{"query":"The Pair","filters":{"category":null,"platform":null,"track":null,"safety":null,"include_blocked":false,"min_stars":0},"total":10,"skills":[{"rank":1,"match_type":"exact","match_score":99,"raw_match_score":656.8,"semantic_relevance":100,"slug":"timwuhaotian-the-pair","name":"The Pair","description":"Open-source AI pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch AI hallucinations. Works with Claude Code, Codex, Gemini & opencode. macOS / Windows / Linux.","tagline":"Open-source AI pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch AI hallucinations. Works with Claude Code, Codex, Gemini & opencode. macOS / Windows / Linux.","category":"coding-agents","tags":["developer-tools","automation","coding","ai","ai-agents","ai-code-review","claude-code","codex","codex-cli","gemini"],"author":{"name":"timwuhaotian","verified":false,"url":"https://github.com/timwuhaotian"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"timwuhaotian/the-pair","creatorName":"timwuhaotian","creatorUrl":"https://github.com/timwuhaotian","sourceUrl":"https://github.com/timwuhaotian/the-pair","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/timwuhaotian-the-pair#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":339,"forks":25,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":48.42},"quality":{"score":71,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"339","tone":"neutral"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":75,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"339 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"339 stars, 25 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"command execution surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add timwuhaotian/the-pair"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":76,"weight":0.07,"status":"info","detail":"shell or command execution"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/timwuhaotian/the-pair"},{"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":"339 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"339 stars, 25 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface"},{"status":"pass","label":"Install availability","detail":"npx skills add timwuhaotian/the-pair"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"shell or command execution"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/timwuhaotian/the-pair"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 339 stars, 25 forks; issue activity unavailable in current metadata"],"evidence":{"stars":"339 GitHub stars","repoActivity":"339 stars, 25 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/timwuhaotian/the-pair","install":"npx skills add timwuhaotian/the-pair","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add timwuhaotian/the-pair","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["TypeScript","Developer Tools","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 339 stars, 25 forks; issue activity unavailable in current metadata"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["coding-agents","developer-tools","automation","coding","ai","ai-agents"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 339 stars, 25 forks; issue activity unavailable in current metadata"]},"safety":{"score":55,"level":"review_before_install","label":"Review before 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":["High-risk permission hints: Shell or command execution","55/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"shell","label":"Shell or command execution","reason":"Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.","severity":"high"},{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["High-risk permission hints: Shell or command execution","Quality score needs review"],"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":["High-risk permission hints: Shell or command execution","55/100 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":"local-desktop","title":"Local desktop"}]},"applicableAgents":["Claude Code","OpenAI Agents","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add timwuhaotian/the-pair","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":339,"starsLabel":"339","forks":25,"license":"Apache-2.0","qualityScore":71,"trustScore":75,"auditScore":79},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":67,"lastPushedAt":"2026-06-16T17:15:06+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 339 stars, 25 forks; issue activity unavailable in current metadata","Needs review"]},"coverageTags":["Coding","Coding agents","coding-agents","developer-tools","automation","ai","ai-agents","ai-code-review"]},"audit":{"audit_score":79,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 339 stars, 25 forks; issue activity unavailable in current metadata"]},"decision":{"readiness_score":70,"readiness_label":"Prototype first","headline":"Fallback candidate for Coding agents","role":"Fallback candidate","primary_fit":"Coding agents","best_for":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one 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":"timwuhaotian-the-pair","name":"The Pair","description":"Open-source AI pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch AI hallucinations. Works with Claude Code, Codex, Gemini & opencode. macOS / Windows / Linux.","category":"coding-agents","url":"https://www.openagentskill.com/skills/timwuhaotian-the-pair","repository":"https://github.com/timwuhaotian/the-pair","github_repo":"timwuhaotian/the-pair"},"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Inspect repository metadata","Compare code changes"],"suited_agents":["TypeScript","Developer Tools","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add timwuhaotian/the-pair","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install timwuhaotian-the-pair"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"The Pair\" agent skill from https://github.com/timwuhaotian/the-pair. 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 pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch AI hallucinations. Works with Claude Code, Codex, Gemini & opencode. macOS / Windows / Linux. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"timwuhaotian-the-pair\",\"task\":\"Install The Pair\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"The Pair\" as a Claude Code skill from https://github.com/timwuhaotian/the-pair. 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 pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch AI hallucinations. Works with Claude Code, Codex, Gemini & opencode. macOS / Windows / Linux. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"timwuhaotian-the-pair\",\"task\":\"Install The Pair\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"The Pair\" from https://github.com/timwuhaotian/the-pair 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 pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch AI hallucinations. Works with Claude Code, Codex, Gemini & opencode. macOS / Windows / Linux. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"timwuhaotian-the-pair\",\"task\":\"Install The Pair\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/timwuhaotian-the-pair/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/timwuhaotian-the-pair"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"339 GitHub stars","repoActivity":"339 stars, 25 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/timwuhaotian/the-pair","install":"npx skills add timwuhaotian/the-pair","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["coding-agents","developer-tools","automation","coding","ai","ai-agents"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 339 stars, 25 forks; issue activity unavailable in current metadata"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":79,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 339 stars, 25 forks; issue activity unavailable in current metadata"]},"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":71,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution","Quality score needs review","Documentation summary is thin","Stars/forks activity: 339 stars, 25 forks; issue activity unavailable in current metadata","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use The Pair in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 79/100 Needs review","Safety: 55/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"timwuhaotian-the-pair (The Pair)","install_command":"npx skills add timwuhaotian/the-pair","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":"timwuhaotian-the-pair","task":"Use The Pair 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/timwuhaotian-the-pair","api":"https://www.openagentskill.com/api/agent/skills/timwuhaotian-the-pair","audit":"https://www.openagentskill.com/skills/timwuhaotian-the-pair/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=timwuhaotian-the-pair&task=Use%20The%20Pair%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20The%20Pair%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20The%20Pair%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/timwuhaotian-the-pair/install","manifest":"https://www.openagentskill.com/api/registry/manifest/timwuhaotian-the-pair"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"timwuhaotian-the-pair","name":"The Pair","description":"Open-source AI pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch AI hallucinations. Works with Claude Code, Codex, Gemini & opencode. macOS / Windows / Linux.","category":"coding-agents","url":"https://www.openagentskill.com/skills/timwuhaotian-the-pair","repository":"https://github.com/timwuhaotian/the-pair","github_repo":"timwuhaotian/the-pair"},"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Inspect repository metadata","Compare code changes"],"suited_agents":["TypeScript","Developer Tools","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add timwuhaotian/the-pair","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install timwuhaotian-the-pair"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"The Pair\" agent skill from https://github.com/timwuhaotian/the-pair. 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 pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch AI hallucinations. Works with Claude Code, Codex, Gemini & opencode. macOS / Windows / Linux. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"timwuhaotian-the-pair\",\"task\":\"Install The Pair\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"The Pair\" as a Claude Code skill from https://github.com/timwuhaotian/the-pair. 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 pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch AI hallucinations. Works with Claude Code, Codex, Gemini & opencode. macOS / Windows / Linux. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"timwuhaotian-the-pair\",\"task\":\"Install The Pair\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"The Pair\" from https://github.com/timwuhaotian/the-pair 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 pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch AI hallucinations. