Superhero\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Refactor Like A Superhero\" from https://github.com/bespoyasov/refactor-like-a-superhero 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: How to refactor code efficiently and without pain. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bespoyasov-refactor-like-a-superhero\",\"task\":\"Install Refactor Like A Superhero\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/bespoyasov-refactor-like-a-superhero/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/bespoyasov-refactor-like-a-superhero"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"1.1K GitHub stars","repoActivity":"1.1K stars, 94 forks","lastPushed":"1y since push","license":"Unknown","repository":"https://github.com/bespoyasov/refactor-like-a-superhero","install":"npx skills add bespoyasov/refactor-like-a-superhero","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["document-processing","pdf","documents","extraction","backend","ebook"],"known_risks":["License is unclear","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","License clarity: Unknown","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":68,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":60,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"Document processing","maintenance":"1y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","Repository appears stale","Quality score needs review"],"agent_contract":{"task_input":"Use Refactor Like A Superhero in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 68/100 Needs review","Safety: 52/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"bespoyasov-refactor-like-a-superhero (Refactor Like A Superhero)","install_command":"npx skills add bespoyasov/refactor-like-a-superhero","risk_summary":"Needs review; Experimental; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"bespoyasov-refactor-like-a-superhero","task":"Use Refactor Like A Superhero 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/bespoyasov-refactor-like-a-superhero","api":"https://www.openagentskill.com/api/agent/skills/bespoyasov-refactor-like-a-superhero","audit":"https://www.openagentskill.com/skills/bespoyasov-refactor-like-a-superhero/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=bespoyasov-refactor-like-a-superhero&task=Use%20Refactor%20Like%20A%20Superhero%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Refactor%20Like%20A%20Superhero%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Refactor%20Like%20A%20Superhero%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/bespoyasov-refactor-like-a-superhero/install","manifest":"https://www.openagentskill.com/api/registry/manifest/bespoyasov-refactor-like-a-superhero"}},"platforms":["PDF"],"use_cases":[{"slug":"document-processing","title":"Document processing","url":"https://www.openagentskill.com/use-cases/document-processing"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"}],"install":"npx skills add bespoyasov/refactor-like-a-superhero","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install bespoyasov-refactor-like-a-superhero","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Refactor Like A Superhero\" agent skill from https://github.com/bespoyasov/refactor-like-a-superhero. 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: How to refactor code efficiently and without pain. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bespoyasov-refactor-like-a-superhero\",\"task\":\"Install Refactor Like A Superhero\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Refactor Like A Superhero\" as a Claude Code skill from https://github.com/bespoyasov/refactor-like-a-superhero. 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: How to refactor code efficiently and without pain. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bespoyasov-refactor-like-a-superhero\",\"task\":\"Install Refactor Like A Superhero\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Refactor Like A Superhero\" from https://github.com/bespoyasov/refactor-like-a-superhero 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: How to refactor code efficiently and without pain. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bespoyasov-refactor-like-a-superhero\",\"task\":\"Install Refactor Like A Superhero\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/bespoyasov/refactor-like-a-superhero","github_repo":"bespoyasov/refactor-like-a-superhero","version":"1.0.0","license":"Unknown","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"bespoyasov/refactor-like-a-superhero","recommendation_reasons":["Matches task terms: refactor, like, superhero","Useful GitHub adoption: 1,067 stars","Install handoff is available","Repository freshness signal is available","Registry match score 99"],"urls":{"web":"https://www.openagentskill.com/skills/bespoyasov-refactor-like-a-superhero","api":"https://www.openagentskill.com/api/agent/skills/bespoyasov-refactor-like-a-superhero","install_api":"https://www.openagentskill.com/api/skills/bespoyasov-refactor-like-a-superhero/install","audit":"https://www.openagentskill.com/skills/bespoyasov-refactor-like-a-superhero/audit","repository":"https://github.com/bespoyasov/refactor-like-a-superhero"}},{"rank":2,"match_type":"related","match_score":13,"raw_match_score":109.2,"semantic_relevance":30,"slug":"anthropic-frontend-design","name":"Frontend Design","description":"Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.","tagline":"Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.","category":"design-creative","tags":["agent-skill","frontend-design","ui","ux","typography","design-system","visual-direction"],"author":{"name":"anthropics","verified":true,"url":"https://github.com/anthropics"},"attribution":{"status":"registry_indexed","statusLabel":"Registry indexed","shortLabel":"REGISTRY INDEXED","sourceLabel":"official skill path","sourceDetail":"anthropics/skills","creatorName":"anthropics","creatorUrl":"https://github.com/anthropics","sourceUrl":"https://github.com/anthropics/skills/tree/main/skills/frontend-design","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/anthropic-frontend-design#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":171052,"forks":20325,"verified_installs":2,"install_attempts":2,"successful_runs":2,"total_outcomes":2,"downloads":0,"rating":0,"review_count":0,"quality_score":83.65},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"171K","tone":"positive"},{"label":"Freshness","value":"1d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Source terms (see LICENSE.txt)","tone":"neutral"}],"warnings":["Use is subject to the upstream source terms; review LICENSE.txt before redistribution."]},"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":"171K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"171K stars, 20K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"1d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Source terms (see LICENSE.txt)"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add anthropics/skills --skill frontend-design"},{"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/anthropics/skills/tree/main/skills/frontend-design"},{"id":"review_status","label":"Review status","score":83.65,"weight":0.05,"status":"info","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"171K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"171K stars, 20K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"1d since push"},{"status":"pass","label":"License clarity","detail":"Source terms (see LICENSE.txt)"},{"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 anthropics/skills --skill frontend-design"},{"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/anthropics/skills/tree/main/skills/frontend-design"},{"status":"info","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":["Use is subject to the upstream source terms; review LICENSE.txt before redistribution.","Documentation summary is thin"],"evidence":{"stars":"171K GitHub stars","repoActivity":"171K stars, 20K forks","lastPushed":"1d since push","license":"Source terms (see LICENSE.txt)","repository":"https://github.com/anthropics/skills/tree/main/skills/frontend-design","install":"npx skills add anthropics/skills --skill frontend-design","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 anthropics/skills --skill frontend-design","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","1d since push"]},"agentCompatibility":["Claude Code","Codex","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Use is subject to the upstream source terms; review LICENSE.txt before redistribution.","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":["design-creative","agent-skill","frontend-design","ui","ux","typography"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Use is subject to the upstream source terms; review LICENSE.txt before redistribution.","Documentation summary is thin"]},"safety":{"score":80,"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","80/100 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","80/100 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":"Design and creative","description":"I need my agent to produce design assets, UI directions, presentations, or creative media workflows.","useCases":[{"slug":"design-creative","title":"Design and creative"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["Claude Code","OpenAI Agents","Cursor","CLI","Codex"],"install":{"ready":true,"command":"npx skills add anthropics/skills --skill frontend-design","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":171052,"starsLabel":"171K","forks":20325,"license":"Source terms (see LICENSE.txt)","qualityScore":100,"trustScore":88,"auditScore":92},"maintenance":{"status":"fresh","label":"1d since push","daysSincePush":1,"lastPushedAt":"2026-08-21T17:10:55+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin","Use is subject to the upstream source terms; review LICENSE.txt before redistribution."]},"coverageTags":["Design","Design and creative","design-creative","agent-skill","frontend-design","ui","ux","typography"]},"audit":{"audit_score":92,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","Use is subject to the upstream source terms; review LICENSE.txt before redistribution."]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Design and creative","role":"Primary pick","primary_fit":"Design and creative","best_for":["Design and creative workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["Use is subject to the upstream source terms; review LICENSE.txt before redistribution.","No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Design and creative 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":"anthropic-frontend-design","name":"Frontend Design","description":"Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.","category":"design-creative","url":"https://www.openagentskill.com/skills/anthropic-frontend-design","repository":"https://github.com/anthropics/skills/tree/main/skills/frontend-design","github_repo":"anthropics/skills"},"suited_tasks":["Design and creative workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect visual requirements","Generate reusable assets","Package output for review","Inspect source files","Explain architecture"],"suited_agents":["Claude Code","Codex","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add anthropics/skills --skill frontend-design","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install anthropic-frontend-design"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Frontend Design\" agent skill from https://github.com/anthropics/skills/tree/main/skills/frontend-design. 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: Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"anthropic-frontend-design\",\"task\":\"Install Frontend Design\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Frontend Design\" as a Claude Code skill from https://github.com/anthropics/skills/tree/main/skills/frontend-design. 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: Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"anthropic-frontend-design\",\"task\":\"Install Frontend Design\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Frontend Design\" from https://github.com/anthropics/skills/tree/main/skills/frontend-design 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: Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"anthropic-frontend-design\",\"task\":\"Install Frontend Design\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/anthropic-frontend-design/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/anthropic-frontend-design"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"171K GitHub stars","repoActivity":"171K stars, 20K forks","lastPushed":"1d since push","license":"Source terms (see LICENSE.txt)","repository":"https://github.com/anthropics/skills/tree/main/skills/frontend-design","install":"npx skills add anthropics/skills --skill frontend-design","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":["design-creative","agent-skill","frontend-design","ui","ux","typography"],"known_risks":["Use is subject to the upstream source terms; review LICENSE.txt before redistribution.","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":92,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","Use is subject to the upstream source terms; review LICENSE.txt before redistribution."]},"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":"Design and creative production","scenario":"Design and creative","maintenance":"1d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","production agents without a repository review","Use is subject to the upstream source terms; review LICENSE.txt before redistribution.","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 Frontend Design 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: 80/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"anthropic-frontend-design (Frontend Design)","install_command":"npx skills add anthropics/skills --skill frontend-design","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":"anthropic-frontend-design","task":"Use Frontend Design 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/anthropic-frontend-design","api":"https://www.openagentskill.com/api/agent/skills/anthropic-frontend-design","audit":"https://www.openagentskill.com/skills/anthropic-frontend-design/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=anthropic-frontend-design&task=Use%20Frontend%20Design%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Frontend%20Design%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Frontend%20Design%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/anthropic-frontend-design/install","manifest":"https://www.openagentskill.com/api/registry/manifest/anthropic-frontend-design"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"anthropic-frontend-design","name":"Frontend Design","description":"Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces.","category":"design-creative","url":"https://www.openagentskill.com/skills/anthropic-frontend-design","repository":"https://github.com/anthropics/skills/tree/main/skills/frontend-design","github_repo":"anthropics/skills"},"suited_tasks":["Design and creative workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect visual requirements","Generate reusable assets","Package output for review","Inspect source files","Explain architecture"],"suited_agents":["Claude Code","Codex","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add anthropics/skills --skill frontend-design","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install anthropic-frontend-design"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Frontend Design\" agent skill from https://github.com/anthropics/skills/tree/main/skills/frontend-design. 