{"query":"LLaMA LoRA Tuner","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":806.7,"slug":"zetavg-llama-lora-tuner","name":"LLaMA LoRA Tuner","description":"UI tool for fine-tuning and testing your own LoRA models base on LLaMA, GPT-J and more. One-click run on Google Colab. + A Gradio ChatGPT-like Chat UI to demonstrate your language models.","tagline":"UI tool for fine-tuning and testing your own LoRA models base on LLaMA, GPT-J and more. One-click run on Google Colab. + A Gradio ChatGPT-like Chat UI to demonstrate your language models.","category":"ml-automation","tags":["machine-learning","automation","ml-media","ai","alpaca","alpaca-lora","google-colab","gpt","gpt-j","language-model"],"author":{"name":"zetavg","verified":false,"url":"https://github.com/zetavg"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"zetavg/LLaMA-LoRA-Tuner","creatorName":"zetavg","creatorUrl":"https://github.com/zetavg","sourceUrl":"https://github.com/zetavg/LLaMA-LoRA-Tuner","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/zetavg-llama-lora-tuner#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":473,"forks":98,"downloads":0,"rating":0,"review_count":0,"quality_score":37.43},"quality":{"score":48,"tier":"review","label":"Needs review","summary":"Inspect the repository carefully before adding it to an agent workflow.","signals":[{"label":"GitHub stars","value":"473","tone":"neutral"},{"label":"Freshness","value":"3y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":69,"tier":"review","label":"Manual review","summary":"Potentially useful, but at least one trust signal needs human inspection.","recommendedAction":"Inspect the repository, license, and recent activity before connecting it to agent workflows.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"473 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":62,"weight":0.08,"status":"info","detail":"473 stars, 98 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":22,"weight":0.14,"status":"fail","detail":"3y since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":90,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add zetavg/LLaMA-LoRA-Tuner"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/zetavg/LLaMA-LoRA-Tuner"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"info","label":"GitHub adoption","detail":"473 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"473 stars, 98 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"3y since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add zetavg/LLaMA-LoRA-Tuner"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/zetavg/LLaMA-LoRA-Tuner"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Install command has no obvious high-risk pattern"],"warnings":["License is unclear","Repository looks stale","Quality score needs review","Recent maintenance: 3y since push","License clarity: Unknown"],"evidence":{"stars":"473 GitHub stars","repoActivity":"473 stars, 98 forks","lastPushed":"3y since push","license":"Unknown","repository":"https://github.com/zetavg/LLaMA-LoRA-Tuner","install":"npx skills add zetavg/LLaMA-LoRA-Tuner","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add zetavg/LLaMA-LoRA-Tuner","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","3y since push"]},"agentCompatibility":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Repository looks stale","Quality score needs review","Recent maintenance: 3y since push","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":["ml-automation","machine-learning","automation","ml-media","ai","alpaca"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","Repository looks stale","Quality score needs review","Recent maintenance: 3y since push","License clarity: Unknown"]},"safety":{"score":45,"level":"avoid_auto_install","label":"Avoid automatic install","safety_tier":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","summary":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","auto_install_policy":"review","reasons":["License is unclear","45/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["License is unclear"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","reasons":["License is unclear","45/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["Claude Code","OpenAI Agents","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add zetavg/LLaMA-LoRA-Tuner","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":473,"starsLabel":"473","forks":98,"license":"Unknown","qualityScore":48,"trustScore":69,"auditScore":61},"maintenance":{"status":"stale","label":"3y since push","daysSincePush":1131,"lastPushedAt":"2023-05-29T23:27:51+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["License is unclear","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 3y since push"]},"coverageTags":["Coding","Coding agents","ml-automation","machine-learning","automation","ml-media","ai","alpaca"]},"audit":{"audit_score":61,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 3y since push"]},"decision":{"readiness_score":38,"readiness_label":"Needs manual review","headline":"Needs validation for Coding agents","role":"Needs validation","primary_fit":"Coding agents","best_for":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects"],"risks":["Repository looks stale","No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"zetavg-llama-lora-tuner","name":"LLaMA LoRA Tuner","description":"UI tool for fine-tuning and testing your own LoRA models base on LLaMA, GPT-J and more. One-click run on Google Colab. + A Gradio ChatGPT-like Chat UI to demonstrate your language models.","category":"ml-automation","url":"https://www.openagentskill.com/skills/zetavg-llama-lora-tuner","repository":"https://github.com/zetavg/LLaMA-LoRA-Tuner","github_repo":"zetavg/LLaMA-LoRA-Tuner"},"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","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","OpenAI Agents","CLI"],"install":{"command":"npx skills add zetavg/LLaMA-LoRA-Tuner","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add zetavg/LLaMA-LoRA-Tuner"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"LLaMA LoRA Tuner\" agent skill from https://github.com/zetavg/LLaMA-LoRA-Tuner. 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: UI tool for fine-tuning and testing your own LoRA models base on LLaMA, GPT-J and more. One-click run on Google Colab. + A Gradio ChatGPT-like Chat UI to demonstrate your language models."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"LLaMA LoRA Tuner\" as a Claude Code skill from https://github.com/zetavg/LLaMA-LoRA-Tuner. 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: UI tool for fine-tuning and testing your own LoRA models base on LLaMA, GPT-J and more. One-click run on Google Colab. + A Gradio ChatGPT-like Chat UI to demonstrate your language models."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"LLaMA LoRA Tuner\" from https://github.com/zetavg/LLaMA-LoRA-Tuner 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: UI tool for fine-tuning and testing your own LoRA models base on LLaMA, GPT-J and more. One-click run on Google Colab. + A Gradio ChatGPT-like Chat UI to demonstrate your language models."}],"handoff_url":"https://www.openagentskill.com/api/skills/zetavg-llama-lora-tuner/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/zetavg-llama-lora-tuner"},"trust":{"score":69,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"473 GitHub stars","repoActivity":"473 stars, 98 forks","lastPushed":"3y since push","license":"Unknown","repository":"https://github.com/zetavg/LLaMA-LoRA-Tuner","install":"npx skills add zetavg/LLaMA-LoRA-Tuner","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["ml-automation","machine-learning","automation","ml-media","ai","alpaca"],"known_risks":["License is unclear","Repository looks stale","Quality score needs review","Recent maintenance: 3y since push","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":61,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 3y since push","License clarity: Unknown"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":48,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"3y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","License is unclear","Repository appears stale","Quality score needs review","Recent maintenance: 3y since push"],"agent_contract":{"task_input":"Use LLaMA LoRA Tuner in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 69/100 Manual review","Audit: 61/100 Needs review","Safety: 45/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"zetavg-llama-lora-tuner (LLaMA LoRA Tuner)","install_command":"npx skills add zetavg/LLaMA-LoRA-Tuner","risk_summary":"Needs review; Experimental; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"zetavg-llama-lora-tuner","task":"Use LLaMA LoRA Tuner 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/zetavg-llama-lora-tuner","api":"https://www.openagentskill.com/api/agent/skills/zetavg-llama-lora-tuner","audit":"https://www.openagentskill.com/skills/zetavg-llama-lora-tuner/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=zetavg-llama-lora-tuner&task=Use%20LLaMA%20LoRA%20Tuner%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20LLaMA%20LoRA%20Tuner%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20LLaMA%20LoRA%20Tuner%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/zetavg-llama-lora-tuner/install","manifest":"https://www.openagentskill.com/api/registry/manifest/zetavg-llama-lora-tuner"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"zetavg-llama-lora-tuner","name":"LLaMA LoRA Tuner","description":"UI tool for fine-tuning and testing your own LoRA models base on LLaMA, GPT-J and more. One-click run on Google Colab. + A Gradio ChatGPT-like Chat UI to demonstrate your language models.","category":"ml-automation","url":"https://www.openagentskill.com/skills/zetavg-llama-lora-tuner","repository":"https://github.com/zetavg/LLaMA-LoRA-Tuner","github_repo":"zetavg/LLaMA-LoRA-Tuner"},"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","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","OpenAI Agents","CLI"],"install":{"command":"npx skills add zetavg/LLaMA-LoRA-Tuner","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add zetavg/LLaMA-LoRA-Tuner"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"LLaMA LoRA Tuner\" agent skill from https://github.com/zetavg/LLaMA-LoRA-Tuner. 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: UI tool for fine-tuning and testing your own LoRA models base on LLaMA, GPT-J and more. One-click run on Google Colab. + A Gradio ChatGPT-like Chat UI to demonstrate your language models."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"LLaMA LoRA Tuner\" as a Claude Code skill from https://github.com/zetavg/LLaMA-LoRA-Tuner. 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: UI tool for fine-tuning and testing your own LoRA models base on LLaMA, GPT-J and more. One-click run on Google Colab. + A Gradio ChatGPT-like Chat UI to demonstrate your language models."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"LLaMA LoRA Tuner\" from https://github.com/zetavg/LLaMA-LoRA-Tuner 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: UI tool for fine-tuning and testing your own LoRA models base on LLaMA, GPT-J and more. One-click run on Google Colab. + A Gradio ChatGPT-like Chat UI to demonstrate your language models."}],"handoff_url":"https://www.openagentskill.com/api/skills/zetavg-llama-lora-tuner/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/zetavg-llama-lora-tuner"},"trust":{"score":69,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"473 GitHub stars","repoActivity":"473 stars, 98 forks","lastPushed":"3y since push","license":"Unknown","repository":"https://github.com/zetavg/LLaMA-LoRA-Tuner","install":"npx skills add zetavg/LLaMA-LoRA-Tuner","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["ml-automation","machine-learning","automation","ml-media","ai","alpaca"],"known_risks":["License is unclear","Repository looks stale","Quality score needs review","Recent maintenance: 3y since push","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":61,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 3y since push","License clarity: Unknown"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":48,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"3y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","License is unclear","Repository appears stale","Quality score needs review","Recent maintenance: 3y since push"],"agent_contract":{"task_input":"Use LLaMA LoRA Tuner in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 69/100 Manual review","Audit: 61/100 Needs review","Safety: 45/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"zetavg-llama-lora-tuner (LLaMA LoRA Tuner)","install_command":"npx skills add zetavg/LLaMA-LoRA-Tuner","risk_summary":"Needs review; Experimental; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"zetavg-llama-lora-tuner","task":"Use LLaMA LoRA Tuner 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/zetavg-llama-lora-tuner","api":"https://www.openagentskill.com/api/agent/skills/zetavg-llama-lora-tuner","audit":"https://www.openagentskill.com/skills/zetavg-llama-lora-tuner/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=zetavg-llama-lora-tuner&task=Use%20LLaMA%20LoRA%20Tuner%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20LLaMA%20LoRA%20Tuner%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20LLaMA%20LoRA%20Tuner%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/zetavg-llama-lora-tuner/install","manifest":"https://www.openagentskill.com/api/registry/manifest/zetavg-llama-lora-tuner"}},"platforms":["Python","Machine Learning","Claude Code","OpenAI Agents"],"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"install":"npx skills add zetavg/LLaMA-LoRA-Tuner","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add zetavg/LLaMA-LoRA-Tuner","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 \"LLaMA LoRA Tuner\" agent skill from https://github.com/zetavg/LLaMA-LoRA-Tuner. 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: UI tool for fine-tuning and testing your own LoRA models base on LLaMA, GPT-J and more. One-click run on Google Colab. + A Gradio ChatGPT-like Chat UI to demonstrate your language models.","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 \"LLaMA LoRA Tuner\" as a Claude Code skill from https://github.com/zetavg/LLaMA-LoRA-Tuner. 