{"query":"Large Language Model Notebooks Course","filters":{"category":null,"platform":null,"track":null,"safety":null,"include_blocked":false,"min_stars":0},"total":10,"skills":[{"rank":1,"match_score":99,"raw_match_score":282.6,"slug":"mlabonne-llm-course","name":"Llm Course","description":"Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.","tagline":"Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.","category":"ml-automation","tags":["machine-learning","automation","ml-media","course","large-language-models","llm","roadmap","github"],"author":{"name":"mlabonne","verified":true,"url":"https://github.com/mlabonne"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"mlabonne/llm-course","creatorName":"mlabonne","creatorUrl":"https://github.com/mlabonne","sourceUrl":"https://github.com/mlabonne/llm-course","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/mlabonne-llm-course#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":80175,"forks":9340,"downloads":0,"rating":0,"review_count":0,"quality_score":70.53},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"80K","tone":"positive"},{"label":"Freshness","value":"6mo 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":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":"80K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"80K stars, 9.3K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"6mo 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 mlabonne/llm-course"},{"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/mlabonne/llm-course"},{"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":"80K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"80K stars, 9.3K forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"6mo 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 mlabonne/llm-course"},{"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/mlabonne/llm-course"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin"],"evidence":{"stars":"80K GitHub stars","repoActivity":"80K stars, 9.3K forks","lastPushed":"6mo since push","license":"Apache-2.0","repository":"https://github.com/mlabonne/llm-course","install":"npx skills add mlabonne/llm-course","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 mlabonne/llm-course","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","6mo since push"]},"agentCompatibility":["Machine Learning","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":["ml-automation","machine-learning","automation","ml-media","course","large-language-models"],"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":78,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","78/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","78/100 agent safety score"]},"supply_profile":{"track":{"slug":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Multimodal media","description":"I need my agent to process images, video, or audio and extract useful information.","useCases":[{"slug":"github-automation","title":"GitHub automation"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Machine Learning"],"install":{"ready":true,"command":"npx skills add mlabonne/llm-course","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":80175,"starsLabel":"80K","forks":9340,"license":"Apache-2.0","qualityScore":100,"trustScore":89,"auditScore":90},"maintenance":{"status":"active","label":"6mo since push","daysSincePush":169,"lastPushedAt":"2026-02-05T13:09:26+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Design","Multimodal media","ml-automation","machine-learning","automation","ml-media","course","large-language-models"]},"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 GitHub automation","role":"Primary pick","primary_fit":"GitHub automation","best_for":["GitHub 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 GitHub automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"mlabonne-llm-course","name":"Llm Course","description":"Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.","category":"ml-automation","url":"https://www.openagentskill.com/skills/mlabonne-llm-course","repository":"https://github.com/mlabonne/llm-course","github_repo":"mlabonne/llm-course"},"suited_tasks":["GitHub automation workflows","general agent builders","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add mlabonne/llm-course","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add mlabonne/llm-course"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Llm Course\" agent skill from https://github.com/mlabonne/llm-course. 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: Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Llm Course\" as a Claude Code skill from https://github.com/mlabonne/llm-course. 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: Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Llm Course\" from https://github.com/mlabonne/llm-course 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: Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks."}],"handoff_url":"https://www.openagentskill.com/api/skills/mlabonne-llm-course/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/mlabonne-llm-course"},"trust":{"score":89,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"80K GitHub stars","repoActivity":"80K stars, 9.3K forks","lastPushed":"6mo since push","license":"Apache-2.0","repository":"https://github.com/mlabonne/llm-course","install":"npx skills add mlabonne/llm-course","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":["ml-automation","machine-learning","automation","ml-media","course","large-language-models"],"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","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":"6mo 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 Llm Course 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: 90/100 Safe to try","Safety: 78/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"mlabonne-llm-course (Llm Course)","install_command":"npx skills add mlabonne/llm-course","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":"mlabonne-llm-course","task":"Use Llm Course 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/mlabonne-llm-course","api":"https://www.openagentskill.com/api/agent/skills/mlabonne-llm-course","audit":"https://www.openagentskill.com/skills/mlabonne-llm-course/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=mlabonne-llm-course&task=Use%20Llm%20Course%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Llm%20Course%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Llm%20Course%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/mlabonne-llm-course/install","manifest":"https://www.openagentskill.com/api/registry/manifest/mlabonne-llm-course"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"mlabonne-llm-course","name":"Llm Course","description":"Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.","category":"ml-automation","url":"https://www.openagentskill.com/skills/mlabonne-llm-course","repository":"https://github.com/mlabonne/llm-course","github_repo":"mlabonne/llm-course"},"suited_tasks":["GitHub automation workflows","general agent builders","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add mlabonne/llm-course","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add mlabonne/llm-course"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Llm Course\" agent skill from https://github.com/mlabonne/llm-course. 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: Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Llm Course\" as a Claude Code skill from https://github.com/mlabonne/llm-course. 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: Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Llm Course\" from https://github.com/mlabonne/llm-course 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: Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks."}],"handoff_url":"https://www.openagentskill.com/api/skills/mlabonne-llm-course/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/mlabonne-llm-course"},"trust":{"score":89,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"80K GitHub stars","repoActivity":"80K stars, 9.3K forks","lastPushed":"6mo since push","license":"Apache-2.0","repository":"https://github.com/mlabonne/llm-course","install":"npx skills add mlabonne/llm-course","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":["ml-automation","machine-learning","automation","ml-media","course","large-language-models"],"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","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":"6mo 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 Llm Course 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: 90/100 Safe to try","Safety: 78/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"mlabonne-llm-course (Llm Course)","install_command":"npx skills add mlabonne/llm-course","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":"mlabonne-llm-course","task":"Use Llm Course 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/mlabonne-llm-course","api":"https://www.openagentskill.com/api/agent/skills/mlabonne-llm-course","audit":"https://www.openagentskill.com/skills/mlabonne-llm-course/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=mlabonne-llm-course&task=Use%20Llm%20Course%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Llm%20Course%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Llm%20Course%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/mlabonne-llm-course/install","manifest":"https://www.openagentskill.com/api/registry/manifest/mlabonne-llm-course"}},"platforms":["Machine Learning"],"use_cases":[{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"install":"npx skills add mlabonne/llm-course","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add mlabonne/llm-course","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Llm Course\" agent skill from https://github.com/mlabonne/llm-course. 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: Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.","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 \"Llm Course\" as a Claude Code skill from https://github.com/mlabonne/llm-course. 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: Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.","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 \"Llm Course\" from https://github.com/mlabonne/llm-course 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: Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/mlabonne/llm-course","github_repo":"mlabonne/llm-course","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-06-16T10:02:50.97734+00:00","canonical_key":"mlabonne/llm-course","recommendation_reasons":["Matches task terms: large, language, model, notebooks","Strong GitHub adoption: 80,175 stars","Quality score 71/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/mlabonne-llm-course","api":"https://www.openagentskill.com/api/agent/skills/mlabonne-llm-course","install_api":"https://www.openagentskill.com/api/skills/mlabonne-llm-course/install","audit":"https://www.openagentskill.com/skills/mlabonne-llm-course/audit","repository":"https://github.com/mlabonne/llm-course"}},{"rank":2,"match_score":66,"raw_match_score":187.9,"slug":"ray-project-ray","name":"Ray","description":"Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.","tagline":"Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.","category":"ml-automation","tags":["machine-learning","automation","ml-media","data-science","deep-learning","deployment","distributed","hyperparameter-optimization","hyperparameter-search","large-language-models"],"author":{"name":"ray-project","verified":true,"url":"https://github.com/ray-project"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"ray-project/ray","creatorName":"ray-project","creatorUrl":"https://github.com/ray-project","sourceUrl":"https://github.com/ray-project/ray","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/ray-project-ray#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":42892,"forks":7690,"downloads":0,"rating":0,"review_count":0,"quality_score":75.63},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"43K","tone":"positive"},{"label":"Freshness","value":"1mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":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":"43K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"43K stars, 7.7K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"1mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":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 ray-project/ray"},{"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/ray-project/ray"},{"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":"43K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"43K stars, 7.7K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"1mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"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 ray-project/ray"},{"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/ray-project/ray"},{"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":"43K GitHub stars","repoActivity":"43K stars, 7.7K forks","lastPushed":"1mo since push","license":"Apache-2.0","repository":"https://github.com/ray-project/ray","install":"npx skills add ray-project/ray","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 ray-project/ray","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","1mo since push"]},"agentCompatibility":["Python","Machine Learning","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":["ml-automation","machine-learning","automation","ml-media","data-science","deep-learning"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"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":"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":"rag-knowledge","title":"RAG and knowledge"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"research-agents","title":"Research agents"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add ray-project/ray","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":42892,"starsLabel":"43K","forks":7690,"license":"Apache-2.0","qualityScore":100,"trustScore":90,"auditScore":92},"maintenance":{"status":"active","label":"1mo since push","daysSincePush":38,"lastPushedAt":"2026-06-16T07:57:00+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Coding","GitHub automation","ml-automation","machine-learning","automation","ml-media","data-science","deep-learning"]},"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 RAG and knowledge","role":"Primary pick","primary_fit":"RAG and knowledge","best_for":["RAG and knowledge workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one RAG and knowledge task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"ray-project-ray","name":"Ray","description":"Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.","category":"ml-automation","url":"https://www.openagentskill.com/skills/ray-project-ray","repository":"https://github.com/ray-project/ray","github_repo":"ray-project/ray"},"suited_tasks":["RAG and knowledge workflows","general agent builders","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Navigate pages","Click and type safely"],"suited_agents":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add ray-project/ray","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add ray-project/ray"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Ray\" agent skill from https://github.com/ray-project/ray. 