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: Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"anthropic-frontend-design\",\"task\":\"Install Frontend Design\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Frontend Design\" as a Claude Code skill from https://github.com/anthropics/skills/tree/main/skills/frontend-design. 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: Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"anthropic-frontend-design\",\"task\":\"Install Frontend Design\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Frontend Design\" from https://github.com/anthropics/skills/tree/main/skills/frontend-design 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: Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"anthropic-frontend-design\",\"task\":\"Install Frontend Design\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/anthropic-frontend-design/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/anthropic-frontend-design"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"171K GitHub stars","repoActivity":"171K stars, 20K forks","lastPushed":"1d since push","license":"Source terms (see LICENSE.txt)","repository":"https://github.com/anthropics/skills/tree/main/skills/frontend-design","install":"npx skills add anthropics/skills --skill frontend-design","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":["design-creative","agent-skill","frontend-design","ui","ux","typography"],"known_risks":["Use is subject to the upstream source terms; review LICENSE.txt before redistribution.","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":92,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","Use is subject to the upstream source terms; review LICENSE.txt before redistribution."]},"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":"Design and creative production","scenario":"Design and creative","maintenance":"1d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","production agents without a repository review","Use is subject to the upstream source terms; review LICENSE.txt before redistribution.","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 Frontend Design 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: 80/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"anthropic-frontend-design (Frontend Design)","install_command":"npx skills add anthropics/skills --skill frontend-design","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":"anthropic-frontend-design","task":"Use Frontend Design 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/anthropic-frontend-design","api":"https://www.openagentskill.com/api/agent/skills/anthropic-frontend-design","audit":"https://www.openagentskill.com/skills/anthropic-frontend-design/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=anthropic-frontend-design&task=Use%20Frontend%20Design%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Frontend%20Design%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Frontend%20Design%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/anthropic-frontend-design/install","manifest":"https://www.openagentskill.com/api/registry/manifest/anthropic-frontend-design"}},"platforms":["Claude Code","Codex","Cursor","OpenAI Agents"],"use_cases":[{"slug":"design-creative","title":"Design and creative","url":"https://www.openagentskill.com/use-cases/design-creative"},{"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/skills --skill frontend-design","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install anthropic-frontend-design","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Frontend Design\" agent skill from https://github.com/anthropics/skills/tree/main/skills/frontend-design. 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: Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"anthropic-frontend-design\",\"task\":\"Install Frontend Design\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Frontend Design\" as a Claude Code skill from https://github.com/anthropics/skills/tree/main/skills/frontend-design. 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: Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"anthropic-frontend-design\",\"task\":\"Install Frontend Design\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Frontend Design\" from https://github.com/anthropics/skills/tree/main/skills/frontend-design 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: Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product interfaces. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"anthropic-frontend-design\",\"task\":\"Install Frontend Design\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/anthropics/skills/tree/main/skills/frontend-design","github_repo":"anthropics/skills","version":"1.0.0","license":"Source terms (see LICENSE.txt)","updated_at":"2026-08-23T04:15:46.021732+00:00","canonical_key":"anthropics/skills#skills/frontend-design","recommendation_reasons":["Matches task terms: like","Strong GitHub adoption: 171,052 stars","Quality score 84/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/anthropic-frontend-design","api":"https://www.openagentskill.com/api/agent/skills/anthropic-frontend-design","install_api":"https://www.openagentskill.com/api/skills/anthropic-frontend-design/install","audit":"https://www.openagentskill.com/skills/anthropic-frontend-design/audit","repository":"https://github.com/anthropics/skills/tree/main/skills/frontend-design"}},{"rank":3,"match_type":"related","match_score":12,"raw_match_score":100.5,"semantic_relevance":30,"slug":"juliusbrussee-caveman","name":"Caveman","description":"🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman","tagline":"🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman","category":"development","tags":["claude-code","agent-skills","developer-tools","ai","anthropic","caveman","claude","llm","meme","prompt-engineering"],"author":{"name":"JuliusBrussee","verified":true,"url":"https://github.com/JuliusBrussee"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"JuliusBrussee/caveman","creatorName":"JuliusBrussee","creatorUrl":"https://github.com/JuliusBrussee","sourceUrl":"https://github.com/JuliusBrussee/caveman","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/juliusbrussee-caveman#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":97436,"forks":5615,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":78.12},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"97K","tone":"positive"},{"label":"Freshness","value":"12d 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":"97K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"97K stars, 5.6K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"12d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"credential or environment access"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add JuliusBrussee/caveman"},{"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":74,"weight":0.07,"status":"info","detail":"secrets or environment access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/JuliusBrussee/caveman"},{"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":"97K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"97K stars, 5.6K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"12d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"info","label":"Dependency/runtime risk","detail":"credential or environment access"},{"status":"pass","label":"Install availability","detail":"npx skills add JuliusBrussee/caveman"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"secrets or environment access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/JuliusBrussee/caveman"},{"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":"97K GitHub stars","repoActivity":"97K stars, 5.6K forks","lastPushed":"12d since push","license":"MIT","repository":"https://github.com/JuliusBrussee/caveman","install":"npx skills add JuliusBrussee/caveman","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add JuliusBrussee/caveman","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","12d since push"]},"agentCompatibility":["JavaScript","Claude Code","Codex","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["development","claude-code","agent-skills","developer-tools","ai","anthropic"],"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":68,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["High-risk permission hints: Secrets or environment access","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":"secrets","label":"Secrets or environment access","reason":"Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.","severity":"high"}],"policy_warnings":["High-risk permission hints: Secrets or environment access","Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["High-risk permission hints: Secrets or environment access","68/100 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":"web-scraping","title":"Web scraping"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","JavaScript"],"install":{"ready":true,"command":"npx skills add JuliusBrussee/caveman","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":97436,"starsLabel":"97K","forks":5615,"license":"MIT","qualityScore":100,"trustScore":88,"auditScore":92},"maintenance":{"status":"fresh","label":"12d since push","daysSincePush":12,"lastPushedAt":"2026-08-11T13:11:16+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Coding","Coding agents","development","claude-code","agent-skills","developer-tools","ai","anthropic"]},"audit":{"audit_score":92,"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 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":"juliusbrussee-caveman","name":"Caveman","description":"🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman","category":"development","url":"https://www.openagentskill.com/skills/juliusbrussee-caveman","repository":"https://github.com/JuliusBrussee/caveman","github_repo":"JuliusBrussee/caveman"},"suited_tasks":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Crawl target URLs","Extract tables and metadata"],"suited_agents":["JavaScript","Claude Code","Codex","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add JuliusBrussee/caveman","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install juliusbrussee-caveman"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Caveman\" agent skill from https://github.com/JuliusBrussee/caveman. 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: 🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"juliusbrussee-caveman\",\"task\":\"Install Caveman\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Caveman\" as a Claude Code skill from https://github.com/JuliusBrussee/caveman. 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: 🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"juliusbrussee-caveman\",\"task\":\"Install Caveman\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Caveman\" from https://github.com/JuliusBrussee/caveman 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: 🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"juliusbrussee-caveman\",\"task\":\"Install Caveman\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/juliusbrussee-caveman/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/juliusbrussee-caveman"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"97K GitHub stars","repoActivity":"97K stars, 5.6K forks","lastPushed":"12d since push","license":"MIT","repository":"https://github.com/JuliusBrussee/caveman","install":"npx skills add JuliusBrussee/caveman","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment 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":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["development","claude-code","agent-skills","developer-tools","ai","anthropic"],"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":92,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"12d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","High-risk permission hints: Secrets or environment access","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 Caveman in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 88/100 Production candidate","Audit: 92/100 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":"juliusbrussee-caveman (Caveman)","install_command":"npx skills add JuliusBrussee/caveman","risk_summary":"Safe to try; Reviewed with permission notes; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"juliusbrussee-caveman","task":"Use Caveman 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/juliusbrussee-caveman","api":"https://www.openagentskill.com/api/agent/skills/juliusbrussee-caveman","audit":"https://www.openagentskill.com/skills/juliusbrussee-caveman/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=juliusbrussee-caveman&task=Use%20Caveman%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Caveman%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Caveman%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/juliusbrussee-caveman/install","manifest":"https://www.openagentskill.com/api/registry/manifest/juliusbrussee-caveman"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"juliusbrussee-caveman","name":"Caveman","description":"🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman","category":"development","url":"https://www.openagentskill.com/skills/juliusbrussee-caveman","repository":"https://github.com/JuliusBrussee/caveman","github_repo":"JuliusBrussee/caveman"},"suited_tasks":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Crawl target URLs","Extract tables and metadata"],"suited_agents":["JavaScript","Claude Code","Codex","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add JuliusBrussee/caveman","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install juliusbrussee-caveman"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Caveman\" agent skill from https://github.com/JuliusBrussee/caveman. 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: 🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"juliusbrussee-caveman\",\"task\":\"Install Caveman\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Caveman\" as a Claude Code skill from https://github.com/JuliusBrussee/caveman. 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: 🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"juliusbrussee-caveman\",\"task\":\"Install Caveman\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Caveman\" from https://github.com/JuliusBrussee/caveman 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: 🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"juliusbrussee-caveman\",\"task\":\"Install Caveman\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/juliusbrussee-caveman/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/juliusbrussee-caveman"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"97K GitHub stars","repoActivity":"97K stars, 5.6K forks","lastPushed":"12d since push","license":"MIT","repository":"https://github.com/JuliusBrussee/caveman","install":"npx skills add JuliusBrussee/caveman","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment 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":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["development","claude-code","agent-skills","developer-tools","ai","anthropic"],"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":92,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"12d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","High-risk permission hints: Secrets or environment access","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 Caveman in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 88/100 Production candidate","Audit: 92/100 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":"juliusbrussee-caveman (Caveman)","install_command":"npx skills add JuliusBrussee/caveman","risk_summary":"Safe to try; Reviewed with permission notes; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"juliusbrussee-caveman","task":"Use Caveman 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/juliusbrussee-caveman","api":"https://www.openagentskill.com/api/agent/skills/juliusbrussee-caveman","audit":"https://www.openagentskill.com/skills/juliusbrussee-caveman/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=juliusbrussee-caveman&task=Use%20Caveman%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Caveman%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Caveman%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/juliusbrussee-caveman/install","manifest":"https://www.openagentskill.com/api/registry/manifest/juliusbrussee-caveman"}},"platforms":["JavaScript","Claude Code"],"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"install":"npx skills add JuliusBrussee/caveman","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install juliusbrussee-caveman","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Caveman\" agent skill from https://github.com/JuliusBrussee/caveman. 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: 🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"juliusbrussee-caveman\",\"task\":\"Install Caveman\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Caveman\" as a Claude Code skill from https://github.com/JuliusBrussee/caveman. 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: 🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"juliusbrussee-caveman\",\"task\":\"Install Caveman\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Caveman\" from https://github.com/JuliusBrussee/caveman 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: 🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"juliusbrussee-caveman\",\"task\":\"Install Caveman\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/JuliusBrussee/caveman","github_repo":"JuliusBrussee/caveman","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"juliusbrussee/caveman","recommendation_reasons":["Matches task terms: like","Strong GitHub adoption: 97,436 stars","Quality score 78/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/juliusbrussee-caveman","api":"https://www.openagentskill.com/api/agent/skills/juliusbrussee-caveman","install_api":"https://www.openagentskill.com/api/skills/juliusbrussee-caveman/install","audit":"https://www.openagentskill.com/skills/juliusbrussee-caveman/audit","repository":"https://github.com/JuliusBrussee/caveman"}},{"rank":4,"match_type":"related","match_score":12,"raw_match_score":99.8,"semantic_relevance":30,"slug":"excalidraw-excalidraw","name":"Excalidraw","description":"Virtual whiteboard for sketching hand-drawn like diagrams","tagline":"Virtual whiteboard for sketching hand-drawn like diagrams","category":"productivity-automation","tags":["productivity","automation","canvas","collaboration","diagrams","drawing","hacktoberfest","whiteboard","typescript","github"],"author":{"name":"excalidraw","verified":true,"url":"https://github.com/excalidraw"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"excalidraw/excalidraw","creatorName":"excalidraw","creatorUrl":"https://github.com/excalidraw","sourceUrl":"https://github.com/excalidraw/excalidraw","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/excalidraw-excalidraw#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":125436,"forks":14034,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":75.2},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"125K","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":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":"125K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"125K stars, 14K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add excalidraw/excalidraw"},{"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/excalidraw/excalidraw"},{"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":"125K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"125K stars, 14K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add excalidraw/excalidraw"},{"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/excalidraw/excalidraw"},{"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":"125K GitHub stars","repoActivity":"125K stars, 14K forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/excalidraw/excalidraw","install":"npx skills add excalidraw/excalidraw","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add excalidraw/excalidraw","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["TypeScript","Productivity","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["productivity-automation","productivity","automation","canvas","collaboration","diagrams"],"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":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"}],"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":"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":"workflow-automation","title":"Workflow automation"},{"slug":"github-automation","title":"GitHub automation"},{"slug":"coding-agents","title":"Coding agents"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","TypeScript"],"install":{"ready":true,"command":"npx skills add excalidraw/excalidraw","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":125436,"starsLabel":"125K","forks":14034,"license":"MIT","qualityScore":100,"trustScore":88,"auditScore":91},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":68,"lastPushedAt":"2026-06-16T08:45:47+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","productivity-automation","productivity","automation","canvas","collaboration","diagrams"]},"audit":{"audit_score":91,"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","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one 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":"excalidraw-excalidraw","name":"Excalidraw","description":"Virtual whiteboard for sketching hand-drawn like diagrams","category":"productivity-automation","url":"https://www.openagentskill.com/skills/excalidraw-excalidraw","repository":"https://github.com/excalidraw/excalidraw","github_repo":"excalidraw/excalidraw"},"suited_tasks":["Workflow automation workflows","general agent builders","teams that value GitHub adoption signals","Move data between tools","Transform files","Trigger repeatable actions","Inspect repository metadata","Compare code changes"],"suited_agents":["TypeScript","Productivity","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add excalidraw/excalidraw","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install excalidraw-excalidraw"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Excalidraw\" agent skill from https://github.com/excalidraw/excalidraw. 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: Virtual whiteboard for sketching hand-drawn like diagrams After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"excalidraw-excalidraw\",\"task\":\"Install Excalidraw\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Excalidraw\" as a Claude Code skill from https://github.com/excalidraw/excalidraw. 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: Virtual whiteboard for sketching hand-drawn like diagrams After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"excalidraw-excalidraw\",\"task\":\"Install Excalidraw\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Excalidraw\" from https://github.com/excalidraw/excalidraw 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: Virtual whiteboard for sketching hand-drawn like diagrams After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"excalidraw-excalidraw\",\"task\":\"Install Excalidraw\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/excalidraw-excalidraw/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/excalidraw-excalidraw"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"125K GitHub stars","repoActivity":"125K stars, 14K forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/excalidraw/excalidraw","install":"npx skills add excalidraw/excalidraw","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["productivity-automation","productivity","automation","canvas","collaboration","diagrams"],"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":91,"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":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Excalidraw 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: 91/100 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":"excalidraw-excalidraw (Excalidraw)","install_command":"npx skills add excalidraw/excalidraw","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":"excalidraw-excalidraw","task":"Use Excalidraw 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/excalidraw-excalidraw","api":"https://www.openagentskill.com/api/agent/skills/excalidraw-excalidraw","audit":"https://www.openagentskill.com/skills/excalidraw-excalidraw/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=excalidraw-excalidraw&task=Use%20Excalidraw%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Excalidraw%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Excalidraw%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/excalidraw-excalidraw/install","manifest":"https://www.openagentskill.com/api/registry/manifest/excalidraw-excalidraw"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"excalidraw-excalidraw","name":"Excalidraw","description":"Virtual whiteboard for sketching hand-drawn like diagrams","category":"productivity-automation","url":"https://www.openagentskill.com/skills/excalidraw-excalidraw","repository":"https://github.com/excalidraw/excalidraw","github_repo":"excalidraw/excalidraw"},"suited_tasks":["Workflow automation workflows","general agent builders","teams that value GitHub adoption signals","Move data between tools","Transform files","Trigger repeatable actions","Inspect repository metadata","Compare code changes"],"suited_agents":["TypeScript","Productivity","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add excalidraw/excalidraw","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install excalidraw-excalidraw"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Excalidraw\" agent skill from https://github.com/excalidraw/excalidraw. 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: Virtual whiteboard for sketching hand-drawn like diagrams After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"excalidraw-excalidraw\",\"task\":\"Install Excalidraw\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Excalidraw\" as a Claude Code skill from https://github.com/excalidraw/excalidraw. 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: Virtual whiteboard for sketching hand-drawn like diagrams After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"excalidraw-excalidraw\",\"task\":\"Install Excalidraw\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Excalidraw\" from https://github.com/excalidraw/excalidraw 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: Virtual whiteboard for sketching hand-drawn like diagrams After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"excalidraw-excalidraw\",\"task\":\"Install Excalidraw\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/excalidraw-excalidraw/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/excalidraw-excalidraw"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"125K GitHub stars","repoActivity":"125K stars, 14K forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/excalidraw/excalidraw","install":"npx skills add excalidraw/excalidraw","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["productivity-automation","productivity","automation","canvas","collaboration","diagrams"],"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":91,"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":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Excalidraw 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: 91/100 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":"excalidraw-excalidraw (Excalidraw)","install_command":"npx skills add excalidraw/excalidraw","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":"excalidraw-excalidraw","task":"Use Excalidraw 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/excalidraw-excalidraw","api":"https://www.openagentskill.com/api/agent/skills/excalidraw-excalidraw","audit":"https://www.openagentskill.com/skills/excalidraw-excalidraw/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=excalidraw-excalidraw&task=Use%20Excalidraw%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Excalidraw%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Excalidraw%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/excalidraw-excalidraw/install","manifest":"https://www.openagentskill.com/api/registry/manifest/excalidraw-excalidraw"}},"platforms":["TypeScript","Productivity"],"use_cases":[{"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":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"install":"npx skills add excalidraw/excalidraw","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install excalidraw-excalidraw","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Excalidraw\" agent skill from https://github.com/excalidraw/excalidraw. 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: Virtual whiteboard for sketching hand-drawn like diagrams After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"excalidraw-excalidraw\",\"task\":\"Install Excalidraw\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Excalidraw\" as a Claude Code skill from https://github.com/excalidraw/excalidraw. 