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: UI tool for fine-tuning and testing your own LoRA models base on LLaMA, GPT-J and more. One-click run on Google Colab. + A Gradio ChatGPT-like Chat UI to demonstrate your language models.","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 \"LLaMA LoRA Tuner\" from https://github.com/zetavg/LLaMA-LoRA-Tuner 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: UI tool for fine-tuning and testing your own LoRA models base on LLaMA, GPT-J and more. One-click run on Google Colab. + A Gradio ChatGPT-like Chat UI to demonstrate your language models.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/zetavg/LLaMA-LoRA-Tuner","github_repo":"zetavg/LLaMA-LoRA-Tuner","version":"1.0.0","license":"Unknown","updated_at":"2026-06-21T03:02:54.677697+00:00","canonical_key":"zetavg/llama-lora-tuner","recommendation_reasons":["Matches task terms: llama, lora, tuner","Install handoff is available","Repository freshness signal is available","Registry match score 99"],"urls":{"web":"https://www.openagentskill.com/skills/zetavg-llama-lora-tuner","api":"https://www.openagentskill.com/api/agent/skills/zetavg-llama-lora-tuner","install_api":"https://www.openagentskill.com/api/skills/zetavg-llama-lora-tuner/install","audit":"https://www.openagentskill.com/skills/zetavg-llama-lora-tuner/audit","repository":"https://github.com/zetavg/LLaMA-LoRA-Tuner"}},{"rank":2,"match_score":17,"raw_match_score":135,"slug":"run-llama-llama-index","name":"Llama Index","description":"LlamaIndex is the leading document agent and OCR platform","tagline":"LlamaIndex is the leading document agent and OCR platform","category":"data","tags":["rag","retrieval","agents","application","data","fine-tuning","framework","llamaindex","llm","multi-agents"],"author":{"name":"run-llama","verified":true,"url":"https://github.com/run-llama"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"run-llama/llama_index","creatorName":"run-llama","creatorUrl":"https://github.com/run-llama","sourceUrl":"https://github.com/run-llama/llama_index","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/run-llama-llama-index#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":50200,"forks":7581,"downloads":0,"rating":0,"review_count":0,"quality_score":76.1},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"50K","tone":"positive"},{"label":"Freshness","value":"16d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":92,"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":"50K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"50K stars, 7.6K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"16d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":74,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add run-llama/llama_index"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/run-llama/llama_index"},{"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":"50K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"50K stars, 7.6K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"16d 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 run-llama/llama_index"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/run-llama/llama_index"},{"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":"50K GitHub stars","repoActivity":"50K stars, 7.6K forks","lastPushed":"16d since push","license":"MIT","repository":"https://github.com/run-llama/llama_index","install":"npx skills add run-llama/llama_index","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add run-llama/llama_index","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","16d since push"]},"agentCompatibility":["Python","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","agents","application","fine-tuning"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":[]},"safety":{"score":87,"level":"safe_to_install","label":"Safe to install with normal review","safety_tier":{"tier":"verified","label":"Verified","badge":"VERIFIED","summary":"Strong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","auto_install_policy":"allow","reasons":["Verified listing","Safe-to-try audit","87/100 agent safety score"]},"auto_install_allowed":true,"human_review_required":false,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":[],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"verified","label":"Verified","badge":"VERIFIED","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","reasons":["Verified listing","Safe-to-try audit","87/100 agent safety score"]},"supply_profile":{"track":{"slug":"data","label":"Data, BI, and analytics","shortLabel":"Data","description":"CSV, SQL, notebooks, dashboards, data pipelines, BI, ETL, and spreadsheet analysis."},"scenario":{"label":"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":"coding-agents","title":"Coding agents"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["Claude Code","LlamaIndex","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add run-llama/llama_index","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":50200,"starsLabel":"50K","forks":7581,"license":"MIT","qualityScore":100,"trustScore":92,"auditScore":95},"maintenance":{"status":"fresh","label":"16d since push","daysSincePush":16,"lastPushedAt":"2026-06-17T19:25:43+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":false,"notes":["No major risk signals from available metadata"]},"coverageTags":["Data","RAG and knowledge","rag","retrieval","agents","application","fine-tuning","framework"]},"audit":{"audit_score":95,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for RAG and knowledge","role":"Primary pick","primary_fit":"RAG and knowledge","best_for":["RAG and knowledge workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one 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":"run-llama-llama-index","name":"Llama Index","description":"LlamaIndex is the leading document agent and OCR platform","category":"data","url":"https://www.openagentskill.com/skills/run-llama-llama-index","repository":"https://github.com/run-llama/llama_index","github_repo":"run-llama/llama_index"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Inspect source files","Explain architecture"],"suited_agents":["Python","RAG","Codex","Claude Code","Cursor","OpenAgentSkill CLI","LlamaIndex","CLI"],"install":{"command":"npx skills add run-llama/llama_index","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add run-llama/llama_index"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Llama Index\" agent skill from https://github.com/run-llama/llama_index. 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: LlamaIndex is the leading document agent and OCR platform"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Llama Index\" as a Claude Code skill from https://github.com/run-llama/llama_index. 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: LlamaIndex is the leading document agent and OCR platform"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Llama Index\" from https://github.com/run-llama/llama_index 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: LlamaIndex is the leading document agent and OCR platform"}],"handoff_url":"https://www.openagentskill.com/api/skills/run-llama-llama-index/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/run-llama-llama-index"},"trust":{"score":92,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"50K GitHub stars","repoActivity":"50K stars, 7.6K forks","lastPushed":"16d since push","license":"MIT","repository":"https://github.com/run-llama/llama_index","install":"npx skills add run-llama/llama_index","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["data","rag","retrieval","agents","application","fine-tuning"],"known_risks":[]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":95,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety_gate":{"tier":"verified","label":"Verified","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Data, BI, and analytics","scenario":"RAG and knowledge","maintenance":"16d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","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 Llama Index 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: 92/100 Production candidate","Audit: 95/100 Safe to try","Safety: 87/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"run-llama-llama-index (Llama Index)","install_command":"npx skills add run-llama/llama_index","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":"run-llama-llama-index","task":"Use Llama Index 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/run-llama-llama-index","api":"https://www.openagentskill.com/api/agent/skills/run-llama-llama-index","audit":"https://www.openagentskill.com/skills/run-llama-llama-index/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=run-llama-llama-index&task=Use%20Llama%20Index%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Llama%20Index%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Llama%20Index%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/run-llama-llama-index/install","manifest":"https://www.openagentskill.com/api/registry/manifest/run-llama-llama-index"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"run-llama-llama-index","name":"Llama Index","description":"LlamaIndex is the leading document agent and OCR platform","category":"data","url":"https://www.openagentskill.com/skills/run-llama-llama-index","repository":"https://github.com/run-llama/llama_index","github_repo":"run-llama/llama_index"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Inspect source files","Explain architecture"],"suited_agents":["Python","RAG","Codex","Claude Code","Cursor","OpenAgentSkill CLI","LlamaIndex","CLI"],"install":{"command":"npx skills add run-llama/llama_index","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add run-llama/llama_index"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Llama Index\" agent skill from https://github.com/run-llama/llama_index. 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: LlamaIndex is the leading document agent and OCR platform"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Llama Index\" as a Claude Code skill from https://github.com/run-llama/llama_index. 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: LlamaIndex is the leading document agent and OCR platform"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Llama Index\" from https://github.com/run-llama/llama_index 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: LlamaIndex is the leading document agent and OCR platform"}],"handoff_url":"https://www.openagentskill.com/api/skills/run-llama-llama-index/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/run-llama-llama-index"},"trust":{"score":92,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"50K GitHub stars","repoActivity":"50K stars, 7.6K forks","lastPushed":"16d since push","license":"MIT","repository":"https://github.com/run-llama/llama_index","install":"npx skills add run-llama/llama_index","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["data","rag","retrieval","agents","application","fine-tuning"],"known_risks":[]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":95,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety_gate":{"tier":"verified","label":"Verified","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Data, BI, and analytics","scenario":"RAG and knowledge","maintenance":"16d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","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 Llama Index 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: 92/100 Production candidate","Audit: 95/100 Safe to try","Safety: 87/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"run-llama-llama-index (Llama Index)","install_command":"npx skills add run-llama/llama_index","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":"run-llama-llama-index","task":"Use Llama Index 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/run-llama-llama-index","api":"https://www.openagentskill.com/api/agent/skills/run-llama-llama-index","audit":"https://www.openagentskill.com/skills/run-llama-llama-index/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=run-llama-llama-index&task=Use%20Llama%20Index%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Llama%20Index%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Llama%20Index%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/run-llama-llama-index/install","manifest":"https://www.openagentskill.com/api/registry/manifest/run-llama-llama-index"}},"platforms":["Python","RAG","Claude Code","LlamaIndex"],"use_cases":[{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"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 run-llama/llama_index","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add run-llama/llama_index","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 \"Llama Index\" agent skill from https://github.com/run-llama/llama_index. 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: LlamaIndex is the leading document agent and OCR platform","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Llama Index\" as a Claude Code skill from https://github.com/run-llama/llama_index. 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: LlamaIndex is the leading document agent and OCR platform","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Llama Index\" from https://github.com/run-llama/llama_index 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: LlamaIndex is the leading document agent and OCR platform","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/run-llama/llama_index","github_repo":"run-llama/llama_index","version":"1.0.0","license":"MIT","updated_at":"2026-06-18T03:02:48.688328+00:00","canonical_key":"run-llama/llama_index","recommendation_reasons":["Matches task terms: llama","Strong GitHub adoption: 50,200 stars","Quality score 76/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/run-llama-llama-index","api":"https://www.openagentskill.com/api/agent/skills/run-llama-llama-index","install_api":"https://www.openagentskill.com/api/skills/run-llama-llama-index/install","audit":"https://www.openagentskill.com/skills/run-llama-llama-index/audit","repository":"https://github.com/run-llama/llama_index"}},{"rank":3,"match_score":16,"raw_match_score":133.6,"slug":"meta-llama-llama-cookbook","name":"Llama Cookbook","description":"Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services  ","tagline":"Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services  ","category":"ml-automation","tags":["machine-learning","automation","ml-media","ai","finetuning","langchain","llama","llama2","llm","python"],"author":{"name":"meta-llama","verified":true,"url":"https://github.com/meta-llama"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"meta-llama/llama-cookbook","creatorName":"meta-llama","creatorUrl":"https://github.com/meta-llama","sourceUrl":"https://github.com/meta-llama/llama-cookbook","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/meta-llama-llama-cookbook#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":18356,"forks":2740,"downloads":0,"rating":0,"review_count":0,"quality_score":73.05},"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":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":92,"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, 2.7K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":90,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add meta-llama/llama-cookbook"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/meta-llama/llama-cookbook"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"18K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"18K stars, 2.7K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add meta-llama/llama-cookbook"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/meta-llama/llama-cookbook"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":[],"evidence":{"stars":"18K GitHub stars","repoActivity":"18K stars, 2.7K forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/meta-llama/llama-cookbook","install":"npx skills add meta-llama/llama-cookbook","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add meta-llama/llama-cookbook","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Jupyter Notebook","Machine Learning","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":["ml-automation","machine-learning","automation","ml-media","ai","finetuning"],"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":85,"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","85/100 agent safety score"]},"auto_install_allowed":true,"human_review_required":false,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":[],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"verified","label":"Verified","badge":"VERIFIED","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","reasons":["Verified listing","Safe-to-try audit","85/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["Claude Code","LangChain","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add meta-llama/llama-cookbook","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":18356,"starsLabel":"18K","forks":2740,"license":"MIT","qualityScore":100,"trustScore":92,"auditScore":93},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":45,"lastPushedAt":"2026-05-19T18:42:31+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":false,"notes":["No major risk signals from available metadata"]},"coverageTags":["Coding","Coding agents","ml-automation","machine-learning","automation","ml-media","ai","finetuning"]},"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 Coding agents","role":"Primary pick","primary_fit":"Coding agents","best_for":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"meta-llama-llama-cookbook","name":"Llama Cookbook","description":"Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services  ","category":"ml-automation","url":"https://www.openagentskill.com/skills/meta-llama-llama-cookbook","repository":"https://github.com/meta-llama/llama-cookbook","github_repo":"meta-llama/llama-cookbook"},"suited_tasks":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Chunk documents","Create embeddings"],"suited_agents":["Jupyter Notebook","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","LangChain","CLI"],"install":{"command":"npx skills add meta-llama/llama-cookbook","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add meta-llama/llama-cookbook"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Llama Cookbook\" agent skill from https://github.com/meta-llama/llama-cookbook. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Llama Cookbook\" as a Claude Code skill from https://github.com/meta-llama/llama-cookbook. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Llama Cookbook\" from https://github.com/meta-llama/llama-cookbook into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services"}],"handoff_url":"https://www.openagentskill.com/api/skills/meta-llama-llama-cookbook/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/meta-llama-llama-cookbook"},"trust":{"score":92,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"18K GitHub stars","repoActivity":"18K stars, 2.7K forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/meta-llama/llama-cookbook","install":"npx skills add meta-llama/llama-cookbook","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["ml-automation","machine-learning","automation","ml-media","ai","finetuning"],"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":"Coding and developer agents","scenario":"Coding agents","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","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 Llama Cookbook 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: 92/100 Production candidate","Audit: 93/100 Safe to try","Safety: 85/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"meta-llama-llama-cookbook (Llama Cookbook)","install_command":"npx skills add meta-llama/llama-cookbook","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":"meta-llama-llama-cookbook","task":"Use Llama Cookbook 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/meta-llama-llama-cookbook","api":"https://www.openagentskill.com/api/agent/skills/meta-llama-llama-cookbook","audit":"https://www.openagentskill.com/skills/meta-llama-llama-cookbook/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=meta-llama-llama-cookbook&task=Use%20Llama%20Cookbook%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Llama%20Cookbook%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Llama%20Cookbook%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/meta-llama-llama-cookbook/install","manifest":"https://www.openagentskill.com/api/registry/manifest/meta-llama-llama-cookbook"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"meta-llama-llama-cookbook","name":"Llama Cookbook","description":"Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services  ","category":"ml-automation","url":"https://www.openagentskill.com/skills/meta-llama-llama-cookbook","repository":"https://github.com/meta-llama/llama-cookbook","github_repo":"meta-llama/llama-cookbook"},"suited_tasks":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Chunk documents","Create embeddings"],"suited_agents":["Jupyter Notebook","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","LangChain","CLI"],"install":{"command":"npx skills add meta-llama/llama-cookbook","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add meta-llama/llama-cookbook"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Llama Cookbook\" agent skill from https://github.com/meta-llama/llama-cookbook. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Llama Cookbook\" as a Claude Code skill from https://github.com/meta-llama/llama-cookbook. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Llama Cookbook\" from https://github.com/meta-llama/llama-cookbook into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services"}],"handoff_url":"https://www.openagentskill.com/api/skills/meta-llama-llama-cookbook/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/meta-llama-llama-cookbook"},"trust":{"score":92,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"18K GitHub stars","repoActivity":"18K stars, 2.7K forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/meta-llama/llama-cookbook","install":"npx skills add meta-llama/llama-cookbook","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["ml-automation","machine-learning","automation","ml-media","ai","finetuning"],"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":"Coding and developer agents","scenario":"Coding agents","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","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 Llama Cookbook 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: 92/100 Production candidate","Audit: 93/100 Safe to try","Safety: 85/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"meta-llama-llama-cookbook (Llama Cookbook)","install_command":"npx skills add meta-llama/llama-cookbook","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":"meta-llama-llama-cookbook","task":"Use Llama Cookbook 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/meta-llama-llama-cookbook","api":"https://www.openagentskill.com/api/agent/skills/meta-llama-llama-cookbook","audit":"https://www.openagentskill.com/skills/meta-llama-llama-cookbook/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=meta-llama-llama-cookbook&task=Use%20Llama%20Cookbook%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Llama%20Cookbook%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Llama%20Cookbook%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/meta-llama-llama-cookbook/install","manifest":"https://www.openagentskill.com/api/registry/manifest/meta-llama-llama-cookbook"}},"platforms":["Jupyter Notebook","Machine Learning","Claude Code","LangChain"],"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"install":"npx skills add meta-llama/llama-cookbook","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add meta-llama/llama-cookbook","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Llama Cookbook\" agent skill from https://github.com/meta-llama/llama-cookbook. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services","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 \"Llama Cookbook\" as a Claude Code skill from https://github.com/meta-llama/llama-cookbook. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services","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 \"Llama Cookbook\" from https://github.com/meta-llama/llama-cookbook into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/meta-llama/llama-cookbook","github_repo":"meta-llama/llama-cookbook","version":"1.0.0","license":"MIT","updated_at":"2026-06-16T08:55:45.612917+00:00","canonical_key":"meta-llama/llama-cookbook","recommendation_reasons":["Matches task terms: llama","Strong GitHub adoption: 18,356 stars","Quality score 73/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/meta-llama-llama-cookbook","api":"https://www.openagentskill.com/api/agent/skills/meta-llama-llama-cookbook","install_api":"https://www.openagentskill.com/api/skills/meta-llama-llama-cookbook/install","audit":"https://www.openagentskill.com/skills/meta-llama-llama-cookbook/audit","repository":"https://github.com/meta-llama/llama-cookbook"}},{"rank":4,"match_score":10,"raw_match_score":79.2,"slug":"unslothai-unsloth","name":"Unsloth","description":"Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.","tagline":"Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.","category":"media-automation","tags":["text-to-speech","voice","ml-media","agent","deepseek","fine-tuning","gemma","gemma3","gpt-oss","llama"],"author":{"name":"unslothai","verified":true,"url":"https://github.com/unslothai"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"unslothai/unsloth","creatorName":"unslothai","creatorUrl":"https://github.com/unslothai","sourceUrl":"https://github.com/unslothai/unsloth","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/unslothai-unsloth#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":66978,"forks":6015,"downloads":0,"rating":0,"review_count":0,"quality_score":76.98},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"67K","tone":"positive"},{"label":"Freshness","value":"13d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":94,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"67K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"67K stars, 6.0K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"13d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":90,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add unslothai/unsloth"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/unslothai/unsloth"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"67K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"67K stars, 6.0K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"13d since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add unslothai/unsloth"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/unslothai/unsloth"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":[],"evidence":{"stars":"67K GitHub stars","repoActivity":"67K stars, 6.0K forks","lastPushed":"13d since push","license":"Apache-2.0","repository":"https://github.com/unslothai/unsloth","install":"npx skills add unslothai/unsloth","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add unslothai/unsloth","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","13d since push"]},"agentCompatibility":["Python","Voice","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":["media-automation","text-to-speech","voice","ml-media","agent","deepseek"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":[]},"safety":{"score":87,"level":"safe_to_install","label":"Safe to install with normal review","safety_tier":{"tier":"verified","label":"Verified","badge":"VERIFIED","summary":"Strong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","auto_install_policy":"allow","reasons":["Verified listing","Safe-to-try audit","87/100 agent safety score"]},"auto_install_allowed":true,"human_review_required":false,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":[],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"verified","label":"Verified","badge":"VERIFIED","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","reasons":["Verified listing","Safe-to-try audit","87/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["Claude Code","OpenAI Agents","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add unslothai/unsloth","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":66978,"starsLabel":"67K","forks":6015,"license":"Apache-2.0","qualityScore":100,"trustScore":94,"auditScore":95},"maintenance":{"status":"fresh","label":"13d since push","daysSincePush":13,"lastPushedAt":"2026-06-20T14:58:53+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":false,"notes":["No major risk signals from available metadata"]},"coverageTags":["Coding","Coding agents","media-automation","text-to-speech","voice","ml-media","agent","deepseek"]},"audit":{"audit_score":95,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Coding agents","role":"Primary pick","primary_fit":"Coding agents","best_for":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"unslothai-unsloth","name":"Unsloth","description":"Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.","category":"media-automation","url":"https://www.openagentskill.com/skills/unslothai-unsloth","repository":"https://github.com/unslothai/unsloth","github_repo":"unslothai/unsloth"},"suited_tasks":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Chunk documents","Create embeddings"],"suited_agents":["Python","Voice","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add unslothai/unsloth","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add unslothai/unsloth"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Unsloth\" agent skill from https://github.com/unslothai/unsloth. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Unsloth\" as a Claude Code skill from https://github.com/unslothai/unsloth. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Unsloth\" from https://github.com/unslothai/unsloth into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally."}],"handoff_url":"https://www.openagentskill.com/api/skills/unslothai-unsloth/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/unslothai-unsloth"},"trust":{"score":94,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"67K GitHub stars","repoActivity":"67K stars, 6.0K forks","lastPushed":"13d since push","license":"Apache-2.0","repository":"https://github.com/unslothai/unsloth","install":"npx skills add unslothai/unsloth","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["media-automation","text-to-speech","voice","ml-media","agent","deepseek"],"known_risks":[]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":95,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety_gate":{"tier":"verified","label":"Verified","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"13d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","No major trust warnings detected from available metadata","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Unsloth in an agent workflow","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","install_policy":"allow","minimum_review_before_use":["Trust: 94/100 Production candidate","Audit: 95/100 Safe to try","Safety: 87/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"unslothai-unsloth (Unsloth)","install_command":"npx skills add unslothai/unsloth","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":"unslothai-unsloth","task":"Use Unsloth in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/unslothai-unsloth","api":"https://www.openagentskill.com/api/agent/skills/unslothai-unsloth","audit":"https://www.openagentskill.com/skills/unslothai-unsloth/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=unslothai-unsloth&task=Use%20Unsloth%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Unsloth%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Unsloth%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/unslothai-unsloth/install","manifest":"https://www.openagentskill.com/api/registry/manifest/unslothai-unsloth"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"unslothai-unsloth","name":"Unsloth","description":"Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.","category":"media-automation","url":"https://www.openagentskill.com/skills/unslothai-unsloth","repository":"https://github.com/unslothai/unsloth","github_repo":"unslothai/unsloth"},"suited_tasks":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Chunk documents","Create embeddings"],"suited_agents":["Python","Voice","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add unslothai/unsloth","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add unslothai/unsloth"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Unsloth\" agent skill from https://github.com/unslothai/unsloth. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Unsloth\" as a Claude Code skill from https://github.com/unslothai/unsloth. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Unsloth\" from https://github.com/unslothai/unsloth into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally."}],"handoff_url":"https://www.openagentskill.com/api/skills/unslothai-unsloth/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/unslothai-unsloth"},"trust":{"score":94,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"67K GitHub stars","repoActivity":"67K stars, 6.0K forks","lastPushed":"13d since push","license":"Apache-2.0","repository":"https://github.com/unslothai/unsloth","install":"npx skills add unslothai/unsloth","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["media-automation","text-to-speech","voice","ml-media","agent","deepseek"],"known_risks":[]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":95,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety_gate":{"tier":"verified","label":"Verified","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"13d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","No major trust warnings detected from available metadata","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Unsloth in an agent workflow","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","install_policy":"allow","minimum_review_before_use":["Trust: 94/100 Production candidate","Audit: 95/100 Safe to try","Safety: 87/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"unslothai-unsloth (Unsloth)","install_command":"npx skills add unslothai/unsloth","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":"unslothai-unsloth","task":"Use Unsloth in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/unslothai-unsloth","api":"https://www.openagentskill.com/api/agent/skills/unslothai-unsloth","audit":"https://www.openagentskill.com/skills/unslothai-unsloth/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=unslothai-unsloth&task=Use%20Unsloth%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Unsloth%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Unsloth%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/unslothai-unsloth/install","manifest":"https://www.openagentskill.com/api/registry/manifest/unslothai-unsloth"}},"platforms":["Python","Voice","Claude Code","OpenAI Agents"],"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"install":"npx skills add unslothai/unsloth","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add unslothai/unsloth","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 \"Unsloth\" agent skill from https://github.com/unslothai/unsloth. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Unsloth\" as a Claude Code skill from https://github.com/unslothai/unsloth. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Unsloth\" from https://github.com/unslothai/unsloth into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/unslothai/unsloth","github_repo":"unslothai/unsloth","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-06-21T00:56:05.074224+00:00","canonical_key":"unslothai/unsloth","recommendation_reasons":["Matches task terms: llama","Strong GitHub adoption: 66,978 stars","Quality score 77/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/unslothai-unsloth","api":"https://www.openagentskill.com/api/agent/skills/unslothai-unsloth","install_api":"https://www.openagentskill.com/api/skills/unslothai-unsloth/install","audit":"https://www.openagentskill.com/skills/unslothai-unsloth/audit","repository":"https://github.com/unslothai/unsloth"}},{"rank":5,"match_score":10,"raw_match_score":78.8,"slug":"khoj-ai-khoj","name":"Khoj","description":"Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.","tagline":"Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.","category":"data","tags":["rag","retrieval","agent","ai","assistant","chat","chatgpt","emacs","image-generation","llama3"],"author":{"name":"khoj-ai","verified":true,"url":"https://github.com/khoj-ai"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"khoj-ai/khoj","creatorName":"khoj-ai","creatorUrl":"https://github.com/khoj-ai","sourceUrl":"https://github.com/khoj-ai/khoj","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/khoj-ai-khoj#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":35337,"forks":2267,"downloads":0,"rating":0,"review_count":0,"quality_score":75.04},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"35K","tone":"positive"},{"label":"Freshness","value":"9d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"AGPL-3.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":93,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"35K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"35K stars, 2.3K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"9d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"AGPL-3.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":90,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add khoj-ai/khoj"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/khoj-ai/khoj"},{"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":"35K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"35K stars, 2.3K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"9d since push"},{"status":"pass","label":"License clarity","detail":"AGPL-3.0"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add khoj-ai/khoj"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/khoj-ai/khoj"},{"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":"35K GitHub stars","repoActivity":"35K stars, 2.3K forks","lastPushed":"9d since push","license":"AGPL-3.0","repository":"https://github.com/khoj-ai/khoj","install":"npx skills add khoj-ai/khoj","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add khoj-ai/khoj","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","9d since push"]},"agentCompatibility":["Python","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","ai","assistant"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":[]},"safety":{"score":87,"level":"safe_to_install","label":"Safe to install with normal review","safety_tier":{"tier":"verified","label":"Verified","badge":"VERIFIED","summary":"Strong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","auto_install_policy":"allow","reasons":["Verified listing","Safe-to-try audit","87/100 agent safety score"]},"auto_install_allowed":true,"human_review_required":false,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":[],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"verified","label":"Verified","badge":"VERIFIED","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","reasons":["Verified listing","Safe-to-try audit","87/100 agent safety score"]},"supply_profile":{"track":{"slug":"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":"workflow-automation","title":"Workflow automation"},{"slug":"coding-agents","title":"Coding agents"}]},"applicableAgents":["Claude Code","OpenAI Agents","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add khoj-ai/khoj","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":35337,"starsLabel":"35K","forks":2267,"license":"AGPL-3.0","qualityScore":100,"trustScore":93,"auditScore":95},"maintenance":{"status":"fresh","label":"9d since push","daysSincePush":9,"lastPushedAt":"2026-06-24T21:17:20+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","ai","assistant"]},"audit":{"audit_score":95,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for RAG and knowledge","role":"Primary pick","primary_fit":"RAG and knowledge","best_for":["RAG and knowledge workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one 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":"khoj-ai-khoj","name":"Khoj","description":"Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.","category":"data","url":"https://www.openagentskill.com/skills/khoj-ai-khoj","repository":"https://github.com/khoj-ai/khoj","github_repo":"khoj-ai/khoj"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Move data between tools","Transform files"],"suited_agents":["Python","RAG","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add khoj-ai/khoj","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add khoj-ai/khoj"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Khoj\" agent skill from https://github.com/khoj-ai/khoj. 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: Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Khoj\" as a Claude Code skill from https://github.com/khoj-ai/khoj. 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: Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Khoj\" from https://github.com/khoj-ai/khoj 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: Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free."}],"handoff_url":"https://www.openagentskill.com/api/skills/khoj-ai-khoj/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/khoj-ai-khoj"},"trust":{"score":93,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"35K GitHub stars","repoActivity":"35K stars, 2.3K forks","lastPushed":"9d since push","license":"AGPL-3.0","repository":"https://github.com/khoj-ai/khoj","install":"npx skills add khoj-ai/khoj","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["data","rag","retrieval","agent","ai","assistant"],"known_risks":[]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":95,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety_gate":{"tier":"verified","label":"Verified","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"9d 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 Khoj in an agent workflow","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","install_policy":"allow","minimum_review_before_use":["Trust: 93/100 Production candidate","Audit: 95/100 Safe to try","Safety: 87/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"khoj-ai-khoj (Khoj)","install_command":"npx skills add khoj-ai/khoj","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":"khoj-ai-khoj","task":"Use Khoj 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/khoj-ai-khoj","api":"https://www.openagentskill.com/api/agent/skills/khoj-ai-khoj","audit":"https://www.openagentskill.com/skills/khoj-ai-khoj/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=khoj-ai-khoj&task=Use%20Khoj%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Khoj%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Khoj%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/khoj-ai-khoj/install","manifest":"https://www.openagentskill.com/api/registry/manifest/khoj-ai-khoj"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"khoj-ai-khoj","name":"Khoj","description":"Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.","category":"data","url":"https://www.openagentskill.com/skills/khoj-ai-khoj","repository":"https://github.com/khoj-ai/khoj","github_repo":"khoj-ai/khoj"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Move data between tools","Transform files"],"suited_agents":["Python","RAG","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add khoj-ai/khoj","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add khoj-ai/khoj"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Khoj\" agent skill from https://github.com/khoj-ai/khoj. 