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: Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Ray\" as a Claude Code skill from https://github.com/ray-project/ray. 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: Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Ray\" from https://github.com/ray-project/ray 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: Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads."}],"handoff_url":"https://www.openagentskill.com/api/skills/ray-project-ray/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/ray-project-ray"},"trust":{"score":90,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"43K GitHub stars","repoActivity":"43K stars, 7.7K forks","lastPushed":"1mo since push","license":"Apache-2.0","repository":"https://github.com/ray-project/ray","install":"npx skills add ray-project/ray","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":["ml-automation","machine-learning","automation","ml-media","data-science","deep-learning"],"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":"Coding and developer agents","scenario":"GitHub automation","maintenance":"1mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","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 Ray 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":"ray-project-ray (Ray)","install_command":"npx skills add ray-project/ray","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":"ray-project-ray","task":"Use Ray 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/ray-project-ray","api":"https://www.openagentskill.com/api/agent/skills/ray-project-ray","audit":"https://www.openagentskill.com/skills/ray-project-ray/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=ray-project-ray&task=Use%20Ray%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Ray%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Ray%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/ray-project-ray/install","manifest":"https://www.openagentskill.com/api/registry/manifest/ray-project-ray"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"ray-project-ray","name":"Ray","description":"Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.","category":"ml-automation","url":"https://www.openagentskill.com/skills/ray-project-ray","repository":"https://github.com/ray-project/ray","github_repo":"ray-project/ray"},"suited_tasks":["RAG and knowledge workflows","general agent builders","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Navigate pages","Click and type safely"],"suited_agents":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add ray-project/ray","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add ray-project/ray"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Ray\" agent skill from https://github.com/ray-project/ray. 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: Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Ray\" as a Claude Code skill from https://github.com/ray-project/ray. 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: Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Ray\" from https://github.com/ray-project/ray 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: Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads."}],"handoff_url":"https://www.openagentskill.com/api/skills/ray-project-ray/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/ray-project-ray"},"trust":{"score":90,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"43K GitHub stars","repoActivity":"43K stars, 7.7K forks","lastPushed":"1mo since push","license":"Apache-2.0","repository":"https://github.com/ray-project/ray","install":"npx skills add ray-project/ray","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":["ml-automation","machine-learning","automation","ml-media","data-science","deep-learning"],"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":"Coding and developer agents","scenario":"GitHub automation","maintenance":"1mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","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 Ray 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":"ray-project-ray (Ray)","install_command":"npx skills add ray-project/ray","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":"ray-project-ray","task":"Use Ray 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/ray-project-ray","api":"https://www.openagentskill.com/api/agent/skills/ray-project-ray","audit":"https://www.openagentskill.com/skills/ray-project-ray/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=ray-project-ray&task=Use%20Ray%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Ray%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Ray%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/ray-project-ray/install","manifest":"https://www.openagentskill.com/api/registry/manifest/ray-project-ray"}},"platforms":["Python","Machine Learning"],"use_cases":[{"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"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"install":"npx skills add ray-project/ray","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add ray-project/ray","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Ray\" agent skill from https://github.com/ray-project/ray. 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: Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.","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 \"Ray\" as a Claude Code skill from https://github.com/ray-project/ray. 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: Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.","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 \"Ray\" from https://github.com/ray-project/ray 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: Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/ray-project/ray","github_repo":"ray-project/ray","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-06-16T10:02:51.632079+00:00","canonical_key":"ray-project/ray","recommendation_reasons":["Matches task terms: large, language, model","Strong GitHub adoption: 42,892 stars","Quality score 76/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/ray-project-ray","api":"https://www.openagentskill.com/api/agent/skills/ray-project-ray","install_api":"https://www.openagentskill.com/api/skills/ray-project-ray/install","audit":"https://www.openagentskill.com/skills/ray-project-ray/audit","repository":"https://github.com/ray-project/ray"}},{"rank":3,"match_score":66,"raw_match_score":187.8,"slug":"hkuds-lightrag","name":"LightRAG","description":"[EMNLP2025] \"LightRAG: Simple and Fast Retrieval-Augmented Generation\"","tagline":"[EMNLP2025] \"LightRAG: Simple and Fast Retrieval-Augmented Generation\"","category":"rag-knowledge","tags":["knowledge-graph","retrieval","knowledge","genai","gpt","gpt-4","graphrag","large-language-models","llm","rag"],"author":{"name":"HKUDS","verified":true,"url":"https://github.com/HKUDS"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"HKUDS/LightRAG","creatorName":"HKUDS","creatorUrl":"https://github.com/HKUDS","sourceUrl":"https://github.com/HKUDS/LightRAG","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/hkuds-lightrag#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":36782,"forks":5188,"downloads":0,"rating":0,"review_count":0,"quality_score":75.16},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"37K","tone":"positive"},{"label":"Freshness","value":"1mo 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":"37K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"37K stars, 5.2K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"1mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"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 HKUDS/LightRAG"},{"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/HKUDS/LightRAG"},{"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":"37K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"37K stars, 5.2K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"1mo 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 HKUDS/LightRAG"},{"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/HKUDS/LightRAG"},{"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":"37K GitHub stars","repoActivity":"37K stars, 5.2K forks","lastPushed":"1mo since push","license":"MIT","repository":"https://github.com/HKUDS/LightRAG","install":"npx skills add HKUDS/LightRAG","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 HKUDS/LightRAG","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","1mo since push"]},"agentCompatibility":["Python","Knowledge Graph","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["rag-knowledge","knowledge-graph","retrieval","knowledge","genai","gpt"],"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":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"RAG and knowledge","description":"I need my agent to build a RAG workflow over documents and retrieve reliable context.","useCases":[{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"customer-support","title":"Customer support"},{"slug":"web-scraping","title":"Web scraping"}]},"applicableAgents":["OpenAI Agents","CLI","Codex","Claude Code","Cursor"],"install":{"ready":true,"command":"npx skills add HKUDS/LightRAG","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":36782,"starsLabel":"37K","forks":5188,"license":"MIT","qualityScore":100,"trustScore":88,"auditScore":91},"maintenance":{"status":"active","label":"1mo since push","daysSincePush":36,"lastPushedAt":"2026-06-18T18:05:25+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"coverageTags":["Research","RAG and knowledge","rag-knowledge","knowledge-graph","retrieval","knowledge","genai","gpt"]},"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 RAG and knowledge","role":"Primary pick","primary_fit":"RAG and knowledge","best_for":["RAG and knowledge 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 RAG and knowledge task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"hkuds-lightrag","name":"LightRAG","description":"[EMNLP2025] \"LightRAG: Simple and Fast Retrieval-Augmented Generation\"","category":"rag-knowledge","url":"https://www.openagentskill.com/skills/hkuds-lightrag","repository":"https://github.com/HKUDS/LightRAG","github_repo":"HKUDS/LightRAG"},"suited_tasks":["RAG and knowledge workflows","OpenAI Agents teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Read user messages","Find relevant knowledge"],"suited_agents":["Python","Knowledge Graph","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add HKUDS/LightRAG","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add HKUDS/LightRAG"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"LightRAG\" agent skill from https://github.com/HKUDS/LightRAG. 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: [EMNLP2025] \"LightRAG: Simple and Fast Retrieval-Augmented Generation\""},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"LightRAG\" as a Claude Code skill from https://github.com/HKUDS/LightRAG. 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: [EMNLP2025] \"LightRAG: Simple and Fast Retrieval-Augmented Generation\""},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"LightRAG\" from https://github.com/HKUDS/LightRAG 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: [EMNLP2025] \"LightRAG: Simple and Fast Retrieval-Augmented Generation\""}],"handoff_url":"https://www.openagentskill.com/api/skills/hkuds-lightrag/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/hkuds-lightrag"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"37K GitHub stars","repoActivity":"37K stars, 5.2K forks","lastPushed":"1mo since push","license":"MIT","repository":"https://github.com/HKUDS/LightRAG","install":"npx skills add HKUDS/LightRAG","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["rag-knowledge","knowledge-graph","retrieval","knowledge","genai","gpt"],"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":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"1mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","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 LightRAG 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":"hkuds-lightrag (LightRAG)","install_command":"npx skills add HKUDS/LightRAG","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":"hkuds-lightrag","task":"Use LightRAG 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/hkuds-lightrag","api":"https://www.openagentskill.com/api/agent/skills/hkuds-lightrag","audit":"https://www.openagentskill.com/skills/hkuds-lightrag/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=hkuds-lightrag&task=Use%20LightRAG%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20LightRAG%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20LightRAG%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/hkuds-lightrag/install","manifest":"https://www.openagentskill.com/api/registry/manifest/hkuds-lightrag"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"hkuds-lightrag","name":"LightRAG","description":"[EMNLP2025] \"LightRAG: Simple and Fast Retrieval-Augmented Generation\"","category":"rag-knowledge","url":"https://www.openagentskill.com/skills/hkuds-lightrag","repository":"https://github.com/HKUDS/LightRAG","github_repo":"HKUDS/LightRAG"},"suited_tasks":["RAG and knowledge workflows","OpenAI Agents teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Read user messages","Find relevant knowledge"],"suited_agents":["Python","Knowledge Graph","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add HKUDS/LightRAG","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add HKUDS/LightRAG"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"LightRAG\" agent skill from https://github.com/HKUDS/LightRAG. 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: [EMNLP2025] \"LightRAG: Simple and Fast Retrieval-Augmented Generation\""},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"LightRAG\" as a Claude Code skill from https://github.com/HKUDS/LightRAG. 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: [EMNLP2025] \"LightRAG: Simple and Fast Retrieval-Augmented Generation\""},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"LightRAG\" from https://github.com/HKUDS/LightRAG 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: [EMNLP2025] \"LightRAG: Simple and Fast Retrieval-Augmented Generation\""}],"handoff_url":"https://www.openagentskill.com/api/skills/hkuds-lightrag/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/hkuds-lightrag"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"37K GitHub stars","repoActivity":"37K stars, 5.2K forks","lastPushed":"1mo since push","license":"MIT","repository":"https://github.com/HKUDS/LightRAG","install":"npx skills add HKUDS/LightRAG","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["rag-knowledge","knowledge-graph","retrieval","knowledge","genai","gpt"],"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":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"1mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","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 LightRAG 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":"hkuds-lightrag (LightRAG)","install_command":"npx skills add HKUDS/LightRAG","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":"hkuds-lightrag","task":"Use LightRAG 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/hkuds-lightrag","api":"https://www.openagentskill.com/api/agent/skills/hkuds-lightrag","audit":"https://www.openagentskill.com/skills/hkuds-lightrag/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=hkuds-lightrag&task=Use%20LightRAG%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20LightRAG%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20LightRAG%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/hkuds-lightrag/install","manifest":"https://www.openagentskill.com/api/registry/manifest/hkuds-lightrag"}},"platforms":["Python","Knowledge Graph","OpenAI Agents"],"use_cases":[{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"customer-support","title":"Customer support","url":"https://www.openagentskill.com/use-cases/customer-support"},{"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 HKUDS/LightRAG","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add HKUDS/LightRAG","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"LightRAG\" agent skill from https://github.com/HKUDS/LightRAG. 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: [EMNLP2025] \"LightRAG: Simple and Fast Retrieval-Augmented Generation\"","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 \"LightRAG\" as a Claude Code skill from https://github.com/HKUDS/LightRAG. 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: [EMNLP2025] \"LightRAG: Simple and Fast Retrieval-Augmented Generation\"","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 \"LightRAG\" from https://github.com/HKUDS/LightRAG 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: [EMNLP2025] \"LightRAG: Simple and Fast Retrieval-Augmented Generation\"","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/HKUDS/LightRAG","github_repo":"HKUDS/LightRAG","version":"1.0.0","license":"MIT","updated_at":"2026-06-20T03:03:35.791897+00:00","canonical_key":"hkuds/lightrag","recommendation_reasons":["Matches task terms: large, language, model","Strong GitHub adoption: 36,782 stars","Quality score 75/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/hkuds-lightrag","api":"https://www.openagentskill.com/api/agent/skills/hkuds-lightrag","install_api":"https://www.openagentskill.com/api/skills/hkuds-lightrag/install","audit":"https://www.openagentskill.com/skills/hkuds-lightrag/audit","repository":"https://github.com/HKUDS/LightRAG"}},{"rank":4,"match_score":66,"raw_match_score":187.6,"slug":"langfuse-langfuse","name":"Langfuse","description":"🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23 ","tagline":"🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23 ","category":"development","tags":["llmops","developer-tools","analytics","autogen","evaluation","langchain","large-language-models","llama-index","llm","llm-evaluation"],"author":{"name":"langfuse","verified":true,"url":"https://github.com/langfuse"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"langfuse/langfuse","creatorName":"langfuse","creatorUrl":"https://github.com/langfuse","sourceUrl":"https://github.com/langfuse/langfuse","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/langfuse-langfuse#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":29437,"forks":3060,"downloads":0,"rating":0,"review_count":0,"quality_score":74.48},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"29K","tone":"positive"},{"label":"Freshness","value":"1mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","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":"29K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"29K stars, 3.1K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"1mo since push"},{"id":"license","label":"License clarity","score":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 langfuse/langfuse"},{"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/langfuse/langfuse"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"29K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"29K stars, 3.1K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"1mo 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 langfuse/langfuse"},{"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/langfuse/langfuse"},{"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":"29K GitHub stars","repoActivity":"29K stars, 3.1K forks","lastPushed":"1mo since push","license":"Unknown","repository":"https://github.com/langfuse/langfuse","install":"npx skills add langfuse/langfuse","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 langfuse/langfuse","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","1mo since push"]},"agentCompatibility":["TypeScript","LLMOps","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":["development","llmops","developer-tools","analytics","autogen","evaluation"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"safety":{"score":78,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","78/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["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","78/100 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":"data-analysis","title":"Data analysis"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["OpenAI Agents","LangChain","CLI","Codex","Claude Code"],"install":{"ready":true,"command":"npx skills add langfuse/langfuse","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":29437,"starsLabel":"29K","forks":3060,"license":"Unknown","qualityScore":100,"trustScore":87,"auditScore":90},"maintenance":{"status":"active","label":"1mo since push","daysSincePush":34,"lastPushedAt":"2026-06-20T09:29:08+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":["Coding","Coding agents","development","llmops","developer-tools","analytics","autogen","evaluation"]},"audit":{"audit_score":90,"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 Data analysis","role":"Primary pick","primary_fit":"Data analysis","best_for":["Data analysis 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 Data analysis task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"langfuse-langfuse","name":"Langfuse","description":"🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23 ","category":"development","url":"https://www.openagentskill.com/skills/langfuse-langfuse","repository":"https://github.com/langfuse/langfuse","github_repo":"langfuse/langfuse"},"suited_tasks":["Data analysis workflows","OpenAI Agents teams","teams that value GitHub adoption signals","Load tabular data","Calculate trends","Summarize findings clearly","Inspect source files","Explain architecture"],"suited_agents":["TypeScript","LLMOps","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","LangChain"],"install":{"command":"npx skills add langfuse/langfuse","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add langfuse/langfuse"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Langfuse\" agent skill from https://github.com/langfuse/langfuse. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: 🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Langfuse\" as a Claude Code skill from https://github.com/langfuse/langfuse. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: 🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Langfuse\" from https://github.com/langfuse/langfuse into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: 🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23"}],"handoff_url":"https://www.openagentskill.com/api/skills/langfuse-langfuse/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/langfuse-langfuse"},"trust":{"score":87,"label":"Production candidate","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"29K GitHub stars","repoActivity":"29K stars, 3.1K forks","lastPushed":"1mo since push","license":"Unknown","repository":"https://github.com/langfuse/langfuse","install":"npx skills add langfuse/langfuse","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["development","llmops","developer-tools","analytics","autogen","evaluation"],"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":90,"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":"Coding and developer agents","scenario":"Coding agents","maintenance":"1mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","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 Langfuse in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 87/100 Production candidate","Audit: 90/100 Safe to try","Safety: 78/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"langfuse-langfuse (Langfuse)","install_command":"npx skills add langfuse/langfuse","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":"langfuse-langfuse","task":"Use Langfuse 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/langfuse-langfuse","api":"https://www.openagentskill.com/api/agent/skills/langfuse-langfuse","audit":"https://www.openagentskill.com/skills/langfuse-langfuse/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=langfuse-langfuse&task=Use%20Langfuse%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Langfuse%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Langfuse%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/langfuse-langfuse/install","manifest":"https://www.openagentskill.com/api/registry/manifest/langfuse-langfuse"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"langfuse-langfuse","name":"Langfuse","description":"🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23 ","category":"development","url":"https://www.openagentskill.com/skills/langfuse-langfuse","repository":"https://github.com/langfuse/langfuse","github_repo":"langfuse/langfuse"},"suited_tasks":["Data analysis workflows","OpenAI Agents teams","teams that value GitHub adoption signals","Load tabular data","Calculate trends","Summarize findings clearly","Inspect source files","Explain architecture"],"suited_agents":["TypeScript","LLMOps","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","LangChain"],"install":{"command":"npx skills add langfuse/langfuse","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add langfuse/langfuse"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Langfuse\" agent skill from https://github.com/langfuse/langfuse. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: 🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Langfuse\" as a Claude Code skill from https://github.com/langfuse/langfuse. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: 🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Langfuse\" from https://github.com/langfuse/langfuse into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: 🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23"}],"handoff_url":"https://www.openagentskill.com/api/skills/langfuse-langfuse/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/langfuse-langfuse"},"trust":{"score":87,"label":"Production candidate","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"29K GitHub stars","repoActivity":"29K stars, 3.1K forks","lastPushed":"1mo since push","license":"Unknown","repository":"https://github.com/langfuse/langfuse","install":"npx skills add langfuse/langfuse","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["development","llmops","developer-tools","analytics","autogen","evaluation"],"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":90,"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":"Coding and developer agents","scenario":"Coding agents","maintenance":"1mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","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 Langfuse in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 87/100 Production candidate","Audit: 90/100 Safe to try","Safety: 78/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"langfuse-langfuse (Langfuse)","install_command":"npx skills add langfuse/langfuse","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":"langfuse-langfuse","task":"Use Langfuse 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/langfuse-langfuse","api":"https://www.openagentskill.com/api/agent/skills/langfuse-langfuse","audit":"https://www.openagentskill.com/skills/langfuse-langfuse/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=langfuse-langfuse&task=Use%20Langfuse%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Langfuse%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Langfuse%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/langfuse-langfuse/install","manifest":"https://www.openagentskill.com/api/registry/manifest/langfuse-langfuse"}},"platforms":["TypeScript","LLMOps","OpenAI Agents","LangChain"],"use_cases":[{"slug":"data-analysis","title":"Data analysis","url":"https://www.openagentskill.com/use-cases/data-analysis"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"}],"install":"npx skills add langfuse/langfuse","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add langfuse/langfuse","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Langfuse\" agent skill from https://github.com/langfuse/langfuse. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: 🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23","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 \"Langfuse\" as a Claude Code skill from https://github.com/langfuse/langfuse. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: 🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23","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 \"Langfuse\" from https://github.com/langfuse/langfuse into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: 🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/langfuse/langfuse","github_repo":"langfuse/langfuse","version":"1.0.0","license":"Unknown","updated_at":"2026-06-21T03:00:09.858058+00:00","canonical_key":"langfuse/langfuse","recommendation_reasons":["Matches task terms: large, language, model","Strong GitHub adoption: 29,437 stars","Quality score 74/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/langfuse-langfuse","api":"https://www.openagentskill.com/api/agent/skills/langfuse-langfuse","install_api":"https://www.openagentskill.com/api/skills/langfuse-langfuse/install","audit":"https://www.openagentskill.com/skills/langfuse-langfuse/audit","repository":"https://github.com/langfuse/langfuse"}},{"rank":5,"match_score":66,"raw_match_score":187.6,"slug":"scrapegraphai-scrapegraph-ai","name":"Scrapegraph AI","description":"Python scraper based on AI","tagline":"Python scraper based on AI","category":"web-automation","tags":["scraping","crawler","ai-crawler","ai-scraping","ai-search","data-extraction","firecrawl-alternative","large-language-model","llm","markdown"],"author":{"name":"ScrapeGraphAI","verified":true,"url":"https://github.com/ScrapeGraphAI"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"ScrapeGraphAI/Scrapegraph-ai","creatorName":"ScrapeGraphAI","creatorUrl":"https://github.com/ScrapeGraphAI","sourceUrl":"https://github.com/ScrapeGraphAI/Scrapegraph-ai","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/scrapegraphai-scrapegraph-ai#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":27245,"forks":2569,"downloads":0,"rating":0,"review_count":0,"quality_score":74.25},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"27K","tone":"positive"},{"label":"Freshness","value":"1mo 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":"27K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"27K stars, 2.6K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"1mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"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 ScrapeGraphAI/Scrapegraph-ai"},{"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/ScrapeGraphAI/Scrapegraph-ai"},{"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":"27K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"27K stars, 2.6K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"1mo 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 ScrapeGraphAI/Scrapegraph-ai"},{"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/ScrapeGraphAI/Scrapegraph-ai"},{"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":"27K GitHub stars","repoActivity":"27K stars, 2.6K forks","lastPushed":"1mo since push","license":"MIT","repository":"https://github.com/ScrapeGraphAI/Scrapegraph-ai","install":"npx skills add ScrapeGraphAI/Scrapegraph-ai","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 ScrapeGraphAI/Scrapegraph-ai","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","1mo since push"]},"agentCompatibility":["Python","Web Automation","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["web-automation","scraping","crawler","ai-crawler","ai-scraping","ai-search"],"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":71,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","71/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"browser","label":"Browser automation","reason":"Skill may drive a browser or interact with web pages.","severity":"medium"},{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","71/100 agent safety score"]},"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"Document processing","description":"I need my agent to read PDFs, extract tables, and turn documents into structured data.","useCases":[{"slug":"web-scraping","title":"Web scraping"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"document-processing","title":"Document processing"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add ScrapeGraphAI/Scrapegraph-ai","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":27245,"starsLabel":"27K","forks":2569,"license":"MIT","qualityScore":100,"trustScore":88,"auditScore":91},"maintenance":{"status":"active","label":"1mo since push","daysSincePush":39,"lastPushedAt":"2026-06-15T14:03:01+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"coverageTags":["Research","Document processing","web-automation","scraping","crawler","ai-crawler","ai-scraping","ai-search"]},"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 Web scraping","role":"Primary pick","primary_fit":"Web scraping","best_for":["Web scraping 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 Web scraping task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"scrapegraphai-scrapegraph-ai","name":"Scrapegraph AI","description":"Python scraper based on AI","category":"web-automation","url":"https://www.openagentskill.com/skills/scrapegraphai-scrapegraph-ai","repository":"https://github.com/ScrapeGraphAI/Scrapegraph-ai","github_repo":"ScrapeGraphAI/Scrapegraph-ai"},"suited_tasks":["Web scraping workflows","general agent builders","teams that value GitHub adoption signals","Crawl target URLs","Extract tables and metadata","Normalize messy page content","Navigate pages","Click and type safely"],"suited_agents":["Python","Web Automation","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add ScrapeGraphAI/Scrapegraph-ai","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add ScrapeGraphAI/Scrapegraph-ai"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Scrapegraph AI\" agent skill from https://github.com/ScrapeGraphAI/Scrapegraph-ai. 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: Python scraper based on AI"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Scrapegraph AI\" as a Claude Code skill from https://github.com/ScrapeGraphAI/Scrapegraph-ai. 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: Python scraper based on AI"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Scrapegraph AI\" from https://github.com/ScrapeGraphAI/Scrapegraph-ai 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: Python scraper based on AI"}],"handoff_url":"https://www.openagentskill.com/api/skills/scrapegraphai-scrapegraph-ai/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/scrapegraphai-scrapegraph-ai"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"27K GitHub stars","repoActivity":"27K stars, 2.6K forks","lastPushed":"1mo since push","license":"MIT","repository":"https://github.com/ScrapeGraphAI/Scrapegraph-ai","install":"npx skills add ScrapeGraphAI/Scrapegraph-ai","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":["web-automation","scraping","crawler","ai-crawler","ai-scraping","ai-search"],"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":"Research and knowledge work","scenario":"Document processing","maintenance":"1mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","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 Scrapegraph AI 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: 71/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"scrapegraphai-scrapegraph-ai (Scrapegraph AI)","install_command":"npx skills add ScrapeGraphAI/Scrapegraph-ai","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":"scrapegraphai-scrapegraph-ai","task":"Use Scrapegraph AI 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/scrapegraphai-scrapegraph-ai","api":"https://www.openagentskill.com/api/agent/skills/scrapegraphai-scrapegraph-ai","audit":"https://www.openagentskill.com/skills/scrapegraphai-scrapegraph-ai/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=scrapegraphai-scrapegraph-ai&task=Use%20Scrapegraph%20AI%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Scrapegraph%20AI%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Scrapegraph%20AI%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/scrapegraphai-scrapegraph-ai/install","manifest":"https://www.openagentskill.com/api/registry/manifest/scrapegraphai-scrapegraph-ai"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"scrapegraphai-scrapegraph-ai","name":"Scrapegraph AI","description":"Python scraper based on AI","category":"web-automation","url":"https://www.openagentskill.com/skills/scrapegraphai-scrapegraph-ai","repository":"https://github.com/ScrapeGraphAI/Scrapegraph-ai","github_repo":"ScrapeGraphAI/Scrapegraph-ai"},"suited_tasks":["Web scraping workflows","general agent builders","teams that value GitHub adoption signals","Crawl target URLs","Extract tables and metadata","Normalize messy page content","Navigate pages","Click and type safely"],"suited_agents":["Python","Web Automation","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add ScrapeGraphAI/Scrapegraph-ai","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add ScrapeGraphAI/Scrapegraph-ai"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Scrapegraph AI\" agent skill from https://github.com/ScrapeGraphAI/Scrapegraph-ai. 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: Python scraper based on AI"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Scrapegraph AI\" as a Claude Code skill from https://github.com/ScrapeGraphAI/Scrapegraph-ai. 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: Python scraper based on AI"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Scrapegraph AI\" from https://github.com/ScrapeGraphAI/Scrapegraph-ai 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: Python scraper based on AI"}],"handoff_url":"https://www.openagentskill.com/api/skills/scrapegraphai-scrapegraph-ai/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/scrapegraphai-scrapegraph-ai"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"27K GitHub stars","repoActivity":"27K stars, 2.6K forks","lastPushed":"1mo since push","license":"MIT","repository":"https://github.com/ScrapeGraphAI/Scrapegraph-ai","install":"npx skills add ScrapeGraphAI/Scrapegraph-ai","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":["web-automation","scraping","crawler","ai-crawler","ai-scraping","ai-search"],"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":"Research and knowledge work","scenario":"Document processing","maintenance":"1mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","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 Scrapegraph AI 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: 71/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"scrapegraphai-scrapegraph-ai (Scrapegraph AI)","install_command":"npx skills add ScrapeGraphAI/Scrapegraph-ai","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":"scrapegraphai-scrapegraph-ai","task":"Use Scrapegraph AI 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/scrapegraphai-scrapegraph-ai","api":"https://www.openagentskill.com/api/agent/skills/scrapegraphai-scrapegraph-ai","audit":"https://www.openagentskill.com/skills/scrapegraphai-scrapegraph-ai/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=scrapegraphai-scrapegraph-ai&task=Use%20Scrapegraph%20AI%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Scrapegraph%20AI%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Scrapegraph%20AI%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/scrapegraphai-scrapegraph-ai/install","manifest":"https://www.openagentskill.com/api/registry/manifest/scrapegraphai-scrapegraph-ai"}},"platforms":["Python","Web Automation"],"use_cases":[{"slug":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"document-processing","title":"Document processing","url":"https://www.openagentskill.com/use-cases/document-processing"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"}],"install":"npx skills add ScrapeGraphAI/Scrapegraph-ai","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add ScrapeGraphAI/Scrapegraph-ai","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Scrapegraph AI\" agent skill from https://github.com/ScrapeGraphAI/Scrapegraph-ai. 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: Python scraper based on AI","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 \"Scrapegraph AI\" as a Claude Code skill from https://github.com/ScrapeGraphAI/Scrapegraph-ai. 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: Python scraper based on AI","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 \"Scrapegraph AI\" from https://github.com/ScrapeGraphAI/Scrapegraph-ai 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: Python scraper based on AI","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/ScrapeGraphAI/Scrapegraph-ai","github_repo":"ScrapeGraphAI/Scrapegraph-ai","version":"1.0.0","license":"MIT","updated_at":"2026-06-16T03:00:01.281701+00:00","canonical_key":"scrapegraphai/scrapegraph-ai","recommendation_reasons":["Matches task terms: large, language, model","Strong GitHub adoption: 27,245 stars","Quality score 74/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/scrapegraphai-scrapegraph-ai","api":"https://www.openagentskill.com/api/agent/skills/scrapegraphai-scrapegraph-ai","install_api":"https://www.openagentskill.com/api/skills/scrapegraphai-scrapegraph-ai/install","audit":"https://www.openagentskill.com/skills/scrapegraphai-scrapegraph-ai/audit","repository":"https://github.com/ScrapeGraphAI/Scrapegraph-ai"}},{"rank":6,"match_score":66,"raw_match_score":187.5,"slug":"deepset-ai-haystack","name":"Haystack","description":"Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.","tagline":"Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.","category":"data","tags":["rag","retrieval","agent","agents","ai","gemini","generative-ai","gpt-4","information-retrieval","large-language-models"],"author":{"name":"deepset-ai","verified":true,"url":"https://github.com/deepset-ai"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"deepset-ai/haystack","creatorName":"deepset-ai","creatorUrl":"https://github.com/deepset-ai","sourceUrl":"https://github.com/deepset-ai/haystack","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/deepset-ai-haystack#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":25567,"forks":2854,"downloads":0,"rating":0,"review_count":0,"quality_score":74.05},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"26K","tone":"positive"},{"label":"Freshness","value":"1mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":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":"26K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"26K stars, 2.9K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"1mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":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 deepset-ai/haystack"},{"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/deepset-ai/haystack"},{"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":"26K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"26K stars, 2.9K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"1mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"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 deepset-ai/haystack"},{"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/deepset-ai/haystack"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":[],"evidence":{"stars":"26K GitHub stars","repoActivity":"26K stars, 2.9K forks","lastPushed":"1mo since push","license":"Apache-2.0","repository":"https://github.com/deepset-ai/haystack","install":"npx skills add deepset-ai/haystack","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 deepset-ai/haystack","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","1mo since push"]},"agentCompatibility":["MDX","RAG","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["No major trust warnings detected from available metadata"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["data","rag","retrieval","agent","agents","ai"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":[]},"safety":{"score":89,"level":"safe_to_install","label":"Safe to install with normal review","safety_tier":{"tier":"verified","label":"Verified","badge":"VERIFIED","summary":"Strong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","auto_install_policy":"allow","reasons":["Verified listing","Safe-to-try audit","89/100 agent safety score"]},"auto_install_allowed":true,"human_review_required":false,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":[],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"verified","label":"Verified","badge":"VERIFIED","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","reasons":["Verified listing","Safe-to-try audit","89/100 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":"RAG and knowledge","description":"I need my agent to build a RAG workflow over documents and retrieve reliable context.","useCases":[{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"research-agents","title":"Research agents"}]},"applicableAgents":["OpenAI Agents","CLI","Codex","Claude Code","Cursor"],"install":{"ready":true,"command":"npx skills add deepset-ai/haystack","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":25567,"starsLabel":"26K","forks":2854,"license":"Apache-2.0","qualityScore":100,"trustScore":90,"auditScore":93},"maintenance":{"status":"active","label":"1mo since push","daysSincePush":42,"lastPushedAt":"2026-06-12T15:45:23+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":false,"notes":["No major risk signals from available metadata"]},"coverageTags":["Research","RAG and knowledge","data","rag","retrieval","agent","agents","ai"]},"audit":{"audit_score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for RAG and knowledge","role":"Primary pick","primary_fit":"RAG and knowledge","best_for":["RAG and knowledge 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 RAG and knowledge task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"deepset-ai-haystack","name":"Haystack","description":"Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.","category":"data","url":"https://www.openagentskill.com/skills/deepset-ai-haystack","repository":"https://github.com/deepset-ai/haystack","github_repo":"deepset-ai/haystack"},"suited_tasks":["RAG and knowledge workflows","OpenAI Agents teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Navigate pages","Click and type safely"],"suited_agents":["MDX","RAG","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add deepset-ai/haystack","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add deepset-ai/haystack"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Haystack\" agent skill from https://github.com/deepset-ai/haystack. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Haystack\" as a Claude Code skill from https://github.com/deepset-ai/haystack. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Haystack\" from https://github.com/deepset-ai/haystack into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems."}],"handoff_url":"https://www.openagentskill.com/api/skills/deepset-ai-haystack/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/deepset-ai-haystack"},"trust":{"score":90,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"26K GitHub stars","repoActivity":"26K stars, 2.9K forks","lastPushed":"1mo since push","license":"Apache-2.0","repository":"https://github.com/deepset-ai/haystack","install":"npx skills add deepset-ai/haystack","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":["data","rag","retrieval","agent","agents","ai"],"known_risks":[]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety_gate":{"tier":"verified","label":"Verified","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"1mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","No major trust warnings detected from available metadata","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Haystack in an agent workflow","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","install_policy":"allow","minimum_review_before_use":["Trust: 90/100 Production candidate","Audit: 93/100 Safe to try","Safety: 89/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"deepset-ai-haystack (Haystack)","install_command":"npx skills add deepset-ai/haystack","risk_summary":"Safe to try; Verified; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"deepset-ai-haystack","task":"Use Haystack 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/deepset-ai-haystack","api":"https://www.openagentskill.com/api/agent/skills/deepset-ai-haystack","audit":"https://www.openagentskill.com/skills/deepset-ai-haystack/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=deepset-ai-haystack&task=Use%20Haystack%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Haystack%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Haystack%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/deepset-ai-haystack/install","manifest":"https://www.openagentskill.com/api/registry/manifest/deepset-ai-haystack"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"deepset-ai-haystack","name":"Haystack","description":"Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.","category":"data","url":"https://www.openagentskill.com/skills/deepset-ai-haystack","repository":"https://github.com/deepset-ai/haystack","github_repo":"deepset-ai/haystack"},"suited_tasks":["RAG and knowledge workflows","OpenAI Agents teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Navigate pages","Click and type safely"],"suited_agents":["MDX","RAG","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add deepset-ai/haystack","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add deepset-ai/haystack"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Haystack\" agent skill from https://github.com/deepset-ai/haystack. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Haystack\" as a Claude Code skill from https://github.com/deepset-ai/haystack. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Haystack\" from https://github.com/deepset-ai/haystack into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems."}],"handoff_url":"https://www.openagentskill.com/api/skills/deepset-ai-haystack/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/deepset-ai-haystack"},"trust":{"score":90,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"26K GitHub stars","repoActivity":"26K stars, 2.9K forks","lastPushed":"1mo since push","license":"Apache-2.0","repository":"https://github.com/deepset-ai/haystack","install":"npx skills add deepset-ai/haystack","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":["data","rag","retrieval","agent","agents","ai"],"known_risks":[]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety_gate":{"tier":"verified","label":"Verified","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"1mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","No major trust warnings detected from available metadata","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Haystack in an agent workflow","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","install_policy":"allow","minimum_review_before_use":["Trust: 90/100 Production candidate","Audit: 93/100 Safe to try","Safety: 89/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"deepset-ai-haystack (Haystack)","install_command":"npx skills add deepset-ai/haystack","risk_summary":"Safe to try; Verified; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"deepset-ai-haystack","task":"Use Haystack 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/deepset-ai-haystack","api":"https://www.openagentskill.com/api/agent/skills/deepset-ai-haystack","audit":"https://www.openagentskill.com/skills/deepset-ai-haystack/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=deepset-ai-haystack&task=Use%20Haystack%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Haystack%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Haystack%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/deepset-ai-haystack/install","manifest":"https://www.openagentskill.com/api/registry/manifest/deepset-ai-haystack"}},"platforms":["MDX","RAG","OpenAI Agents"],"use_cases":[{"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"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"install":"npx skills add deepset-ai/haystack","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add deepset-ai/haystack","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Haystack\" agent skill from https://github.com/deepset-ai/haystack. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.","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 \"Haystack\" as a Claude Code skill from https://github.com/deepset-ai/haystack. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.","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 \"Haystack\" from https://github.com/deepset-ai/haystack into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/deepset-ai/haystack","github_repo":"deepset-ai/haystack","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-06-15T03:01:20.572162+00:00","canonical_key":"deepset-ai/haystack","recommendation_reasons":["Matches task terms: large, language, model","Strong GitHub adoption: 25,567 stars","Quality score 74/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/deepset-ai-haystack","api":"https://www.openagentskill.com/api/agent/skills/deepset-ai-haystack","install_api":"https://www.openagentskill.com/api/skills/deepset-ai-haystack/install","audit":"https://www.openagentskill.com/skills/deepset-ai-haystack/audit","repository":"https://github.com/deepset-ai/haystack"}},{"rank":7,"match_score":66,"raw_match_score":187.5,"slug":"hkuds-deeptutor","name":"DeepTutor","description":"DeepTutor: Agent-native, Open-sourced Personalized Tutoring. https://deeptutor.info/.","tagline":"DeepTutor: Agent-native, Open-sourced Personalized Tutoring. https://deeptutor.info/.","category":"agent-frameworks","tags":["agents","ai-agents","ai-tutor","clawdbot","cli-tool","deepresearch","interactive-learning","large-language-models","multi-agent-systems","rag"],"author":{"name":"HKUDS","verified":true,"url":"https://github.com/HKUDS"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"HKUDS/DeepTutor","creatorName":"HKUDS","creatorUrl":"https://github.com/HKUDS","sourceUrl":"https://github.com/HKUDS/DeepTutor","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/hkuds-deeptutor#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":24817,"forks":3356,"downloads":0,"rating":0,"review_count":0,"quality_score":73.96},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"25K","tone":"positive"},{"label":"Freshness","value":"1mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":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":"25K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"25K stars, 3.4K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"1mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":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 HKUDS/DeepTutor"},{"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/HKUDS/DeepTutor"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"25K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"25K stars, 3.4K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"1mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"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 HKUDS/DeepTutor"},{"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/HKUDS/DeepTutor"},{"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":"25K GitHub stars","repoActivity":"25K stars, 3.4K forks","lastPushed":"1mo since push","license":"Apache-2.0","repository":"https://github.com/HKUDS/DeepTutor","install":"npx skills add HKUDS/DeepTutor","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 HKUDS/DeepTutor","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","1mo 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-agents","ai-tutor","clawdbot","cli-tool"],"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":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"Research agents","description":"I need my agent to research a topic, compare sources, and produce a concise report.","useCases":[{"slug":"research-agents","title":"Research agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"education-tutoring","title":"Education and tutoring"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add HKUDS/DeepTutor","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":24817,"starsLabel":"25K","forks":3356,"license":"Apache-2.0","qualityScore":100,"trustScore":87,"auditScore":90},"maintenance":{"status":"active","label":"1mo since push","daysSincePush":37,"lastPushedAt":"2026-06-17T16:25:11+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Research","Research agents","agent-frameworks","agents","ai-agents","ai-tutor","clawdbot","cli-tool"]},"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 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":"hkuds-deeptutor","name":"DeepTutor","description":"DeepTutor: Agent-native, Open-sourced Personalized Tutoring. https://deeptutor.info/.","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/hkuds-deeptutor","repository":"https://github.com/HKUDS/DeepTutor","github_repo":"HKUDS/DeepTutor"},"suited_tasks":["Research agents workflows","general agent builders","teams that value GitHub adoption signals","Search sources","Extract claims","Synthesize findings","Chunk documents","Create embeddings"],"suited_agents":["Python","AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add HKUDS/DeepTutor","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add HKUDS/DeepTutor"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"DeepTutor\" agent skill from https://github.com/HKUDS/DeepTutor. 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: DeepTutor: Agent-native, Open-sourced Personalized Tutoring. https://deeptutor.info/."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"DeepTutor\" as a Claude Code skill from https://github.com/HKUDS/DeepTutor. 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: DeepTutor: Agent-native, Open-sourced Personalized Tutoring. https://deeptutor.info/."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"DeepTutor\" from https://github.com/HKUDS/DeepTutor 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: DeepTutor: Agent-native, Open-sourced Personalized Tutoring. https://deeptutor.info/."}],"handoff_url":"https://www.openagentskill.com/api/skills/hkuds-deeptutor/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/hkuds-deeptutor"},"trust":{"score":87,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"25K GitHub stars","repoActivity":"25K stars, 3.4K forks","lastPushed":"1mo since push","license":"Apache-2.0","repository":"https://github.com/HKUDS/DeepTutor","install":"npx skills add HKUDS/DeepTutor","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-agents","ai-tutor","clawdbot","cli-tool"],"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":"Research and knowledge work","scenario":"Research agents","maintenance":"1mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","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 DeepTutor 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":"hkuds-deeptutor (DeepTutor)","install_command":"npx skills add HKUDS/DeepTutor","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":"hkuds-deeptutor","task":"Use DeepTutor 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/hkuds-deeptutor","api":"https://www.openagentskill.com/api/agent/skills/hkuds-deeptutor","audit":"https://www.openagentskill.com/skills/hkuds-deeptutor/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=hkuds-deeptutor&task=Use%20DeepTutor%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20DeepTutor%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20DeepTutor%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/hkuds-deeptutor/install","manifest":"https://www.openagentskill.com/api/registry/manifest/hkuds-deeptutor"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"hkuds-deeptutor","name":"DeepTutor","description":"DeepTutor: Agent-native, Open-sourced Personalized Tutoring. https://deeptutor.info/.","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/hkuds-deeptutor","repository":"https://github.com/HKUDS/DeepTutor","github_repo":"HKUDS/DeepTutor"},"suited_tasks":["Research agents workflows","general agent builders","teams that value GitHub adoption signals","Search sources","Extract claims","Synthesize findings","Chunk documents","Create embeddings"],"suited_agents":["Python","AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add HKUDS/DeepTutor","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add HKUDS/DeepTutor"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"DeepTutor\" agent skill from https://github.com/HKUDS/DeepTutor. 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: DeepTutor: Agent-native, Open-sourced Personalized Tutoring. https://deeptutor.info/."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"DeepTutor\" as a Claude Code skill from https://github.com/HKUDS/DeepTutor. 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: DeepTutor: Agent-native, Open-sourced Personalized Tutoring. https://deeptutor.info/."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"DeepTutor\" from https://github.com/HKUDS/DeepTutor 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: DeepTutor: Agent-native, Open-sourced Personalized Tutoring. https://deeptutor.info/."}],"handoff_url":"https://www.openagentskill.com/api/skills/hkuds-deeptutor/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/hkuds-deeptutor"},"trust":{"score":87,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"25K GitHub stars","repoActivity":"25K stars, 3.4K forks","lastPushed":"1mo since push","license":"Apache-2.0","repository":"https://github.com/HKUDS/DeepTutor","install":"npx skills add HKUDS/DeepTutor","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-agents","ai-tutor","clawdbot","cli-tool"],"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":"Research and knowledge work","scenario":"Research agents","maintenance":"1mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","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 DeepTutor 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":"hkuds-deeptutor (DeepTutor)","install_command":"npx skills add HKUDS/DeepTutor","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":"hkuds-deeptutor","task":"Use DeepTutor 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/hkuds-deeptutor","api":"https://www.openagentskill.com/api/agent/skills/hkuds-deeptutor","audit":"https://www.openagentskill.com/skills/hkuds-deeptutor/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=hkuds-deeptutor&task=Use%20DeepTutor%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20DeepTutor%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20DeepTutor%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/hkuds-deeptutor/install","manifest":"https://www.openagentskill.com/api/registry/manifest/hkuds-deeptutor"}},"platforms":["Python","AI Agents"],"use_cases":[{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"education-tutoring","title":"Education and tutoring","url":"https://www.openagentskill.com/use-cases/education-tutoring"},{"slug":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"}],"install":"npx skills add HKUDS/DeepTutor","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add HKUDS/DeepTutor","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"DeepTutor\" agent skill from https://github.com/HKUDS/DeepTutor. 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: DeepTutor: Agent-native, Open-sourced Personalized Tutoring. https://deeptutor.info/.","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 \"DeepTutor\" as a Claude Code skill from https://github.com/HKUDS/DeepTutor. 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: DeepTutor: Agent-native, Open-sourced Personalized Tutoring. https://deeptutor.info/.","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 \"DeepTutor\" from https://github.com/HKUDS/DeepTutor 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: DeepTutor: Agent-native, Open-sourced Personalized Tutoring. https://deeptutor.info/.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/HKUDS/DeepTutor","github_repo":"HKUDS/DeepTutor","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-06-18T03:00:09.719366+00:00","canonical_key":"hkuds/deeptutor","recommendation_reasons":["Matches task terms: large, language, model","Strong GitHub adoption: 24,817 stars","Quality score 74/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/hkuds-deeptutor","api":"https://www.openagentskill.com/api/agent/skills/hkuds-deeptutor","install_api":"https://www.openagentskill.com/api/skills/hkuds-deeptutor/install","audit":"https://www.openagentskill.com/skills/hkuds-deeptutor/audit","repository":"https://github.com/HKUDS/DeepTutor"}},{"rank":8,"match_score":65,"raw_match_score":186.9,"slug":"ai4finance-foundation-fingpt","name":"FinGPT","description":"FinGPT: Open-Source Financial Large Language Models!  Revolutionize 🔥    We release the trained model on HuggingFace.","tagline":"FinGPT: Open-Source Financial Large Language Models!  Revolutionize 🔥    We release the trained model on HuggingFace.","category":"finance","tags":["finance","analysis","chatgpt","fingpt","fintech","large-language-models","machine-learning","nlp","prompt-engineering","pytorch"],"author":{"name":"AI4Finance-Foundation","verified":true,"url":"https://github.com/AI4Finance-Foundation"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"AI4Finance-Foundation/FinGPT","creatorName":"AI4Finance-Foundation","creatorUrl":"https://github.com/AI4Finance-Foundation","sourceUrl":"https://github.com/AI4Finance-Foundation/FinGPT","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/ai4finance-foundation-fingpt#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":20704,"forks":2940,"downloads":0,"rating":0,"review_count":0,"quality_score":73.41},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"21K","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":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":"21K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"21K stars, 2.9K 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":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 AI4Finance-Foundation/FinGPT"},{"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/AI4Finance-Foundation/FinGPT"},{"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":"21K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"21K stars, 2.9K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add AI4Finance-Foundation/FinGPT"},{"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/AI4Finance-Foundation/FinGPT"},{"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":"21K GitHub stars","repoActivity":"21K stars, 2.9K forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/AI4Finance-Foundation/FinGPT","install":"npx skills add AI4Finance-Foundation/FinGPT","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 AI4Finance-Foundation/FinGPT","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":["Jupyter Notebook","Finance","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":["finance","analysis","chatgpt","fingpt","fintech","large-language-models"],"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":"finance","label":"Finance and quant workflows","shortLabel":"Finance","description":"Market data, SEC filings, portfolio analysis, quant research, backtesting, and risk workflows."},"scenario":{"label":"Finance and quant","description":"I need my agent to analyze markets, financial data, filings, portfolios, and quant strategies.","useCases":[{"slug":"research-agents","title":"Research agents"},{"slug":"finance-quant","title":"Finance and quant"},{"slug":"github-automation","title":"GitHub automation"}]},"applicableAgents":["OpenAI Agents","CLI","Codex","Claude Code","Cursor"],"install":{"ready":true,"command":"npx skills add AI4Finance-Foundation/FinGPT","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":20704,"starsLabel":"21K","forks":2940,"license":"MIT","qualityScore":100,"trustScore":90,"auditScore":92},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":53,"lastPushedAt":"2026-06-01T15:15:48+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Finance","Finance and quant","analysis","chatgpt","fingpt","fintech","large-language-models","machine-learning"]},"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","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 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":"ai4finance-foundation-fingpt","name":"FinGPT","description":"FinGPT: Open-Source Financial Large Language Models!  Revolutionize 🔥    We release the trained model on HuggingFace.","category":"finance","url":"https://www.openagentskill.com/skills/ai4finance-foundation-fingpt","repository":"https://github.com/AI4Finance-Foundation/FinGPT","github_repo":"AI4Finance-Foundation/FinGPT"},"suited_tasks":["Research agents workflows","OpenAI Agents teams","teams that value GitHub adoption signals","Search sources","Extract claims","Synthesize findings","Retrieve market data","Compare financial signals"],"suited_agents":["Jupyter Notebook","Finance","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add AI4Finance-Foundation/FinGPT","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add AI4Finance-Foundation/FinGPT"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"FinGPT\" agent skill from https://github.com/AI4Finance-Foundation/FinGPT. 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: FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"FinGPT\" as a Claude Code skill from https://github.com/AI4Finance-Foundation/FinGPT. 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: FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"FinGPT\" from https://github.com/AI4Finance-Foundation/FinGPT 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: FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace."}],"handoff_url":"https://www.openagentskill.com/api/skills/ai4finance-foundation-fingpt/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/ai4finance-foundation-fingpt"},"trust":{"score":90,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"21K GitHub stars","repoActivity":"21K stars, 2.9K forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/AI4Finance-Foundation/FinGPT","install":"npx skills add AI4Finance-Foundation/FinGPT","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":["finance","analysis","chatgpt","fingpt","fintech","large-language-models"],"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":"Finance and quant workflows","scenario":"Finance and quant","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 FinGPT 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":"ai4finance-foundation-fingpt (FinGPT)","install_command":"npx skills add AI4Finance-Foundation/FinGPT","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":"ai4finance-foundation-fingpt","task":"Use FinGPT 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/ai4finance-foundation-fingpt","api":"https://www.openagentskill.com/api/agent/skills/ai4finance-foundation-fingpt","audit":"https://www.openagentskill.com/skills/ai4finance-foundation-fingpt/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=ai4finance-foundation-fingpt&task=Use%20FinGPT%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20FinGPT%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20FinGPT%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/ai4finance-foundation-fingpt/install","manifest":"https://www.openagentskill.com/api/registry/manifest/ai4finance-foundation-fingpt"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"ai4finance-foundation-fingpt","name":"FinGPT","description":"FinGPT: Open-Source Financial Large Language Models!  Revolutionize 🔥    We release the trained model on HuggingFace.","category":"finance","url":"https://www.openagentskill.com/skills/ai4finance-foundation-fingpt","repository":"https://github.com/AI4Finance-Foundation/FinGPT","github_repo":"AI4Finance-Foundation/FinGPT"},"suited_tasks":["Research agents workflows","OpenAI Agents teams","teams that value GitHub adoption signals","Search sources","Extract claims","Synthesize findings","Retrieve market data","Compare financial signals"],"suited_agents":["Jupyter Notebook","Finance","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add AI4Finance-Foundation/FinGPT","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add AI4Finance-Foundation/FinGPT"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"FinGPT\" agent skill from https://github.com/AI4Finance-Foundation/FinGPT. 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: FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"FinGPT\" as a Claude Code skill from https://github.com/AI4Finance-Foundation/FinGPT. 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: FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"FinGPT\" from https://github.com/AI4Finance-Foundation/FinGPT 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: FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace."}],"handoff_url":"https://www.openagentskill.com/api/skills/ai4finance-foundation-fingpt/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/ai4finance-foundation-fingpt"},"trust":{"score":90,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"21K GitHub stars","repoActivity":"21K stars, 2.9K forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/AI4Finance-Foundation/FinGPT","install":"npx skills add AI4Finance-Foundation/FinGPT","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":["finance","analysis","chatgpt","fingpt","fintech","large-language-models"],"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":"Finance and quant workflows","scenario":"Finance and quant","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 FinGPT 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":"ai4finance-foundation-fingpt (FinGPT)","install_command":"npx skills add AI4Finance-Foundation/FinGPT","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":"ai4finance-foundation-fingpt","task":"Use FinGPT 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/ai4finance-foundation-fingpt","api":"https://www.openagentskill.com/api/agent/skills/ai4finance-foundation-fingpt","audit":"https://www.openagentskill.com/skills/ai4finance-foundation-fingpt/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=ai4finance-foundation-fingpt&task=Use%20FinGPT%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20FinGPT%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20FinGPT%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/ai4finance-foundation-fingpt/install","manifest":"https://www.openagentskill.com/api/registry/manifest/ai4finance-foundation-fingpt"}},"platforms":["Jupyter Notebook","Finance","OpenAI Agents"],"use_cases":[{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"finance-quant","title":"Finance and quant","url":"https://www.openagentskill.com/use-cases/finance-quant"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"data-analysis","title":"Data analysis","url":"https://www.openagentskill.com/use-cases/data-analysis"}],"install":"npx skills add AI4Finance-Foundation/FinGPT","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add AI4Finance-Foundation/FinGPT","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"FinGPT\" agent skill from https://github.com/AI4Finance-Foundation/FinGPT. 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: FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.","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 \"FinGPT\" as a Claude Code skill from https://github.com/AI4Finance-Foundation/FinGPT. 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: FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.","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 \"FinGPT\" from https://github.com/AI4Finance-Foundation/FinGPT 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: FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/AI4Finance-Foundation/FinGPT","github_repo":"AI4Finance-Foundation/FinGPT","version":"1.0.0","license":"MIT","updated_at":"2026-06-26T03:03:18.883862+00:00","canonical_key":"ai4finance-foundation/fingpt","recommendation_reasons":["Matches task terms: large, language, model","Strong GitHub adoption: 20,704 stars","Quality score 73/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/ai4finance-foundation-fingpt","api":"https://www.openagentskill.com/api/agent/skills/ai4finance-foundation-fingpt","install_api":"https://www.openagentskill.com/api/skills/ai4finance-foundation-fingpt/install","audit":"https://www.openagentskill.com/skills/ai4finance-foundation-fingpt/audit","repository":"https://github.com/AI4Finance-Foundation/FinGPT"}},{"rank":9,"match_score":65,"raw_match_score":186.5,"slug":"stas00-ml-engineering","name":"Ml Engineering","description":"Machine Learning Engineering Open Book","tagline":"Machine Learning Engineering Open Book","category":"ml-automation","tags":["machine-learning","automation","ml-media","ai","debugging","gpus","inference","large-language-models","llm","machine-learning-engineering"],"author":{"name":"stas00","verified":true,"url":"https://github.com/stas00"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"stas00/ml-engineering","creatorName":"stas00","creatorUrl":"https://github.com/stas00","sourceUrl":"https://github.com/stas00/ml-engineering","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/stas00-ml-engineering#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":18124,"forks":1151,"downloads":0,"rating":0,"review_count":0,"quality_score":73.01},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"18K","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"CC-BY-SA-4.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":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":"18K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"18K stars, 1.2K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"CC-BY-SA-4.0"},{"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 stas00/ml-engineering"},{"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/stas00/ml-engineering"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"18K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"18K stars, 1.2K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"CC-BY-SA-4.0"},{"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 stas00/ml-engineering"},{"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/stas00/ml-engineering"},{"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":"18K GitHub stars","repoActivity":"18K stars, 1.2K forks","lastPushed":"2mo since push","license":"CC-BY-SA-4.0","repository":"https://github.com/stas00/ml-engineering","install":"npx skills add stas00/ml-engineering","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 stas00/ml-engineering","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","Machine Learning","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":["ml-automation","machine-learning","automation","ml-media","ai","debugging"],"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":"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":"coding-agents","title":"Coding agents"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"workflow-automation","title":"Workflow automation"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add stas00/ml-engineering","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":18124,"starsLabel":"18K","forks":1151,"license":"CC-BY-SA-4.0","qualityScore":100,"trustScore":88,"auditScore":91},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":68,"lastPushedAt":"2026-05-18T05:37:28+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":["Design","Multimodal media","ml-automation","machine-learning","automation","ml-media","ai","debugging"]},"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":"stas00-ml-engineering","name":"Ml Engineering","description":"Machine Learning Engineering Open Book","category":"ml-automation","url":"https://www.openagentskill.com/skills/stas00-ml-engineering","repository":"https://github.com/stas00/ml-engineering","github_repo":"stas00/ml-engineering"},"suited_tasks":["Coding agents workflows","general agent builders","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Navigate pages","Click and type safely"],"suited_agents":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add stas00/ml-engineering","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add stas00/ml-engineering"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Ml Engineering\" agent skill from https://github.com/stas00/ml-engineering. 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: Machine Learning Engineering Open Book"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Ml Engineering\" as a Claude Code skill from https://github.com/stas00/ml-engineering. 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: Machine Learning Engineering Open Book"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Ml Engineering\" from https://github.com/stas00/ml-engineering 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: Machine Learning Engineering Open Book"}],"handoff_url":"https://www.openagentskill.com/api/skills/stas00-ml-engineering/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/stas00-ml-engineering"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"18K GitHub stars","repoActivity":"18K stars, 1.2K forks","lastPushed":"2mo since push","license":"CC-BY-SA-4.0","repository":"https://github.com/stas00/ml-engineering","install":"npx skills add stas00/ml-engineering","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":["ml-automation","machine-learning","automation","ml-media","ai","debugging"],"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":"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","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 Ml Engineering 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":"stas00-ml-engineering (Ml Engineering)","install_command":"npx skills add stas00/ml-engineering","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":"stas00-ml-engineering","task":"Use Ml Engineering 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/stas00-ml-engineering","api":"https://www.openagentskill.com/api/agent/skills/stas00-ml-engineering","audit":"https://www.openagentskill.com/skills/stas00-ml-engineering/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=stas00-ml-engineering&task=Use%20Ml%20Engineering%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Ml%20Engineering%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Ml%20Engineering%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/stas00-ml-engineering/install","manifest":"https://www.openagentskill.com/api/registry/manifest/stas00-ml-engineering"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"stas00-ml-engineering","name":"Ml Engineering","description":"Machine Learning Engineering Open Book","category":"ml-automation","url":"https://www.openagentskill.com/skills/stas00-ml-engineering","repository":"https://github.com/stas00/ml-engineering","github_repo":"stas00/ml-engineering"},"suited_tasks":["Coding agents workflows","general agent builders","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Navigate pages","Click and type safely"],"suited_agents":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add stas00/ml-engineering","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add stas00/ml-engineering"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Ml Engineering\" agent skill from https://github.com/stas00/ml-engineering. 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: Machine Learning Engineering Open Book"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Ml Engineering\" as a Claude Code skill from https://github.com/stas00/ml-engineering. 