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: Virtual whiteboard for sketching hand-drawn like diagrams After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"excalidraw-excalidraw\",\"task\":\"Install Excalidraw\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Excalidraw\" from https://github.com/excalidraw/excalidraw 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: Virtual whiteboard for sketching hand-drawn like diagrams After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"excalidraw-excalidraw\",\"task\":\"Install Excalidraw\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/excalidraw/excalidraw","github_repo":"excalidraw/excalidraw","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"excalidraw/excalidraw","recommendation_reasons":["Matches task terms: like","Strong GitHub adoption: 125,436 stars","Quality score 75/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/excalidraw-excalidraw","api":"https://www.openagentskill.com/api/agent/skills/excalidraw-excalidraw","install_api":"https://www.openagentskill.com/api/skills/excalidraw-excalidraw/install","audit":"https://www.openagentskill.com/skills/excalidraw-excalidraw/audit","repository":"https://github.com/excalidraw/excalidraw"}},{"rank":5,"match_type":"related","match_score":12,"raw_match_score":99.8,"semantic_relevance":30,"slug":"rasbt-llms-from-scratch","name":"LLMs From Scratch","description":"Implement a ChatGPT-like LLM in PyTorch from scratch, step by step","tagline":"Implement a ChatGPT-like LLM in PyTorch from scratch, step by step","category":"ml-automation","tags":["machine-learning","automation","ml-media","ai","artificial-intelligence","attention-mechanism","deep-learning","finetuning","from-scratch","generative-ai"],"author":{"name":"rasbt","verified":true,"url":"https://github.com/rasbt"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"rasbt/LLMs-from-scratch","creatorName":"rasbt","creatorUrl":"https://github.com/rasbt","sourceUrl":"https://github.com/rasbt/LLMs-from-scratch","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/rasbt-llms-from-scratch#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":97256,"forks":14876,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":75.12},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"97K","tone":"positive"},{"label":"Freshness","value":"3mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":85,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"97K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"97K stars, 15K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"3mo since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add rasbt/LLMs-from-scratch"},{"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/rasbt/LLMs-from-scratch"},{"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":"97K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"97K stars, 15K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3mo since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add rasbt/LLMs-from-scratch"},{"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/rasbt/LLMs-from-scratch"},{"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","Documentation summary is thin","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"97K GitHub stars","repoActivity":"97K stars, 15K forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/rasbt/LLMs-from-scratch","install":"npx skills add rasbt/LLMs-from-scratch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add rasbt/LLMs-from-scratch","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","No Agent Proven outcome evidence yet","3mo since push"]},"agentCompatibility":["Jupyter Notebook","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Documentation summary is thin","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["ml-automation","machine-learning","automation","ml-media","ai","artificial-intelligence"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","Documentation summary is thin","License clarity: Unknown","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 with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["License is unclear","77/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["License is unclear"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["License is unclear","77/100 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":"browser-automation","title":"Browser automation"},{"slug":"workflow-automation","title":"Workflow automation"},{"slug":"data-analysis","title":"Data analysis"}]},"applicableAgents":["OpenAI Agents","CLI","Codex","Claude Code","Cursor"],"install":{"ready":true,"command":"npx skills add rasbt/LLMs-from-scratch","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":97256,"starsLabel":"97K","forks":14876,"license":"Unknown","qualityScore":100,"trustScore":85,"auditScore":89},"maintenance":{"status":"active","label":"3mo since push","daysSincePush":82,"lastPushedAt":"2026-06-02T14:14:19+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["License is unclear","Documentation summary is thin","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Needs review"]},"coverageTags":["Design","Multimodal media","ml-automation","machine-learning","automation","ml-media","ai","artificial-intelligence"]},"audit":{"audit_score":89,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown","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","OpenAI Agents teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Browser automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"rasbt-llms-from-scratch","name":"LLMs From Scratch","description":"Implement a ChatGPT-like LLM in PyTorch from scratch, step by step","category":"ml-automation","url":"https://www.openagentskill.com/skills/rasbt-llms-from-scratch","repository":"https://github.com/rasbt/LLMs-from-scratch","github_repo":"rasbt/LLMs-from-scratch"},"suited_tasks":["Browser automation workflows","OpenAI Agents 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":["Jupyter Notebook","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add rasbt/LLMs-from-scratch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install rasbt-llms-from-scratch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"LLMs From Scratch\" agent skill from https://github.com/rasbt/LLMs-from-scratch. 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: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"rasbt-llms-from-scratch\",\"task\":\"Install LLMs From Scratch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"LLMs From Scratch\" as a Claude Code skill from https://github.com/rasbt/LLMs-from-scratch. 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: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"rasbt-llms-from-scratch\",\"task\":\"Install LLMs From Scratch\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"LLMs From Scratch\" from https://github.com/rasbt/LLMs-from-scratch 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: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"rasbt-llms-from-scratch\",\"task\":\"Install LLMs From Scratch\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/rasbt-llms-from-scratch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/rasbt-llms-from-scratch"},"trust":{"score":85,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"97K GitHub stars","repoActivity":"97K stars, 15K forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/rasbt/LLMs-from-scratch","install":"npx skills add rasbt/LLMs-from-scratch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["ml-automation","machine-learning","automation","ml-media","ai","artificial-intelligence"],"known_risks":["License is unclear","Documentation summary is thin","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":89,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"3mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use LLMs From Scratch in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 85/100 Strong shortlist","Audit: 89/100 Needs review","Safety: 77/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"rasbt-llms-from-scratch (LLMs From Scratch)","install_command":"npx skills add rasbt/LLMs-from-scratch","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"rasbt-llms-from-scratch","task":"Use LLMs From Scratch 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/rasbt-llms-from-scratch","api":"https://www.openagentskill.com/api/agent/skills/rasbt-llms-from-scratch","audit":"https://www.openagentskill.com/skills/rasbt-llms-from-scratch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=rasbt-llms-from-scratch&task=Use%20LLMs%20From%20Scratch%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20LLMs%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20LLMs%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/rasbt-llms-from-scratch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/rasbt-llms-from-scratch"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"rasbt-llms-from-scratch","name":"LLMs From Scratch","description":"Implement a ChatGPT-like LLM in PyTorch from scratch, step by step","category":"ml-automation","url":"https://www.openagentskill.com/skills/rasbt-llms-from-scratch","repository":"https://github.com/rasbt/LLMs-from-scratch","github_repo":"rasbt/LLMs-from-scratch"},"suited_tasks":["Browser automation workflows","OpenAI Agents 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":["Jupyter Notebook","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add rasbt/LLMs-from-scratch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install rasbt-llms-from-scratch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"LLMs From Scratch\" agent skill from https://github.com/rasbt/LLMs-from-scratch. 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: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"rasbt-llms-from-scratch\",\"task\":\"Install LLMs From Scratch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"LLMs From Scratch\" as a Claude Code skill from https://github.com/rasbt/LLMs-from-scratch. 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: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"rasbt-llms-from-scratch\",\"task\":\"Install LLMs From Scratch\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"LLMs From Scratch\" from https://github.com/rasbt/LLMs-from-scratch 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: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"rasbt-llms-from-scratch\",\"task\":\"Install LLMs From Scratch\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/rasbt-llms-from-scratch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/rasbt-llms-from-scratch"},"trust":{"score":85,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"97K GitHub stars","repoActivity":"97K stars, 15K forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/rasbt/LLMs-from-scratch","install":"npx skills add rasbt/LLMs-from-scratch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["ml-automation","machine-learning","automation","ml-media","ai","artificial-intelligence"],"known_risks":["License is unclear","Documentation summary is thin","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":89,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"3mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use LLMs From Scratch in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 85/100 Strong shortlist","Audit: 89/100 Needs review","Safety: 77/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"rasbt-llms-from-scratch (LLMs From Scratch)","install_command":"npx skills add rasbt/LLMs-from-scratch","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"rasbt-llms-from-scratch","task":"Use LLMs From Scratch 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/rasbt-llms-from-scratch","api":"https://www.openagentskill.com/api/agent/skills/rasbt-llms-from-scratch","audit":"https://www.openagentskill.com/skills/rasbt-llms-from-scratch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=rasbt-llms-from-scratch&task=Use%20LLMs%20From%20Scratch%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20LLMs%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20LLMs%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/rasbt-llms-from-scratch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/rasbt-llms-from-scratch"}},"platforms":["Jupyter Notebook","Machine Learning","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":"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"}],"install":"npx skills add rasbt/LLMs-from-scratch","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install rasbt-llms-from-scratch","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"LLMs From Scratch\" agent skill from https://github.com/rasbt/LLMs-from-scratch. 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: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"rasbt-llms-from-scratch\",\"task\":\"Install LLMs From Scratch\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"LLMs From Scratch\" as a Claude Code skill from https://github.com/rasbt/LLMs-from-scratch. 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: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"rasbt-llms-from-scratch\",\"task\":\"Install LLMs From Scratch\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"LLMs From Scratch\" from https://github.com/rasbt/LLMs-from-scratch 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: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"rasbt-llms-from-scratch\",\"task\":\"Install LLMs From Scratch\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/rasbt/LLMs-from-scratch","github_repo":"rasbt/LLMs-from-scratch","version":"1.0.0","license":"Unknown","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"rasbt/llms-from-scratch","recommendation_reasons":["Matches task terms: like","Strong GitHub adoption: 97,256 stars","Quality score 75/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/rasbt-llms-from-scratch","api":"https://www.openagentskill.com/api/agent/skills/rasbt-llms-from-scratch","install_api":"https://www.openagentskill.com/api/skills/rasbt-llms-from-scratch/install","audit":"https://www.openagentskill.com/skills/rasbt-llms-from-scratch/audit","repository":"https://github.com/rasbt/LLMs-from-scratch"}},{"rank":6,"match_type":"related","match_score":12,"raw_match_score":99.6,"semantic_relevance":30,"slug":"grafana-grafana","name":"Grafana","description":"The open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more. ","tagline":"The open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more. ","category":"data-analysis","tags":["business-intelligence","analytics","data","alerting","dashboard","data-visualization","elasticsearch","go","grafana","hacktoberfest"],"author":{"name":"grafana","verified":true,"url":"https://github.com/grafana"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"grafana/grafana","creatorName":"grafana","creatorUrl":"https://github.com/grafana","sourceUrl":"https://github.com/grafana/grafana","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/grafana-grafana#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":74422,"forks":14068,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":74.3},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"74K","tone":"positive"},{"label":"Freshness","value":"2mo 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":89,"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":"74K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"74K stars, 14K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"AGPL-3.