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: Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Khoj\" as a Claude Code skill from https://github.com/khoj-ai/khoj. 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: Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Khoj\" from https://github.com/khoj-ai/khoj 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: Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free."}],"handoff_url":"https://www.openagentskill.com/api/skills/khoj-ai-khoj/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/khoj-ai-khoj"},"trust":{"score":93,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"35K GitHub stars","repoActivity":"35K stars, 2.3K forks","lastPushed":"9d since push","license":"AGPL-3.0","repository":"https://github.com/khoj-ai/khoj","install":"npx skills add khoj-ai/khoj","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["data","rag","retrieval","agent","ai","assistant"],"known_risks":[]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":95,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety_gate":{"tier":"verified","label":"Verified","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"9d 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 Khoj in an agent workflow","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","install_policy":"allow","minimum_review_before_use":["Trust: 93/100 Production candidate","Audit: 95/100 Safe to try","Safety: 87/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"khoj-ai-khoj (Khoj)","install_command":"npx skills add khoj-ai/khoj","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":"khoj-ai-khoj","task":"Use Khoj 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/khoj-ai-khoj","api":"https://www.openagentskill.com/api/agent/skills/khoj-ai-khoj","audit":"https://www.openagentskill.com/skills/khoj-ai-khoj/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=khoj-ai-khoj&task=Use%20Khoj%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Khoj%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Khoj%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/khoj-ai-khoj/install","manifest":"https://www.openagentskill.com/api/registry/manifest/khoj-ai-khoj"}},"platforms":["Python","RAG","Claude Code","OpenAI Agents"],"use_cases":[{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"install":"npx skills add khoj-ai/khoj","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add khoj-ai/khoj","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 \"Khoj\" agent skill from https://github.com/khoj-ai/khoj. 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: Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.","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 \"Khoj\" as a Claude Code skill from https://github.com/khoj-ai/khoj. 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: Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.","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 \"Khoj\" from https://github.com/khoj-ai/khoj 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: Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/khoj-ai/khoj","github_repo":"khoj-ai/khoj","version":"1.0.0","license":"AGPL-3.0","updated_at":"2026-06-27T03:00:37.740483+00:00","canonical_key":"khoj-ai/khoj","recommendation_reasons":["Matches task terms: llama","Strong GitHub adoption: 35,337 stars","Quality score 75/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/khoj-ai-khoj","api":"https://www.openagentskill.com/api/agent/skills/khoj-ai-khoj","install_api":"https://www.openagentskill.com/api/skills/khoj-ai-khoj/install","audit":"https://www.openagentskill.com/skills/khoj-ai-khoj/audit","repository":"https://github.com/khoj-ai/khoj"}},{"rank":6,"match_score":10,"raw_match_score":78.6,"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":"13d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","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":"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":100,"weight":0.14,"status":"pass","detail":"13d since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":90,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add 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":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/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":"13d since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add langfuse/langfuse"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/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","License clarity: Unknown"],"evidence":{"stars":"29K GitHub stars","repoActivity":"29K stars, 3.1K forks","lastPushed":"13d since push","license":"Unknown","repository":"https://github.com/langfuse/langfuse","install":"npx skills add langfuse/langfuse","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add 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","13d since push"]},"agentCompatibility":["TypeScript","LLMOps","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","License clarity: Unknown"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["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","License clarity: Unknown"]},"safety":{"score":77,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","77/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["License is unclear"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","77/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["Claude Code","OpenAI Agents","LangChain","CLI","Codex"],"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":90,"auditScore":93},"maintenance":{"status":"fresh","label":"13d since push","daysSincePush":13,"lastPushedAt":"2026-06-20T09:29:08+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["License is unclear","License clarity: Unknown"]},"coverageTags":["Coding","Coding agents","development","llmops","developer-tools","analytics","autogen","evaluation"]},"audit":{"audit_score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","License clarity: Unknown"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Coding agents","role":"Primary pick","primary_fit":"Coding agents","best_for":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"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":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Chunk documents","Create embeddings"],"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":90,"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":"13d since push","license":"Unknown","repository":"https://github.com/langfuse/langfuse","install":"npx skills add langfuse/langfuse","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["development","llmops","developer-tools","analytics","autogen","evaluation"],"known_risks":["License is unclear","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"13d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use 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: 90/100 Production candidate","Audit: 93/100 Safe to try","Safety: 77/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"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":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Chunk documents","Create embeddings"],"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":90,"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":"13d since push","license":"Unknown","repository":"https://github.com/langfuse/langfuse","install":"npx skills add langfuse/langfuse","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["development","llmops","developer-tools","analytics","autogen","evaluation"],"known_risks":["License is unclear","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"13d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use 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: 90/100 Production candidate","Audit: 93/100 Safe to try","Safety: 77/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"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","Claude Code","OpenAI Agents","LangChain"],"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"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: llama","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":7,"match_score":10,"raw_match_score":78.6,"slug":"nirdiamant-rag-techniques","name":"RAG Techniques","description":"This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.","tagline":"This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.","category":"rag-knowledge","tags":["semantic-search","retrieval","knowledge","agentic-rag","ai","embeddings","generative-ai","gpt","langchain","llama-index"],"author":{"name":"NirDiamant","verified":true,"url":"https://github.com/NirDiamant"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"NirDiamant/RAG_Techniques","creatorName":"NirDiamant","creatorUrl":"https://github.com/NirDiamant","sourceUrl":"https://github.com/NirDiamant/RAG_Techniques","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/nirdiamant-rag-techniques#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":28057,"forks":3397,"downloads":0,"rating":0,"review_count":0,"quality_score":74.34},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"28K","tone":"positive"},{"label":"Freshness","value":"16d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":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":"28K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"28K stars, 3.4K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"16d since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":90,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add NirDiamant/RAG_Techniques"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/NirDiamant/RAG_Techniques"},{"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":"28K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"28K stars, 3.4K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"16d since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add NirDiamant/RAG_Techniques"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/NirDiamant/RAG_Techniques"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["License is unclear","License clarity: Unknown"],"evidence":{"stars":"28K GitHub stars","repoActivity":"28K stars, 3.4K forks","lastPushed":"16d since push","license":"Unknown","repository":"https://github.com/NirDiamant/RAG_Techniques","install":"npx skills add NirDiamant/RAG_Techniques","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add NirDiamant/RAG_Techniques","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","No Agent Proven outcome evidence yet","16d since push"]},"agentCompatibility":["Jupyter Notebook","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","License clarity: Unknown"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["rag-knowledge","semantic-search","retrieval","knowledge","agentic-rag","ai"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","License clarity: Unknown"]},"safety":{"score":77,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","77/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["License is unclear"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","77/100 agent safety score"]},"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"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":"coding-agents","title":"Coding agents"},{"slug":"github-automation","title":"GitHub automation"}]},"applicableAgents":["Claude Code","OpenAI Agents","LangChain","CLI","Codex"],"install":{"ready":true,"command":"npx skills add NirDiamant/RAG_Techniques","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":28057,"starsLabel":"28K","forks":3397,"license":"Unknown","qualityScore":100,"trustScore":90,"auditScore":93},"maintenance":{"status":"fresh","label":"16d since push","daysSincePush":16,"lastPushedAt":"2026-06-17T20:54:18+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["License is unclear","License clarity: Unknown"]},"coverageTags":["Research","RAG and knowledge","rag-knowledge","semantic-search","retrieval","knowledge","agentic-rag","ai"]},"audit":{"audit_score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","License clarity: Unknown"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for RAG and knowledge","role":"Primary pick","primary_fit":"RAG and knowledge","best_for":["RAG and knowledge workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one 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":"nirdiamant-rag-techniques","name":"RAG Techniques","description":"This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.","category":"rag-knowledge","url":"https://www.openagentskill.com/skills/nirdiamant-rag-techniques","repository":"https://github.com/NirDiamant/RAG_Techniques","github_repo":"NirDiamant/RAG_Techniques"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Inspect source files","Explain architecture"],"suited_agents":["Jupyter Notebook","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","LangChain"],"install":{"command":"npx skills add NirDiamant/RAG_Techniques","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add NirDiamant/RAG_Techniques"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"RAG Techniques\" agent skill from https://github.com/NirDiamant/RAG_Techniques. 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: This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"RAG Techniques\" as a Claude Code skill from https://github.com/NirDiamant/RAG_Techniques. 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: This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"RAG Techniques\" from https://github.com/NirDiamant/RAG_Techniques 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: This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial."}],"handoff_url":"https://www.openagentskill.com/api/skills/nirdiamant-rag-techniques/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/nirdiamant-rag-techniques"},"trust":{"score":90,"label":"Production candidate","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"28K GitHub stars","repoActivity":"28K stars, 3.4K forks","lastPushed":"16d since push","license":"Unknown","repository":"https://github.com/NirDiamant/RAG_Techniques","install":"npx skills add NirDiamant/RAG_Techniques","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["rag-knowledge","semantic-search","retrieval","knowledge","agentic-rag","ai"],"known_risks":["License is unclear","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"16d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use RAG Techniques 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: 93/100 Safe to try","Safety: 77/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"nirdiamant-rag-techniques (RAG Techniques)","install_command":"npx skills add NirDiamant/RAG_Techniques","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":"nirdiamant-rag-techniques","task":"Use RAG Techniques 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/nirdiamant-rag-techniques","api":"https://www.openagentskill.com/api/agent/skills/nirdiamant-rag-techniques","audit":"https://www.openagentskill.com/skills/nirdiamant-rag-techniques/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=nirdiamant-rag-techniques&task=Use%20RAG%20Techniques%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20RAG%20Techniques%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20RAG%20Techniques%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/nirdiamant-rag-techniques/install","manifest":"https://www.openagentskill.com/api/registry/manifest/nirdiamant-rag-techniques"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"nirdiamant-rag-techniques","name":"RAG Techniques","description":"This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.","category":"rag-knowledge","url":"https://www.openagentskill.com/skills/nirdiamant-rag-techniques","repository":"https://github.com/NirDiamant/RAG_Techniques","github_repo":"NirDiamant/RAG_Techniques"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Inspect source files","Explain architecture"],"suited_agents":["Jupyter Notebook","Semantic Search","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","LangChain"],"install":{"command":"npx skills add NirDiamant/RAG_Techniques","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add NirDiamant/RAG_Techniques"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"RAG Techniques\" agent skill from https://github.com/NirDiamant/RAG_Techniques. 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: This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"RAG Techniques\" as a Claude Code skill from https://github.com/NirDiamant/RAG_Techniques. 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: This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"RAG Techniques\" from https://github.com/NirDiamant/RAG_Techniques 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: This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial."}],"handoff_url":"https://www.openagentskill.com/api/skills/nirdiamant-rag-techniques/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/nirdiamant-rag-techniques"},"trust":{"score":90,"label":"Production candidate","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"28K GitHub stars","repoActivity":"28K stars, 3.4K forks","lastPushed":"16d since push","license":"Unknown","repository":"https://github.com/NirDiamant/RAG_Techniques","install":"npx skills add NirDiamant/RAG_Techniques","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["rag-knowledge","semantic-search","retrieval","knowledge","agentic-rag","ai"],"known_risks":["License is unclear","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"16d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use RAG Techniques 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: 93/100 Safe to try","Safety: 77/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"nirdiamant-rag-techniques (RAG Techniques)","install_command":"npx skills add NirDiamant/RAG_Techniques","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":"nirdiamant-rag-techniques","task":"Use RAG Techniques 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/nirdiamant-rag-techniques","api":"https://www.openagentskill.com/api/agent/skills/nirdiamant-rag-techniques","audit":"https://www.openagentskill.com/skills/nirdiamant-rag-techniques/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=nirdiamant-rag-techniques&task=Use%20RAG%20Techniques%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20RAG%20Techniques%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20RAG%20Techniques%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/nirdiamant-rag-techniques/install","manifest":"https://www.openagentskill.com/api/registry/manifest/nirdiamant-rag-techniques"}},"platforms":["Jupyter Notebook","Semantic Search","Claude Code","OpenAI Agents","LangChain"],"use_cases":[{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"install":"npx skills add NirDiamant/RAG_Techniques","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add NirDiamant/RAG_Techniques","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 \"RAG Techniques\" agent skill from https://github.com/NirDiamant/RAG_Techniques. 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: This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.","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 \"RAG Techniques\" as a Claude Code skill from https://github.com/NirDiamant/RAG_Techniques. 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: This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.","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 \"RAG Techniques\" from https://github.com/NirDiamant/RAG_Techniques 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: This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/NirDiamant/RAG_Techniques","github_repo":"NirDiamant/RAG_Techniques","version":"1.0.0","license":"Unknown","updated_at":"2026-06-20T03:01:24.053611+00:00","canonical_key":"nirdiamant/rag_techniques","recommendation_reasons":["Matches task terms: llama","Strong GitHub adoption: 28,057 stars","Quality score 74/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/nirdiamant-rag-techniques","api":"https://www.openagentskill.com/api/agent/skills/nirdiamant-rag-techniques","install_api":"https://www.openagentskill.com/api/skills/nirdiamant-rag-techniques/install","audit":"https://www.openagentskill.com/skills/nirdiamant-rag-techniques/audit","repository":"https://github.com/NirDiamant/RAG_Techniques"}},{"rank":8,"match_score":10,"raw_match_score":77.8,"slug":"comet-ml-opik","name":"Opik","description":"Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.","tagline":"Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.","category":"development","tags":["llmops","developer-tools","evaluation","hacktoberfest","hacktoberfest2025","langchain","llama-index","llm","llm-evaluation","llm-observability"],"author":{"name":"comet-ml","verified":true,"url":"https://github.com/comet-ml"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"comet-ml/opik","creatorName":"comet-ml","creatorUrl":"https://github.com/comet-ml","sourceUrl":"https://github.com/comet-ml/opik","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/comet-ml-opik#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":19788,"forks":1538,"downloads":0,"rating":0,"review_count":0,"quality_score":73.27},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"20K","tone":"positive"},{"label":"Freshness","value":"8d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":93,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"20K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"20K stars, 1.5K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"8d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":90,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add comet-ml/opik"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/comet-ml/opik"},{"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":"20K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"20K stars, 1.5K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"8d since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add comet-ml/opik"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/comet-ml/opik"},{"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":"20K GitHub stars","repoActivity":"20K stars, 1.5K forks","lastPushed":"8d since push","license":"Apache-2.0","repository":"https://github.com/comet-ml/opik","install":"npx skills add comet-ml/opik","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add comet-ml/opik","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","8d since push"]},"agentCompatibility":["Python","LLMOps","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["No major trust warnings detected from available metadata"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["development","llmops","developer-tools","evaluation","hacktoberfest","hacktoberfest2025"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":[]},"safety":{"score":87,"level":"safe_to_install","label":"Safe to install with normal review","safety_tier":{"tier":"verified","label":"Verified","badge":"VERIFIED","summary":"Strong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","auto_install_policy":"allow","reasons":["Verified listing","Safe-to-try audit","87/100 agent safety score"]},"auto_install_allowed":true,"human_review_required":false,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":[],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"verified","label":"Verified","badge":"VERIFIED","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","reasons":["Verified listing","Safe-to-try audit","87/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"github-automation","title":"GitHub automation"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["Claude Code","LangChain","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add comet-ml/opik","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":19788,"starsLabel":"20K","forks":1538,"license":"Apache-2.0","qualityScore":100,"trustScore":93,"auditScore":95},"maintenance":{"status":"fresh","label":"8d since push","daysSincePush":8,"lastPushedAt":"2026-06-25T01:25:11+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":false,"notes":["No major risk signals from available metadata"]},"coverageTags":["Coding","Coding agents","development","llmops","developer-tools","evaluation","hacktoberfest","hacktoberfest2025"]},"audit":{"audit_score":95,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Coding agents","role":"Primary pick","primary_fit":"Coding agents","best_for":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"comet-ml-opik","name":"Opik","description":"Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.","category":"development","url":"https://www.openagentskill.com/skills/comet-ml-opik","repository":"https://github.com/comet-ml/opik","github_repo":"comet-ml/opik"},"suited_tasks":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","LLMOps","Codex","Claude Code","Cursor","OpenAgentSkill CLI","LangChain","CLI"],"install":{"command":"npx skills add comet-ml/opik","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add comet-ml/opik"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Opik\" agent skill from https://github.com/comet-ml/opik. 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: Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Opik\" as a Claude Code skill from https://github.com/comet-ml/opik. 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: Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Opik\" from https://github.com/comet-ml/opik 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: Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards."}],"handoff_url":"https://www.openagentskill.com/api/skills/comet-ml-opik/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/comet-ml-opik"},"trust":{"score":93,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"20K GitHub stars","repoActivity":"20K stars, 1.5K forks","lastPushed":"8d since push","license":"Apache-2.0","repository":"https://github.com/comet-ml/opik","install":"npx skills add comet-ml/opik","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["development","llmops","developer-tools","evaluation","hacktoberfest","hacktoberfest2025"],"known_risks":[]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":95,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety_gate":{"tier":"verified","label":"Verified","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"8d 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 Opik in an agent workflow","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","install_policy":"allow","minimum_review_before_use":["Trust: 93/100 Production candidate","Audit: 95/100 Safe to try","Safety: 87/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"comet-ml-opik (Opik)","install_command":"npx skills add comet-ml/opik","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":"comet-ml-opik","task":"Use Opik 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/comet-ml-opik","api":"https://www.openagentskill.com/api/agent/skills/comet-ml-opik","audit":"https://www.openagentskill.com/skills/comet-ml-opik/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=comet-ml-opik&task=Use%20Opik%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Opik%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Opik%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/comet-ml-opik/install","manifest":"https://www.openagentskill.com/api/registry/manifest/comet-ml-opik"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"comet-ml-opik","name":"Opik","description":"Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.","category":"development","url":"https://www.openagentskill.com/skills/comet-ml-opik","repository":"https://github.com/comet-ml/opik","github_repo":"comet-ml/opik"},"suited_tasks":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","LLMOps","Codex","Claude Code","Cursor","OpenAgentSkill CLI","LangChain","CLI"],"install":{"command":"npx skills add comet-ml/opik","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add comet-ml/opik"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Opik\" agent skill from https://github.com/comet-ml/opik. 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: Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Opik\" as a Claude Code skill from https://github.com/comet-ml/opik. 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: Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Opik\" from https://github.com/comet-ml/opik 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: Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards."}],"handoff_url":"https://www.openagentskill.com/api/skills/comet-ml-opik/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/comet-ml-opik"},"trust":{"score":93,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"20K GitHub stars","repoActivity":"20K stars, 1.5K forks","lastPushed":"8d since push","license":"Apache-2.0","repository":"https://github.com/comet-ml/opik","install":"npx skills add comet-ml/opik","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["development","llmops","developer-tools","evaluation","hacktoberfest","hacktoberfest2025"],"known_risks":[]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":95,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety_gate":{"tier":"verified","label":"Verified","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"8d 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 Opik in an agent workflow","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","install_policy":"allow","minimum_review_before_use":["Trust: 93/100 Production candidate","Audit: 95/100 Safe to try","Safety: 87/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"comet-ml-opik (Opik)","install_command":"npx skills add comet-ml/opik","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":"comet-ml-opik","task":"Use Opik 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/comet-ml-opik","api":"https://www.openagentskill.com/api/agent/skills/comet-ml-opik","audit":"https://www.openagentskill.com/skills/comet-ml-opik/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=comet-ml-opik&task=Use%20Opik%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Opik%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Opik%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/comet-ml-opik/install","manifest":"https://www.openagentskill.com/api/registry/manifest/comet-ml-opik"}},"platforms":["Python","LLMOps","Claude Code","LangChain"],"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"install":"npx skills add comet-ml/opik","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add comet-ml/opik","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 \"Opik\" agent skill from https://github.com/comet-ml/opik. 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: Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.","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 \"Opik\" as a Claude Code skill from https://github.com/comet-ml/opik. 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: Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.","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 \"Opik\" from https://github.com/comet-ml/opik 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: Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/comet-ml/opik","github_repo":"comet-ml/opik","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-06-25T03:03:33.116599+00:00","canonical_key":"comet-ml/opik","recommendation_reasons":["Matches task terms: llama","Strong GitHub adoption: 19,788 stars","Quality score 73/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/comet-ml-opik","api":"https://www.openagentskill.com/api/agent/skills/comet-ml-opik","install_api":"https://www.openagentskill.com/api/skills/comet-ml-opik/install","audit":"https://www.openagentskill.com/skills/comet-ml-opik/audit","repository":"https://github.com/comet-ml/opik"}},{"rank":9,"match_score":10,"raw_match_score":77.5,"slug":"emcie-co-parlant","name":"Parlant","description":"Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.","tagline":"Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.","category":"agent-frameworks","tags":["agents","ai-agents","ai-alignment","customer-service","customer-success","gemini","genai","hacktoberfest","llama3","llm"],"author":{"name":"emcie-co","verified":true,"url":"https://github.com/emcie-co"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"emcie-co/parlant","creatorName":"emcie-co","creatorUrl":"https://github.com/emcie-co","sourceUrl":"https://github.com/emcie-co/parlant","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/emcie-co-parlant#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":18113,"forks":1536,"downloads":0,"rating":0,"review_count":0,"quality_score":73.01},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"18K","tone":"positive"},{"label":"Freshness","value":"21d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":94,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"18K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"18K stars, 1.5K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"21d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":90,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add emcie-co/parlant"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/emcie-co/parlant"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"18K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"18K stars, 1.5K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"21d since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add emcie-co/parlant"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/emcie-co/parlant"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":[],"evidence":{"stars":"18K GitHub stars","repoActivity":"18K stars, 1.5K forks","lastPushed":"21d since push","license":"Apache-2.0","repository":"https://github.com/emcie-co/parlant","install":"npx skills add emcie-co/parlant","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add emcie-co/parlant","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","21d since push"]},"agentCompatibility":["Python","AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["No major trust warnings detected from available metadata"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["agent-frameworks","agents","ai-agents","ai-alignment","customer-service","customer-success"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":[]},"safety":{"score":92,"level":"safe_to_install","label":"Safe to install with normal review","safety_tier":{"tier":"verified","label":"Verified","badge":"VERIFIED","summary":"Strong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","auto_install_policy":"allow","reasons":["Verified listing","Safe-to-try audit","92/100 agent safety score"]},"auto_install_allowed":true,"human_review_required":false,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":[],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"verified","label":"Verified","badge":"VERIFIED","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","reasons":["Verified listing","Safe-to-try audit","92/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"GitHub automation","description":"I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.","useCases":[{"slug":"github-automation","title":"GitHub automation"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","Python"],"install":{"ready":true,"command":"npx skills add emcie-co/parlant","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":18113,"starsLabel":"18K","forks":1536,"license":"Apache-2.0","qualityScore":100,"trustScore":94,"auditScore":96},"maintenance":{"status":"fresh","label":"21d since push","daysSincePush":21,"lastPushedAt":"2026-06-12T10:50:18+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":false,"notes":["No major risk signals from available metadata"]},"coverageTags":["Coding","GitHub automation","agent-frameworks","agents","ai-agents","ai-alignment","customer-service","customer-success"]},"audit":{"audit_score":96,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for GitHub automation","role":"Primary pick","primary_fit":"GitHub automation","best_for":["GitHub automation workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one GitHub automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"emcie-co-parlant","name":"Parlant","description":"Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/emcie-co-parlant","repository":"https://github.com/emcie-co/parlant","github_repo":"emcie-co/parlant"},"suited_tasks":["GitHub automation workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Python","AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add emcie-co/parlant","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add emcie-co/parlant"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Parlant\" agent skill from https://github.com/emcie-co/parlant. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Parlant\" as a Claude Code skill from https://github.com/emcie-co/parlant. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Parlant\" from https://github.com/emcie-co/parlant into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions."}],"handoff_url":"https://www.openagentskill.com/api/skills/emcie-co-parlant/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/emcie-co-parlant"},"trust":{"score":94,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"18K GitHub stars","repoActivity":"18K stars, 1.5K forks","lastPushed":"21d since push","license":"Apache-2.0","repository":"https://github.com/emcie-co/parlant","install":"npx skills add emcie-co/parlant","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["agent-frameworks","agents","ai-agents","ai-alignment","customer-service","customer-success"],"known_risks":[]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":96,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety_gate":{"tier":"verified","label":"Verified","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"21d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","No major trust warnings detected from available metadata","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Parlant in an agent workflow","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","install_policy":"allow","minimum_review_before_use":["Trust: 94/100 Production candidate","Audit: 96/100 Safe to try","Safety: 92/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"emcie-co-parlant (Parlant)","install_command":"npx skills add emcie-co/parlant","risk_summary":"Safe to try; Verified; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"emcie-co-parlant","task":"Use Parlant in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/emcie-co-parlant","api":"https://www.openagentskill.com/api/agent/skills/emcie-co-parlant","audit":"https://www.openagentskill.com/skills/emcie-co-parlant/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=emcie-co-parlant&task=Use%20Parlant%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Parlant%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Parlant%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/emcie-co-parlant/install","manifest":"https://www.openagentskill.com/api/registry/manifest/emcie-co-parlant"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"emcie-co-parlant","name":"Parlant","description":"Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/emcie-co-parlant","repository":"https://github.com/emcie-co/parlant","github_repo":"emcie-co/parlant"},"suited_tasks":["GitHub automation workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Python","AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add emcie-co/parlant","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add emcie-co/parlant"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Parlant\" agent skill from https://github.com/emcie-co/parlant. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Parlant\" as a Claude Code skill from https://github.com/emcie-co/parlant. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Parlant\" from https://github.com/emcie-co/parlant into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions."}],"handoff_url":"https://www.openagentskill.com/api/skills/emcie-co-parlant/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/emcie-co-parlant"},"trust":{"score":94,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"18K GitHub stars","repoActivity":"18K stars, 1.5K forks","lastPushed":"21d since push","license":"Apache-2.0","repository":"https://github.com/emcie-co/parlant","install":"npx skills add emcie-co/parlant","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["agent-frameworks","agents","ai-agents","ai-alignment","customer-service","customer-success"],"known_risks":[]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":96,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety_gate":{"tier":"verified","label":"Verified","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"21d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","No major trust warnings detected from available metadata","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Parlant in an agent workflow","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","install_policy":"allow","minimum_review_before_use":["Trust: 94/100 Production candidate","Audit: 96/100 Safe to try","Safety: 92/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"emcie-co-parlant (Parlant)","install_command":"npx skills add emcie-co/parlant","risk_summary":"Safe to try; Verified; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"emcie-co-parlant","task":"Use Parlant in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/emcie-co-parlant","api":"https://www.openagentskill.com/api/agent/skills/emcie-co-parlant","audit":"https://www.openagentskill.com/skills/emcie-co-parlant/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=emcie-co-parlant&task=Use%20Parlant%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Parlant%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Parlant%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/emcie-co-parlant/install","manifest":"https://www.openagentskill.com/api/registry/manifest/emcie-co-parlant"}},"platforms":["Python","AI Agents","Claude Code"],"use_cases":[{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"sports-analytics","title":"Sports analytics","url":"https://www.openagentskill.com/use-cases/sports-analytics"}],"install":"npx skills add emcie-co/parlant","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add emcie-co/parlant","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Parlant\" agent skill from https://github.com/emcie-co/parlant. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Parlant\" as a Claude Code skill from https://github.com/emcie-co/parlant. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Parlant\" from https://github.com/emcie-co/parlant into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/emcie-co/parlant","github_repo":"emcie-co/parlant","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-06-13T03:01:54.678991+00:00","canonical_key":"emcie-co/parlant","recommendation_reasons":["Matches task terms: llama","Strong GitHub adoption: 18,113 stars","Quality score 73/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/emcie-co-parlant","api":"https://www.openagentskill.com/api/agent/skills/emcie-co-parlant","install_api":"https://www.openagentskill.com/api/skills/emcie-co-parlant/install","audit":"https://www.openagentskill.com/skills/emcie-co-parlant/audit","repository":"https://github.com/emcie-co/parlant"}},{"rank":10,"match_score":9,"raw_match_score":77.2,"slug":"kanaries-pygwalker","name":"Pygwalker","description":"PyGWalker: Turn your dataframe into an interactive UI for visual analysis","tagline":"PyGWalker: Turn your dataframe into an interactive UI for visual analysis","category":"data-analysis","tags":["data-analysis","analytics","data-exploration","dataframe","matplotlib","pandas","plotly","tableau","tableau-alternative","visualization"],"author":{"name":"Kanaries","verified":true,"url":"https://github.com/Kanaries"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"Kanaries/pygwalker","creatorName":"Kanaries","creatorUrl":"https://github.com/Kanaries","sourceUrl":"https://github.com/Kanaries/pygwalker","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/kanaries-pygwalker#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":15890,"forks":879,"downloads":0,"rating":0,"review_count":0,"quality_score":72.61},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"16K","tone":"positive"},{"label":"Freshness","value":"13d 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":91,"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":"16K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":92,"weight":0.08,"status":"pass","detail":"16K stars, 879 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"13d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":74,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add Kanaries/pygwalker"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/Kanaries/pygwalker"},{"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":"16K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"16K stars, 879 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"13d 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 Kanaries/pygwalker"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/Kanaries/pygwalker"},{"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":"16K GitHub stars","repoActivity":"16K stars, 879 forks","lastPushed":"13d since push","license":"Apache-2.0","repository":"https://github.com/Kanaries/pygwalker","install":"npx skills add Kanaries/pygwalker","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add Kanaries/pygwalker","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","13d since push"]},"agentCompatibility":["Python","Data Analysis","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["No major trust warnings detected from available metadata"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["data-analysis","analytics","data-exploration","dataframe","matplotlib","pandas"],"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":86,"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","86/100 agent safety score"]},"auto_install_allowed":true,"human_review_required":false,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":[],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"verified","label":"Verified","badge":"VERIFIED","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","reasons":["Verified listing","Safe-to-try audit","86/100 agent safety score"]},"supply_profile":{"track":{"slug":"data","label":"Data, BI, and analytics","shortLabel":"Data","description":"CSV, SQL, notebooks, dashboards, data pipelines, BI, ETL, and spreadsheet analysis."},"scenario":{"label":"Data analysis","description":"I need my agent to analyze CSV data, produce insights, and explain trends.","useCases":[{"slug":"data-analysis","title":"Data analysis"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","Python"],"install":{"ready":true,"command":"npx skills add Kanaries/pygwalker","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":15890,"starsLabel":"16K","forks":879,"license":"Apache-2.0","qualityScore":100,"trustScore":91,"auditScore":94},"maintenance":{"status":"fresh","label":"13d since push","daysSincePush":13,"lastPushedAt":"2026-06-20T16:33:11+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":false,"notes":["No major risk signals from available metadata"]},"coverageTags":["Data","Data analysis","data-analysis","analytics","data-exploration","dataframe","matplotlib","pandas"]},"audit":{"audit_score":94,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Data analysis","role":"Primary pick","primary_fit":"Data analysis","best_for":["Data analysis workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Data analysis task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"kanaries-pygwalker","name":"Pygwalker","description":"PyGWalker: Turn your dataframe into an interactive UI for visual analysis","category":"data-analysis","url":"https://www.openagentskill.com/skills/kanaries-pygwalker","repository":"https://github.com/Kanaries/pygwalker","github_repo":"Kanaries/pygwalker"},"suited_tasks":["Data analysis workflows","Claude Code teams","teams that value GitHub adoption signals","Load tabular data","Calculate trends","Summarize findings clearly","Inspect source files","Explain architecture"],"suited_agents":["Python","Data Analysis","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add Kanaries/pygwalker","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add Kanaries/pygwalker"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Pygwalker\" agent skill from https://github.com/Kanaries/pygwalker. 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: PyGWalker: Turn your dataframe into an interactive UI for visual analysis"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Pygwalker\" as a Claude Code skill from https://github.com/Kanaries/pygwalker. 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: PyGWalker: Turn your dataframe into an interactive UI for visual analysis"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Pygwalker\" from https://github.com/Kanaries/pygwalker 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: PyGWalker: Turn your dataframe into an interactive UI for visual analysis"}],"handoff_url":"https://www.openagentskill.com/api/skills/kanaries-pygwalker/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/kanaries-pygwalker"},"trust":{"score":91,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"16K GitHub stars","repoActivity":"16K stars, 879 forks","lastPushed":"13d since push","license":"Apache-2.0","repository":"https://github.com/Kanaries/pygwalker","install":"npx skills add Kanaries/pygwalker","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["data-analysis","analytics","data-exploration","dataframe","matplotlib","pandas"],"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":94,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety_gate":{"tier":"verified","label":"Verified","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Data, BI, and analytics","scenario":"Data analysis","maintenance":"13d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","No major trust warnings detected from available metadata","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Pygwalker 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: 91/100 Production candidate","Audit: 94/100 Safe to try","Safety: 86/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"kanaries-pygwalker (Pygwalker)","install_command":"npx skills add Kanaries/pygwalker","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":"kanaries-pygwalker","task":"Use Pygwalker 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/kanaries-pygwalker","api":"https://www.openagentskill.com/api/agent/skills/kanaries-pygwalker","audit":"https://www.openagentskill.com/skills/kanaries-pygwalker/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=kanaries-pygwalker&task=Use%20Pygwalker%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Pygwalker%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Pygwalker%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/kanaries-pygwalker/install","manifest":"https://www.openagentskill.com/api/registry/manifest/kanaries-pygwalker"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"kanaries-pygwalker","name":"Pygwalker","description":"PyGWalker: Turn your dataframe into an interactive UI for visual analysis","category":"data-analysis","url":"https://www.openagentskill.com/skills/kanaries-pygwalker","repository":"https://github.com/Kanaries/pygwalker","github_repo":"Kanaries/pygwalker"},"suited_tasks":["Data analysis workflows","Claude Code teams","teams that value GitHub adoption signals","Load tabular data","Calculate trends","Summarize findings clearly","Inspect source files","Explain architecture"],"suited_agents":["Python","Data Analysis","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add Kanaries/pygwalker","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add Kanaries/pygwalker"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Pygwalker\" agent skill from https://github.com/Kanaries/pygwalker. 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: PyGWalker: Turn your dataframe into an interactive UI for visual analysis"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Pygwalker\" as a Claude Code skill from https://github.com/Kanaries/pygwalker. 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: PyGWalker: Turn your dataframe into an interactive UI for visual analysis"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Pygwalker\" from https://github.com/Kanaries/pygwalker 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: PyGWalker: Turn your dataframe into an interactive UI for visual analysis"}],"handoff_url":"https://www.openagentskill.com/api/skills/kanaries-pygwalker/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/kanaries-pygwalker"},"trust":{"score":91,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"16K GitHub stars","repoActivity":"16K stars, 879 forks","lastPushed":"13d since push","license":"Apache-2.0","repository":"https://github.com/Kanaries/pygwalker","install":"npx skills add Kanaries/pygwalker","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["data-analysis","analytics","data-exploration","dataframe","matplotlib","pandas"],"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":94,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety_gate":{"tier":"verified","label":"Verified","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Data, BI, and analytics","scenario":"Data analysis","maintenance":"13d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","No major trust warnings detected from available metadata","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Pygwalker 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: 91/100 Production candidate","Audit: 94/100 Safe to try","Safety: 86/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"kanaries-pygwalker (Pygwalker)","install_command":"npx skills add Kanaries/pygwalker","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":"kanaries-pygwalker","task":"Use Pygwalker 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/kanaries-pygwalker","api":"https://www.openagentskill.com/api/agent/skills/kanaries-pygwalker","audit":"https://www.openagentskill.com/skills/kanaries-pygwalker/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=kanaries-pygwalker&task=Use%20Pygwalker%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Pygwalker%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Pygwalker%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/kanaries-pygwalker/install","manifest":"https://www.openagentskill.com/api/registry/manifest/kanaries-pygwalker"}},"platforms":["Python","Data Analysis","Claude Code"],"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":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"install":"npx skills add Kanaries/pygwalker","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add Kanaries/pygwalker","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 \"Pygwalker\" agent skill from https://github.com/Kanaries/pygwalker. 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: PyGWalker: Turn your dataframe into an interactive UI for visual analysis","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 \"Pygwalker\" as a Claude Code skill from https://github.com/Kanaries/pygwalker. 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: PyGWalker: Turn your dataframe into an interactive UI for visual analysis","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 \"Pygwalker\" from https://github.com/Kanaries/pygwalker 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: PyGWalker: Turn your dataframe into an interactive UI for visual analysis","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/Kanaries/pygwalker","github_repo":"Kanaries/pygwalker","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-06-21T03:01:19.341696+00:00","canonical_key":"kanaries/pygwalker","recommendation_reasons":["Matches task terms: lora","Strong GitHub adoption: 15,890 stars","Quality score 73/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/kanaries-pygwalker","api":"https://www.openagentskill.com/api/agent/skills/kanaries-pygwalker","install_api":"https://www.openagentskill.com/api/skills/kanaries-pygwalker/install","audit":"https://www.openagentskill.com/skills/kanaries-pygwalker/audit","repository":"https://github.com/Kanaries/pygwalker"}}],"meta":{"endpoint":"/api/skills/search","canonical_agent_endpoint":"/api/agent/resolve","safety_policy":"Blocked candidates are excluded by default. Pass include_blocked=true only for manual audit workflows.","agent_friendly":true,"api_version":"1.0","generated_at":"2026-07-03T23:53:32.430Z"}}