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: Machine Learning Engineering Open Book"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Ml Engineering\" from https://github.com/stas00/ml-engineering 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: Machine Learning Engineering Open Book"}],"handoff_url":"https://www.openagentskill.com/api/skills/stas00-ml-engineering/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/stas00-ml-engineering"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"18K GitHub stars","repoActivity":"18K stars, 1.2K forks","lastPushed":"2mo since push","license":"CC-BY-SA-4.0","repository":"https://github.com/stas00/ml-engineering","install":"npx skills add stas00/ml-engineering","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":["ml-automation","machine-learning","automation","ml-media","ai","debugging"],"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":"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","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 Ml Engineering 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":"stas00-ml-engineering (Ml Engineering)","install_command":"npx skills add stas00/ml-engineering","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":"stas00-ml-engineering","task":"Use Ml Engineering 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/stas00-ml-engineering","api":"https://www.openagentskill.com/api/agent/skills/stas00-ml-engineering","audit":"https://www.openagentskill.com/skills/stas00-ml-engineering/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=stas00-ml-engineering&task=Use%20Ml%20Engineering%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Ml%20Engineering%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Ml%20Engineering%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/stas00-ml-engineering/install","manifest":"https://www.openagentskill.com/api/registry/manifest/stas00-ml-engineering"}},"platforms":["Python","Machine Learning"],"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"slug":"testing-qa","title":"Testing and QA","url":"https://www.openagentskill.com/use-cases/testing-qa"}],"install":"npx skills add stas00/ml-engineering","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add stas00/ml-engineering","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Ml Engineering\" agent skill from https://github.com/stas00/ml-engineering. 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: Machine Learning Engineering Open Book","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 \"Ml Engineering\" as a Claude Code skill from https://github.com/stas00/ml-engineering. 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: Machine Learning Engineering Open Book","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 \"Ml Engineering\" from https://github.com/stas00/ml-engineering 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: Machine Learning Engineering Open Book","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/stas00/ml-engineering","github_repo":"stas00/ml-engineering","version":"1.0.0","license":"CC-BY-SA-4.0","updated_at":"2026-06-16T08:55:45.656779+00:00","canonical_key":"stas00/ml-engineering","recommendation_reasons":["Matches task terms: large, language, model","Strong GitHub adoption: 18,124 stars","Quality score 73/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/stas00-ml-engineering","api":"https://www.openagentskill.com/api/agent/skills/stas00-ml-engineering","install_api":"https://www.openagentskill.com/api/skills/stas00-ml-engineering/install","audit":"https://www.openagentskill.com/skills/stas00-ml-engineering/audit","repository":"https://github.com/stas00/ml-engineering"}},{"rank":10,"match_score":65,"raw_match_score":186.4,"slug":"camel-ai-camel","name":"Camel","description":"🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org","tagline":"🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org","category":"agent-frameworks","tags":["agent-framework","orchestration","agent","ai-societies","artificial-intelligence","communicative-ai","cooperative-ai","deep-learning","large-language-models","multi-agent-systems"],"author":{"name":"camel-ai","verified":true,"url":"https://github.com/camel-ai"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"camel-ai/camel","creatorName":"camel-ai","creatorUrl":"https://github.com/camel-ai","sourceUrl":"https://github.com/camel-ai/camel","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/camel-ai-camel#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":17232,"forks":1959,"downloads":0,"rating":0,"review_count":0,"quality_score":72.85},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"17K","tone":"positive"},{"label":"Freshness","value":"1mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":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":"17K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"17K stars, 2.0K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"1mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":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 camel-ai/camel"},{"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/camel-ai/camel"},{"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":"17K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"17K stars, 2.0K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"1mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"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 camel-ai/camel"},{"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/camel-ai/camel"},{"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":"17K GitHub stars","repoActivity":"17K stars, 2.0K forks","lastPushed":"1mo since push","license":"Apache-2.0","repository":"https://github.com/camel-ai/camel","install":"npx skills add camel-ai/camel","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 camel-ai/camel","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","1mo since push"]},"agentCompatibility":["Python","LLM","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","agent-framework","orchestration","agent","ai-societies","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"],"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":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"GitHub automation","description":"I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.","useCases":[{"slug":"github-automation","title":"GitHub automation"},{"slug":"testing-qa","title":"Testing and QA"},{"slug":"web-scraping","title":"Web scraping"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add camel-ai/camel","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":17232,"starsLabel":"17K","forks":1959,"license":"Apache-2.0","qualityScore":100,"trustScore":90,"auditScore":92},"maintenance":{"status":"active","label":"1mo since push","daysSincePush":37,"lastPushedAt":"2026-06-17T07:53:19+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Coding","GitHub automation","agent-frameworks","agent-framework","orchestration","agent","ai-societies","artificial-intelligence"]},"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 GitHub automation","role":"Primary pick","primary_fit":"GitHub automation","best_for":["GitHub 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 GitHub automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"camel-ai-camel","name":"Camel","description":"🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/camel-ai-camel","repository":"https://github.com/camel-ai/camel","github_repo":"camel-ai/camel"},"suited_tasks":["GitHub automation workflows","general agent builders","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Run test suites","Capture failures"],"suited_agents":["Python","LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add camel-ai/camel","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add camel-ai/camel"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Camel\" agent skill from https://github.com/camel-ai/camel. 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: 🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Camel\" as a Claude Code skill from https://github.com/camel-ai/camel. 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: 🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Camel\" from https://github.com/camel-ai/camel 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: 🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org"}],"handoff_url":"https://www.openagentskill.com/api/skills/camel-ai-camel/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/camel-ai-camel"},"trust":{"score":90,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"17K GitHub stars","repoActivity":"17K stars, 2.0K forks","lastPushed":"1mo since push","license":"Apache-2.0","repository":"https://github.com/camel-ai/camel","install":"npx skills add camel-ai/camel","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":["agent-frameworks","agent-framework","orchestration","agent","ai-societies","artificial-intelligence"],"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":"Coding and developer agents","scenario":"GitHub automation","maintenance":"1mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","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 Camel 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":"camel-ai-camel (Camel)","install_command":"npx skills add camel-ai/camel","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":"camel-ai-camel","task":"Use Camel 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/camel-ai-camel","api":"https://www.openagentskill.com/api/agent/skills/camel-ai-camel","audit":"https://www.openagentskill.com/skills/camel-ai-camel/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=camel-ai-camel&task=Use%20Camel%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Camel%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Camel%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/camel-ai-camel/install","manifest":"https://www.openagentskill.com/api/registry/manifest/camel-ai-camel"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"camel-ai-camel","name":"Camel","description":"🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/camel-ai-camel","repository":"https://github.com/camel-ai/camel","github_repo":"camel-ai/camel"},"suited_tasks":["GitHub automation workflows","general agent builders","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Run test suites","Capture failures"],"suited_agents":["Python","LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add camel-ai/camel","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add camel-ai/camel"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Camel\" agent skill from https://github.com/camel-ai/camel. 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: 🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Camel\" as a Claude Code skill from https://github.com/camel-ai/camel. 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: 🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Camel\" from https://github.com/camel-ai/camel 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: 🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org"}],"handoff_url":"https://www.openagentskill.com/api/skills/camel-ai-camel/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/camel-ai-camel"},"trust":{"score":90,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"17K GitHub stars","repoActivity":"17K stars, 2.0K forks","lastPushed":"1mo since push","license":"Apache-2.0","repository":"https://github.com/camel-ai/camel","install":"npx skills add camel-ai/camel","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":["agent-frameworks","agent-framework","orchestration","agent","ai-societies","artificial-intelligence"],"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":"Coding and developer agents","scenario":"GitHub automation","maintenance":"1mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","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 Camel 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":"camel-ai-camel (Camel)","install_command":"npx skills add camel-ai/camel","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":"camel-ai-camel","task":"Use Camel 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/camel-ai-camel","api":"https://www.openagentskill.com/api/agent/skills/camel-ai-camel","audit":"https://www.openagentskill.com/skills/camel-ai-camel/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=camel-ai-camel&task=Use%20Camel%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Camel%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Camel%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/camel-ai-camel/install","manifest":"https://www.openagentskill.com/api/registry/manifest/camel-ai-camel"}},"platforms":["Python","LLM"],"use_cases":[{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"testing-qa","title":"Testing and QA","url":"https://www.openagentskill.com/use-cases/testing-qa"},{"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 camel-ai/camel","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add camel-ai/camel","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Camel\" agent skill from https://github.com/camel-ai/camel. 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: 🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org","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 \"Camel\" as a Claude Code skill from https://github.com/camel-ai/camel. 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: 🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org","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 \"Camel\" from https://github.com/camel-ai/camel 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: 🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/camel-ai/camel","github_repo":"camel-ai/camel","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-06-20T03:00:26.533616+00:00","canonical_key":"camel-ai/camel","recommendation_reasons":["Matches task terms: large, language, model","Strong GitHub adoption: 17,232 stars","Quality score 73/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/camel-ai-camel","api":"https://www.openagentskill.com/api/agent/skills/camel-ai-camel","install_api":"https://www.openagentskill.com/api/skills/camel-ai-camel/install","audit":"https://www.openagentskill.com/skills/camel-ai-camel/audit","repository":"https://github.com/camel-ai/camel"}}],"meta":{"endpoint":"/api/skills/search","canonical_agent_endpoint":"/api/agent/resolve","safety_policy":"Blocked candidates are excluded by default. Pass include_blocked=true only for manual audit workflows.","agent_friendly":true,"api_version":"1.0","generated_at":"2026-07-25T07:11:01.091Z"}}