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":82,"weight":0.12,"status":"pass","detail":"database surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add grafana/grafana"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":88,"weight":0.07,"status":"pass","detail":"database access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/grafana/grafana"},{"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":"74K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"74K stars, 14K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"AGPL-3.0"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"database surface"},{"status":"pass","label":"Install availability","detail":"npx skills add grafana/grafana"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"database access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/grafana/grafana"},{"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":"74K GitHub stars","repoActivity":"74K stars, 14K forks","lastPushed":"2mo since push","license":"AGPL-3.0","repository":"https://github.com/grafana/grafana","install":"npx skills add grafana/grafana","installSafety":"standard package or runtime install path","permissionSurface":"database access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add grafana/grafana","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["TypeScript","BI","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["data-analysis","business-intelligence","analytics","data","alerting","dashboard"],"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":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":"database","label":"Database access","reason":"Skill may inspect schemas, query databases, or work with persistent stores.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"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":"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":"research-agents","title":"Research agents"},{"slug":"data-analysis","title":"Data analysis"},{"slug":"database-sql","title":"Database and SQL"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","TypeScript"],"install":{"ready":true,"command":"npx skills add grafana/grafana","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":74422,"starsLabel":"74K","forks":14068,"license":"AGPL-3.0","qualityScore":100,"trustScore":89,"auditScore":92},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":69,"lastPushedAt":"2026-06-15T02:43:14+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Data","Data analysis","data-analysis","business-intelligence","analytics","alerting","dashboard","data-visualization"]},"audit":{"audit_score":92,"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 Research agents","role":"Primary pick","primary_fit":"Research agents","best_for":["Research agents workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Research agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"grafana-grafana","name":"Grafana","description":"The open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more. ","category":"data-analysis","url":"https://www.openagentskill.com/skills/grafana-grafana","repository":"https://github.com/grafana/grafana","github_repo":"grafana/grafana"},"suited_tasks":["Research agents workflows","general agent builders","teams that value GitHub adoption signals","Search sources","Extract claims","Synthesize findings","Load tabular data","Calculate trends"],"suited_agents":["TypeScript","BI","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add grafana/grafana","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install grafana-grafana"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Grafana\" agent skill from https://github.com/grafana/grafana. 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 open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"grafana-grafana\",\"task\":\"Install Grafana\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Grafana\" as a Claude Code skill from https://github.com/grafana/grafana. 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 open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"grafana-grafana\",\"task\":\"Install Grafana\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Grafana\" from https://github.com/grafana/grafana 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 open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"grafana-grafana\",\"task\":\"Install Grafana\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/grafana-grafana/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/grafana-grafana"},"trust":{"score":89,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"74K GitHub stars","repoActivity":"74K stars, 14K forks","lastPushed":"2mo since push","license":"AGPL-3.0","repository":"https://github.com/grafana/grafana","install":"npx skills add grafana/grafana","installSafety":"standard package or runtime install path","permissionSurface":"database 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":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["data-analysis","business-intelligence","analytics","data","alerting","dashboard"],"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":92,"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":"Data, BI, and analytics","scenario":"Data analysis","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Grafana 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: 89/100 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":"grafana-grafana (Grafana)","install_command":"npx skills add grafana/grafana","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":"grafana-grafana","task":"Use Grafana 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/grafana-grafana","api":"https://www.openagentskill.com/api/agent/skills/grafana-grafana","audit":"https://www.openagentskill.com/skills/grafana-grafana/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=grafana-grafana&task=Use%20Grafana%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Grafana%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Grafana%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/grafana-grafana/install","manifest":"https://www.openagentskill.com/api/registry/manifest/grafana-grafana"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"grafana-grafana","name":"Grafana","description":"The open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more. ","category":"data-analysis","url":"https://www.openagentskill.com/skills/grafana-grafana","repository":"https://github.com/grafana/grafana","github_repo":"grafana/grafana"},"suited_tasks":["Research agents workflows","general agent builders","teams that value GitHub adoption signals","Search sources","Extract claims","Synthesize findings","Load tabular data","Calculate trends"],"suited_agents":["TypeScript","BI","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add grafana/grafana","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install grafana-grafana"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Grafana\" agent skill from https://github.com/grafana/grafana. 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 open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"grafana-grafana\",\"task\":\"Install Grafana\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Grafana\" as a Claude Code skill from https://github.com/grafana/grafana. 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 open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"grafana-grafana\",\"task\":\"Install Grafana\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Grafana\" from https://github.com/grafana/grafana 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 open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"grafana-grafana\",\"task\":\"Install Grafana\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/grafana-grafana/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/grafana-grafana"},"trust":{"score":89,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"74K GitHub stars","repoActivity":"74K stars, 14K forks","lastPushed":"2mo since push","license":"AGPL-3.0","repository":"https://github.com/grafana/grafana","install":"npx skills add grafana/grafana","installSafety":"standard package or runtime install path","permissionSurface":"database 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":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["data-analysis","business-intelligence","analytics","data","alerting","dashboard"],"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":92,"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":"Data, BI, and analytics","scenario":"Data analysis","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Grafana 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: 89/100 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":"grafana-grafana (Grafana)","install_command":"npx skills add grafana/grafana","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":"grafana-grafana","task":"Use Grafana 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/grafana-grafana","api":"https://www.openagentskill.com/api/agent/skills/grafana-grafana","audit":"https://www.openagentskill.com/skills/grafana-grafana/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=grafana-grafana&task=Use%20Grafana%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Grafana%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Grafana%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/grafana-grafana/install","manifest":"https://www.openagentskill.com/api/registry/manifest/grafana-grafana"}},"platforms":["TypeScript","BI"],"use_cases":[{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"data-analysis","title":"Data analysis","url":"https://www.openagentskill.com/use-cases/data-analysis"},{"slug":"database-sql","title":"Database and SQL","url":"https://www.openagentskill.com/use-cases/database-sql"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"}],"install":"npx skills add grafana/grafana","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install grafana-grafana","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Grafana\" agent skill from https://github.com/grafana/grafana. 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 open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"grafana-grafana\",\"task\":\"Install Grafana\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Grafana\" as a Claude Code skill from https://github.com/grafana/grafana. 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 open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"grafana-grafana\",\"task\":\"Install Grafana\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Grafana\" from https://github.com/grafana/grafana 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 open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"grafana-grafana\",\"task\":\"Install Grafana\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/grafana/grafana","github_repo":"grafana/grafana","version":"1.0.0","license":"AGPL-3.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"grafana/grafana","recommendation_reasons":["Matches task terms: like","Strong GitHub adoption: 74,422 stars","Quality score 74/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/grafana-grafana","api":"https://www.openagentskill.com/api/agent/skills/grafana-grafana","install_api":"https://www.openagentskill.com/api/skills/grafana-grafana/install","audit":"https://www.openagentskill.com/skills/grafana-grafana/audit","repository":"https://github.com/grafana/grafana"}},{"rank":7,"match_type":"related","match_score":12,"raw_match_score":99.5,"semantic_relevance":30,"slug":"opendatalab-mineru","name":"MinerU","description":"Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.","tagline":"Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.","category":"document-processing","tags":["pdf","documents","extraction","ai4science","document-analysis","docx","extract-data","layout-analysis","ocr","parser"],"author":{"name":"opendatalab","verified":true,"url":"https://github.com/opendatalab"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"opendatalab/MinerU","creatorName":"opendatalab","creatorUrl":"https://github.com/opendatalab","sourceUrl":"https://github.com/opendatalab/MinerU","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/opendatalab-mineru#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":67913,"forks":5719,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":74.02},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"68K","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":86,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"68K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"68K stars, 5.7K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add opendatalab/MinerU"},{"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/opendatalab/MinerU"},{"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":"68K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"68K stars, 5.7K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add opendatalab/MinerU"},{"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/opendatalab/MinerU"},{"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","Documentation summary is thin","License clarity: Unknown"],"evidence":{"stars":"68K GitHub stars","repoActivity":"68K stars, 5.7K forks","lastPushed":"2mo since push","license":"Unknown","repository":"https://github.com/opendatalab/MinerU","install":"npx skills add opendatalab/MinerU","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 opendatalab/MinerU","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Python","PDF","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["document-processing","pdf","documents","extraction","ai4science","document-analysis"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"safety":{"score":73,"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","73/100 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","73/100 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":"document-processing","title":"Document processing"},{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"web-scraping","title":"Web scraping"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add opendatalab/MinerU","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":67913,"starsLabel":"68K","forks":5719,"license":"Unknown","qualityScore":100,"trustScore":86,"auditScore":89},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":67,"lastPushedAt":"2026-06-17T12:16:33+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"coverageTags":["Research","Document processing","document-processing","pdf","documents","extraction","ai4science","document-analysis"]},"audit":{"audit_score":89,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Document processing","role":"Primary pick","primary_fit":"Document processing","best_for":["Document processing workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Document processing task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"opendatalab-mineru","name":"MinerU","description":"Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.","category":"document-processing","url":"https://www.openagentskill.com/skills/opendatalab-mineru","repository":"https://github.com/opendatalab/MinerU","github_repo":"opendatalab/MinerU"},"suited_tasks":["Document processing workflows","general agent builders","teams that value GitHub adoption signals","Read uploaded files","Extract structured fields","Prepare clean context for downstream agents","Chunk documents","Create embeddings"],"suited_agents":["Python","PDF","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add opendatalab/MinerU","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install opendatalab-mineru"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"MinerU\" agent skill from https://github.com/opendatalab/MinerU. 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: Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"opendatalab-mineru\",\"task\":\"Install MinerU\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"MinerU\" as a Claude Code skill from https://github.com/opendatalab/MinerU. 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: Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"opendatalab-mineru\",\"task\":\"Install MinerU\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"MinerU\" from https://github.com/opendatalab/MinerU 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: Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"opendatalab-mineru\",\"task\":\"Install MinerU\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/opendatalab-mineru/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/opendatalab-mineru"},"trust":{"score":86,"label":"Production candidate","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"68K GitHub stars","repoActivity":"68K stars, 5.7K forks","lastPushed":"2mo since push","license":"Unknown","repository":"https://github.com/opendatalab/MinerU","install":"npx skills add opendatalab/MinerU","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":["document-processing","pdf","documents","extraction","ai4science","document-analysis"],"known_risks":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":89,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"Document processing","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use MinerU in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 86/100 Production candidate","Audit: 89/100 Safe to try","Safety: 73/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"opendatalab-mineru (MinerU)","install_command":"npx skills add opendatalab/MinerU","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":"opendatalab-mineru","task":"Use MinerU 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/opendatalab-mineru","api":"https://www.openagentskill.com/api/agent/skills/opendatalab-mineru","audit":"https://www.openagentskill.com/skills/opendatalab-mineru/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=opendatalab-mineru&task=Use%20MinerU%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20MinerU%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20MinerU%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/opendatalab-mineru/install","manifest":"https://www.openagentskill.com/api/registry/manifest/opendatalab-mineru"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"opendatalab-mineru","name":"MinerU","description":"Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.","category":"document-processing","url":"https://www.openagentskill.com/skills/opendatalab-mineru","repository":"https://github.com/opendatalab/MinerU","github_repo":"opendatalab/MinerU"},"suited_tasks":["Document processing workflows","general agent builders","teams that value GitHub adoption signals","Read uploaded files","Extract structured fields","Prepare clean context for downstream agents","Chunk documents","Create embeddings"],"suited_agents":["Python","PDF","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add opendatalab/MinerU","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install opendatalab-mineru"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"MinerU\" agent skill from https://github.com/opendatalab/MinerU. 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: Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"opendatalab-mineru\",\"task\":\"Install MinerU\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"MinerU\" as a Claude Code skill from https://github.com/opendatalab/MinerU. 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: Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"opendatalab-mineru\",\"task\":\"Install MinerU\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"MinerU\" from https://github.com/opendatalab/MinerU 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: Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"opendatalab-mineru\",\"task\":\"Install MinerU\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/opendatalab-mineru/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/opendatalab-mineru"},"trust":{"score":86,"label":"Production candidate","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"68K GitHub stars","repoActivity":"68K stars, 5.7K forks","lastPushed":"2mo since push","license":"Unknown","repository":"https://github.com/opendatalab/MinerU","install":"npx skills add opendatalab/MinerU","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":["document-processing","pdf","documents","extraction","ai4science","document-analysis"],"known_risks":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":89,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"Document processing","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use MinerU in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 86/100 Production candidate","Audit: 89/100 Safe to try","Safety: 73/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"opendatalab-mineru (MinerU)","install_command":"npx skills add opendatalab/MinerU","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":"opendatalab-mineru","task":"Use MinerU 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/opendatalab-mineru","api":"https://www.openagentskill.com/api/agent/skills/opendatalab-mineru","audit":"https://www.openagentskill.com/skills/opendatalab-mineru/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=opendatalab-mineru&task=Use%20MinerU%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20MinerU%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20MinerU%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/opendatalab-mineru/install","manifest":"https://www.openagentskill.com/api/registry/manifest/opendatalab-mineru"}},"platforms":["Python","PDF"],"use_cases":[{"slug":"document-processing","title":"Document processing","url":"https://www.openagentskill.com/use-cases/document-processing"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"install":"npx skills add opendatalab/MinerU","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install opendatalab-mineru","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"MinerU\" agent skill from https://github.com/opendatalab/MinerU. 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: Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"opendatalab-mineru\",\"task\":\"Install MinerU\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"MinerU\" as a Claude Code skill from https://github.com/opendatalab/MinerU. 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: Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"opendatalab-mineru\",\"task\":\"Install MinerU\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"MinerU\" from https://github.com/opendatalab/MinerU 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: Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"opendatalab-mineru\",\"task\":\"Install MinerU\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/opendatalab/MinerU","github_repo":"opendatalab/MinerU","version":"1.0.0","license":"Unknown","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"opendatalab/mineru","recommendation_reasons":["Matches task terms: like","Strong GitHub adoption: 67,913 stars","Quality score 74/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/opendatalab-mineru","api":"https://www.openagentskill.com/api/agent/skills/opendatalab-mineru","install_api":"https://www.openagentskill.com/api/skills/opendatalab-mineru/install","audit":"https://www.openagentskill.com/skills/opendatalab-mineru/audit","repository":"https://github.com/opendatalab/MinerU"}},{"rank":8,"match_type":"related","match_score":12,"raw_match_score":99.5,"semantic_relevance":30,"slug":"shareai-lab-learn-claude-code","name":"Learn Claude Code","description":"Bash is all you need -  A nano claude code–like 「agent harness」, built from 0 to 1","tagline":"Bash is all you need -  A nano claude code–like 「agent harness」, built from 0 to 1","category":"agent-frameworks","tags":["agents","ai-agent","agent","agent-development","claude","claude-code","educational","llm","python","teaching"],"author":{"name":"shareAI-lab","verified":true,"url":"https://github.com/shareAI-lab"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"shareAI-lab/learn-claude-code","creatorName":"shareAI-lab","creatorUrl":"https://github.com/shareAI-lab","sourceUrl":"https://github.com/shareAI-lab/learn-claude-code","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/shareai-lab-learn-claude-code#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":67517,"forks":10967,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":74.01},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"68K","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":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":"68K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"68K stars, 11K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"command execution surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add shareAI-lab/learn-claude-code"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":76,"weight":0.07,"status":"info","detail":"shell or command execution"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/shareAI-lab/learn-claude-code"},{"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":"68K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"68K stars, 11K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface"},{"status":"pass","label":"Install availability","detail":"npx skills add shareAI-lab/learn-claude-code"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"shell or command execution"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/shareAI-lab/learn-claude-code"},{"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":"68K GitHub stars","repoActivity":"68K stars, 11K forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/shareAI-lab/learn-claude-code","install":"npx skills add shareAI-lab/learn-claude-code","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add shareAI-lab/learn-claude-code","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Python","AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["agent-frameworks","agents","ai-agent","agent","agent-development","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":66,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["High-risk permission hints: Shell or command execution","66/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"shell","label":"Shell or command execution","reason":"Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.","severity":"high"},{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["High-risk permission hints: Shell or command execution","Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["High-risk permission hints: Shell or command execution","66/100 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":"education-tutoring","title":"Education and tutoring"},{"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 shareAI-lab/learn-claude-code","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":67517,"starsLabel":"68K","forks":10967,"license":"MIT","qualityScore":100,"trustScore":87,"auditScore":90},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":69,"lastPushedAt":"2026-06-15T16:16:14+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Coding","Coding agents","agent-frameworks","agents","ai-agent","agent","agent-development","claude"]},"audit":{"audit_score":90,"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 Education and tutoring","role":"Primary pick","primary_fit":"Education and tutoring","best_for":["Education and tutoring 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 Education and tutoring 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":"shareai-lab-learn-claude-code","name":"Learn Claude Code","description":"Bash is all you need -  A nano claude code–like 「agent harness」, built from 0 to 1","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/shareai-lab-learn-claude-code","repository":"https://github.com/shareAI-lab/learn-claude-code","github_repo":"shareAI-lab/learn-claude-code"},"suited_tasks":["Education and tutoring workflows","Claude Code teams","teams that value GitHub adoption signals","Break down concepts","Create practice material","Adapt explanations to the learner","Inspect source files","Explain architecture"],"suited_agents":["Python","AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add shareAI-lab/learn-claude-code","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install shareai-lab-learn-claude-code"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Learn Claude Code\" agent skill from https://github.com/shareAI-lab/learn-claude-code. 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: Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"shareai-lab-learn-claude-code\",\"task\":\"Install Learn Claude Code\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Learn Claude Code\" as a Claude Code skill from https://github.com/shareAI-lab/learn-claude-code. 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: Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"shareai-lab-learn-claude-code\",\"task\":\"Install Learn Claude Code\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Learn Claude Code\" from https://github.com/shareAI-lab/learn-claude-code 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: Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"shareai-lab-learn-claude-code\",\"task\":\"Install Learn Claude Code\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/shareai-lab-learn-claude-code/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/shareai-lab-learn-claude-code"},"trust":{"score":87,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"68K GitHub stars","repoActivity":"68K stars, 11K forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/shareAI-lab/learn-claude-code","install":"npx skills add shareAI-lab/learn-claude-code","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["agent-frameworks","agents","ai-agent","agent","agent-development","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":90,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Learn Claude Code in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 87/100 Production candidate","Audit: 90/100 Safe to try","Safety: 66/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"shareai-lab-learn-claude-code (Learn Claude Code)","install_command":"npx skills add shareAI-lab/learn-claude-code","risk_summary":"Safe to try; Reviewed with permission notes; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"shareai-lab-learn-claude-code","task":"Use Learn Claude Code 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/shareai-lab-learn-claude-code","api":"https://www.openagentskill.com/api/agent/skills/shareai-lab-learn-claude-code","audit":"https://www.openagentskill.com/skills/shareai-lab-learn-claude-code/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=shareai-lab-learn-claude-code&task=Use%20Learn%20Claude%20Code%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Learn%20Claude%20Code%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Learn%20Claude%20Code%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/shareai-lab-learn-claude-code/install","manifest":"https://www.openagentskill.com/api/registry/manifest/shareai-lab-learn-claude-code"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"shareai-lab-learn-claude-code","name":"Learn Claude Code","description":"Bash is all you need -  A nano claude code–like 「agent harness」, built from 0 to 1","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/shareai-lab-learn-claude-code","repository":"https://github.com/shareAI-lab/learn-claude-code","github_repo":"shareAI-lab/learn-claude-code"},"suited_tasks":["Education and tutoring workflows","Claude Code teams","teams that value GitHub adoption signals","Break down concepts","Create practice material","Adapt explanations to the learner","Inspect source files","Explain architecture"],"suited_agents":["Python","AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add shareAI-lab/learn-claude-code","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install shareai-lab-learn-claude-code"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Learn Claude Code\" agent skill from https://github.com/shareAI-lab/learn-claude-code. 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: Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"shareai-lab-learn-claude-code\",\"task\":\"Install Learn Claude Code\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Learn Claude Code\" as a Claude Code skill from https://github.com/shareAI-lab/learn-claude-code. 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: Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"shareai-lab-learn-claude-code\",\"task\":\"Install Learn Claude Code\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Learn Claude Code\" from https://github.com/shareAI-lab/learn-claude-code 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: Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"shareai-lab-learn-claude-code\",\"task\":\"Install Learn Claude Code\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/shareai-lab-learn-claude-code/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/shareai-lab-learn-claude-code"},"trust":{"score":87,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"68K GitHub stars","repoActivity":"68K stars, 11K forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/shareAI-lab/learn-claude-code","install":"npx skills add shareAI-lab/learn-claude-code","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["agent-frameworks","agents","ai-agent","agent","agent-development","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":90,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Learn Claude Code in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 87/100 Production candidate","Audit: 90/100 Safe to try","Safety: 66/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"shareai-lab-learn-claude-code (Learn Claude Code)","install_command":"npx skills add shareAI-lab/learn-claude-code","risk_summary":"Safe to try; Reviewed with permission notes; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"shareai-lab-learn-claude-code","task":"Use Learn Claude Code 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/shareai-lab-learn-claude-code","api":"https://www.openagentskill.com/api/agent/skills/shareai-lab-learn-claude-code","audit":"https://www.openagentskill.com/skills/shareai-lab-learn-claude-code/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=shareai-lab-learn-claude-code&task=Use%20Learn%20Claude%20Code%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Learn%20Claude%20Code%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Learn%20Claude%20Code%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/shareai-lab-learn-claude-code/install","manifest":"https://www.openagentskill.com/api/registry/manifest/shareai-lab-learn-claude-code"}},"platforms":["Python","AI Agents","Claude Code"],"use_cases":[{"slug":"education-tutoring","title":"Education and tutoring","url":"https://www.openagentskill.com/use-cases/education-tutoring"},{"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":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"}],"install":"npx skills add shareAI-lab/learn-claude-code","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install shareai-lab-learn-claude-code","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Learn Claude Code\" agent skill from https://github.com/shareAI-lab/learn-claude-code. 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: Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"shareai-lab-learn-claude-code\",\"task\":\"Install Learn Claude Code\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Learn Claude Code\" as a Claude Code skill from https://github.com/shareAI-lab/learn-claude-code. 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: Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"shareai-lab-learn-claude-code\",\"task\":\"Install Learn Claude Code\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Learn Claude Code\" from https://github.com/shareAI-lab/learn-claude-code 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: Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"shareai-lab-learn-claude-code\",\"task\":\"Install Learn Claude Code\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/shareAI-lab/learn-claude-code","github_repo":"shareAI-lab/learn-claude-code","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"shareai-lab/learn-claude-code","recommendation_reasons":["Matches task terms: like","Strong GitHub adoption: 67,517 stars","Quality score 74/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/shareai-lab-learn-claude-code","api":"https://www.openagentskill.com/api/agent/skills/shareai-lab-learn-claude-code","install_api":"https://www.openagentskill.com/api/skills/shareai-lab-learn-claude-code/install","audit":"https://www.openagentskill.com/skills/shareai-lab-learn-claude-code/audit","repository":"https://github.com/shareAI-lab/learn-claude-code"}},{"rank":9,"match_type":"related","match_score":12,"raw_match_score":99.5,"semantic_relevance":30,"slug":"unslothai-unsloth","name":"Unsloth","description":"Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.","tagline":"Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.","category":"media-automation","tags":["text-to-speech","voice","ml-media","agent","deepseek","fine-tuning","gemma","gemma3","gpt-oss","llama"],"author":{"name":"unslothai","verified":true,"url":"https://github.com/unslothai"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"unslothai/unsloth","creatorName":"unslothai","creatorUrl":"https://github.com/unslothai","sourceUrl":"https://github.com/unslothai/unsloth","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/unslothai-unsloth#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":66978,"forks":6015,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":73.98},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"67K","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":90,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"67K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"67K stars, 6.0K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add unslothai/unsloth"},{"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/unslothai/unsloth"},{"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":"67K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"67K stars, 6.0K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add unslothai/unsloth"},{"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/unslothai/unsloth"},{"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":"67K GitHub stars","repoActivity":"67K stars, 6.0K forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/unslothai/unsloth","install":"npx skills add unslothai/unsloth","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 unslothai/unsloth","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Python","Voice","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["media-automation","text-to-speech","voice","ml-media","agent","deepseek"],"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":80,"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","80/100 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","80/100 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":"browser-automation","title":"Browser automation"},{"slug":"local-desktop","title":"Local desktop"},{"slug":"workflow-automation","title":"Workflow automation"}]},"applicableAgents":["OpenAI Agents","CLI","Codex","Claude Code","Cursor"],"install":{"ready":true,"command":"npx skills add unslothai/unsloth","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":66978,"starsLabel":"67K","forks":6015,"license":"Apache-2.0","qualityScore":100,"trustScore":90,"auditScore":92},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":64,"lastPushedAt":"2026-06-20T14:58:53+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Design","Multimodal media","media-automation","text-to-speech","voice","ml-media","agent","deepseek"]},"audit":{"audit_score":92,"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 Browser automation","role":"Primary pick","primary_fit":"Browser automation","best_for":["Browser automation workflows","OpenAI Agents teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Browser automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"unslothai-unsloth","name":"Unsloth","description":"Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.","category":"media-automation","url":"https://www.openagentskill.com/skills/unslothai-unsloth","repository":"https://github.com/unslothai/unsloth","github_repo":"unslothai/unsloth"},"suited_tasks":["Browser automation workflows","OpenAI Agents teams","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Navigate local resources","Run repeatable desktop actions"],"suited_agents":["Python","Voice","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add unslothai/unsloth","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install unslothai-unsloth"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Unsloth\" agent skill from https://github.com/unslothai/unsloth. 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: Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"unslothai-unsloth\",\"task\":\"Install Unsloth\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Unsloth\" as a Claude Code skill from https://github.com/unslothai/unsloth. 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: Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"unslothai-unsloth\",\"task\":\"Install Unsloth\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Unsloth\" from https://github.com/unslothai/unsloth 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: Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"unslothai-unsloth\",\"task\":\"Install Unsloth\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/unslothai-unsloth/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/unslothai-unsloth"},"trust":{"score":90,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"67K GitHub stars","repoActivity":"67K stars, 6.0K forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/unslothai/unsloth","install":"npx skills add unslothai/unsloth","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":["media-automation","text-to-speech","voice","ml-media","agent","deepseek"],"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":92,"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":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Unsloth 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: 90/100 Production candidate","Audit: 92/100 Safe to try","Safety: 80/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"unslothai-unsloth (Unsloth)","install_command":"npx skills add unslothai/unsloth","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":"unslothai-unsloth","task":"Use Unsloth 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/unslothai-unsloth","api":"https://www.openagentskill.com/api/agent/skills/unslothai-unsloth","audit":"https://www.openagentskill.com/skills/unslothai-unsloth/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=unslothai-unsloth&task=Use%20Unsloth%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Unsloth%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Unsloth%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/unslothai-unsloth/install","manifest":"https://www.openagentskill.com/api/registry/manifest/unslothai-unsloth"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"unslothai-unsloth","name":"Unsloth","description":"Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.","category":"media-automation","url":"https://www.openagentskill.com/skills/unslothai-unsloth","repository":"https://github.com/unslothai/unsloth","github_repo":"unslothai/unsloth"},"suited_tasks":["Browser automation workflows","OpenAI Agents teams","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Navigate local resources","Run repeatable desktop actions"],"suited_agents":["Python","Voice","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add unslothai/unsloth","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install unslothai-unsloth"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Unsloth\" agent skill from https://github.com/unslothai/unsloth. 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: Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"unslothai-unsloth\",\"task\":\"Install Unsloth\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Unsloth\" as a Claude Code skill from https://github.com/unslothai/unsloth. 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: Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"unslothai-unsloth\",\"task\":\"Install Unsloth\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Unsloth\" from https://github.com/unslothai/unsloth 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: Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"unslothai-unsloth\",\"task\":\"Install Unsloth\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/unslothai-unsloth/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/unslothai-unsloth"},"trust":{"score":90,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"67K GitHub stars","repoActivity":"67K stars, 6.0K forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/unslothai/unsloth","install":"npx skills add unslothai/unsloth","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":["media-automation","text-to-speech","voice","ml-media","agent","deepseek"],"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":92,"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":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Unsloth 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: 90/100 Production candidate","Audit: 92/100 Safe to try","Safety: 80/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"unslothai-unsloth (Unsloth)","install_command":"npx skills add unslothai/unsloth","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":"unslothai-unsloth","task":"Use Unsloth 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/unslothai-unsloth","api":"https://www.openagentskill.com/api/agent/skills/unslothai-unsloth","audit":"https://www.openagentskill.com/skills/unslothai-unsloth/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=unslothai-unsloth&task=Use%20Unsloth%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Unsloth%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Unsloth%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/unslothai-unsloth/install","manifest":"https://www.openagentskill.com/api/registry/manifest/unslothai-unsloth"}},"platforms":["Python","Voice","OpenAI Agents"],"use_cases":[{"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"},{"slug":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"}],"install":"npx skills add unslothai/unsloth","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install unslothai-unsloth","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Unsloth\" agent skill from https://github.com/unslothai/unsloth. 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: Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"unslothai-unsloth\",\"task\":\"Install Unsloth\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Unsloth\" as a Claude Code skill from https://github.com/unslothai/unsloth. 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: Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"unslothai-unsloth\",\"task\":\"Install Unsloth\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Unsloth\" from https://github.com/unslothai/unsloth 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: Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"unslothai-unsloth\",\"task\":\"Install Unsloth\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/unslothai/unsloth","github_repo":"unslothai/unsloth","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"unslothai/unsloth","recommendation_reasons":["Matches task terms: like","Strong GitHub adoption: 66,978 stars","Quality score 74/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/unslothai-unsloth","api":"https://www.openagentskill.com/api/agent/skills/unslothai-unsloth","install_api":"https://www.openagentskill.com/api/skills/unslothai-unsloth/install","audit":"https://www.openagentskill.com/skills/unslothai-unsloth/audit","repository":"https://github.com/unslothai/unsloth"}},{"rank":10,"match_type":"related","match_score":12,"raw_match_score":99.5,"semantic_relevance":30,"slug":"openinterpreter-openinterpreter","name":"Openinterpreter","description":"A lightweight coding agent for open models like Deepseek, Kimi, and Qwen","tagline":"A lightweight coding agent for open models like Deepseek, Kimi, and Qwen","category":"coding-agents","tags":["coding-agent","developer-tools","coding","deepseek","interpreter","kimi","qwen","rust","tui","github"],"author":{"name":"openinterpreter","verified":true,"url":"https://github.com/openinterpreter"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"openinterpreter/openinterpreter","creatorName":"openinterpreter","creatorUrl":"https://github.com/openinterpreter","sourceUrl":"https://github.com/openinterpreter/openinterpreter","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/openinterpreter-openinterpreter#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":63993,"forks":5553,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":73.84},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"64K","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":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":"64K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"64K stars, 5.6K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add openinterpreter/openinterpreter"},{"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/openinterpreter/openinterpreter"},{"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":"64K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"64K stars, 5.6K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add openinterpreter/openinterpreter"},{"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/openinterpreter/openinterpreter"},{"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":"64K GitHub stars","repoActivity":"64K stars, 5.6K forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/openinterpreter/openinterpreter","install":"npx skills add openinterpreter/openinterpreter","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add openinterpreter/openinterpreter","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Rust","Coding Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["coding-agents","coding-agent","developer-tools","coding","deepseek","interpreter"],"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":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"}],"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":"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":"github-automation","title":"GitHub automation"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Rust"],"install":{"ready":true,"command":"npx skills add openinterpreter/openinterpreter","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":63993,"starsLabel":"64K","forks":5553,"license":"Apache-2.0","qualityScore":100,"trustScore":88,"auditScore":91},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":68,"lastPushedAt":"2026-06-15T22:39:23+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","coding-agents","coding-agent","developer-tools","deepseek","interpreter","kimi"]},"audit":{"audit_score":91,"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 Coding agents","role":"Primary pick","primary_fit":"Coding agents","best_for":["Coding agents workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one 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":"openinterpreter-openinterpreter","name":"Openinterpreter","description":"A lightweight coding agent for open models like Deepseek, Kimi, and Qwen","category":"coding-agents","url":"https://www.openagentskill.com/skills/openinterpreter-openinterpreter","repository":"https://github.com/openinterpreter/openinterpreter","github_repo":"openinterpreter/openinterpreter"},"suited_tasks":["Coding agents workflows","general agent builders","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Inspect repository metadata","Compare code changes"],"suited_agents":["Rust","Coding Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add openinterpreter/openinterpreter","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install openinterpreter-openinterpreter"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Openinterpreter\" agent skill from https://github.com/openinterpreter/openinterpreter. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A lightweight coding agent for open models like Deepseek, Kimi, and Qwen After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"openinterpreter-openinterpreter\",\"task\":\"Install Openinterpreter\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Openinterpreter\" as a Claude Code skill from https://github.com/openinterpreter/openinterpreter. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A lightweight coding agent for open models like Deepseek, Kimi, and Qwen After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"openinterpreter-openinterpreter\",\"task\":\"Install Openinterpreter\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Openinterpreter\" from https://github.com/openinterpreter/openinterpreter into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A lightweight coding agent for open models like Deepseek, Kimi, and Qwen After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"openinterpreter-openinterpreter\",\"task\":\"Install Openinterpreter\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/openinterpreter-openinterpreter/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/openinterpreter-openinterpreter"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"64K GitHub stars","repoActivity":"64K stars, 5.6K forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/openinterpreter/openinterpreter","install":"npx skills add openinterpreter/openinterpreter","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["coding-agents","coding-agent","developer-tools","coding","deepseek","interpreter"],"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":91,"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":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Openinterpreter 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: 91/100 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":"openinterpreter-openinterpreter (Openinterpreter)","install_command":"npx skills add openinterpreter/openinterpreter","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":"openinterpreter-openinterpreter","task":"Use Openinterpreter 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/openinterpreter-openinterpreter","api":"https://www.openagentskill.com/api/agent/skills/openinterpreter-openinterpreter","audit":"https://www.openagentskill.com/skills/openinterpreter-openinterpreter/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=openinterpreter-openinterpreter&task=Use%20Openinterpreter%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Openinterpreter%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Openinterpreter%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/openinterpreter-openinterpreter/install","manifest":"https://www.openagentskill.com/api/registry/manifest/openinterpreter-openinterpreter"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"openinterpreter-openinterpreter","name":"Openinterpreter","description":"A lightweight coding agent for open models like Deepseek, Kimi, and Qwen","category":"coding-agents","url":"https://www.openagentskill.com/skills/openinterpreter-openinterpreter","repository":"https://github.com/openinterpreter/openinterpreter","github_repo":"openinterpreter/openinterpreter"},"suited_tasks":["Coding agents workflows","general agent builders","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Inspect repository metadata","Compare code changes"],"suited_agents":["Rust","Coding Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add openinterpreter/openinterpreter","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install openinterpreter-openinterpreter"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Openinterpreter\" agent skill from https://github.com/openinterpreter/openinterpreter. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A lightweight coding agent for open models like Deepseek, Kimi, and Qwen After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"openinterpreter-openinterpreter\",\"task\":\"Install Openinterpreter\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Openinterpreter\" as a Claude Code skill from https://github.com/openinterpreter/openinterpreter. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A lightweight coding agent for open models like Deepseek, Kimi, and Qwen After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"openinterpreter-openinterpreter\",\"task\":\"Install Openinterpreter\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Openinterpreter\" from https://github.com/openinterpreter/openinterpreter into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A lightweight coding agent for open models like Deepseek, Kimi, and Qwen After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"openinterpreter-openinterpreter\",\"task\":\"Install Openinterpreter\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/openinterpreter-openinterpreter/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/openinterpreter-openinterpreter"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"64K GitHub stars","repoActivity":"64K stars, 5.6K forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/openinterpreter/openinterpreter","install":"npx skills add openinterpreter/openinterpreter","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["coding-agents","coding-agent","developer-tools","coding","deepseek","interpreter"],"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":91,"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":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Openinterpreter 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: 91/100 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":"openinterpreter-openinterpreter (Openinterpreter)","install_command":"npx skills add openinterpreter/openinterpreter","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":"openinterpreter-openinterpreter","task":"Use Openinterpreter 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/openinterpreter-openinterpreter","api":"https://www.openagentskill.com/api/agent/skills/openinterpreter-openinterpreter","audit":"https://www.openagentskill.com/skills/openinterpreter-openinterpreter/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=openinterpreter-openinterpreter&task=Use%20Openinterpreter%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Openinterpreter%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Openinterpreter%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/openinterpreter-openinterpreter/install","manifest":"https://www.openagentskill.com/api/registry/manifest/openinterpreter-openinterpreter"}},"platforms":["Rust","Coding Agent"],"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"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"}],"install":"npx skills add openinterpreter/openinterpreter","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install openinterpreter-openinterpreter","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Openinterpreter\" agent skill from https://github.com/openinterpreter/openinterpreter. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A lightweight coding agent for open models like Deepseek, Kimi, and Qwen After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"openinterpreter-openinterpreter\",\"task\":\"Install Openinterpreter\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Openinterpreter\" as a Claude Code skill from https://github.com/openinterpreter/openinterpreter. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A lightweight coding agent for open models like Deepseek, Kimi, and Qwen After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"openinterpreter-openinterpreter\",\"task\":\"Install Openinterpreter\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Openinterpreter\" from https://github.com/openinterpreter/openinterpreter into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A lightweight coding agent for open models like Deepseek, Kimi, and Qwen After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"openinterpreter-openinterpreter\",\"task\":\"Install Openinterpreter\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/openinterpreter/openinterpreter","github_repo":"openinterpreter/openinterpreter","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"openinterpreter/openinterpreter","recommendation_reasons":["Matches task terms: like","Strong GitHub adoption: 63,993 stars","Quality score 74/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/openinterpreter-openinterpreter","api":"https://www.openagentskill.com/api/agent/skills/openinterpreter-openinterpreter","install_api":"https://www.openagentskill.com/api/skills/openinterpreter-openinterpreter/install","audit":"https://www.openagentskill.com/skills/openinterpreter-openinterpreter/audit","repository":"https://github.com/openinterpreter/openinterpreter"}}],"meta":{"endpoint":"/api/skills/search","canonical_agent_endpoint":"/api/agent/resolve","lookup_intent":false,"exact_match_found":true,"match_counts":{"exact":1,"near":0,"related":9},"no_match_message":null,"safety_policy":"Blocked candidates are excluded by default. Pass include_blocked=true only for manual audit workflows.","agent_friendly":true,"api_version":"1.0","generated_at":"2026-08-23T16:55:19.811Z"}}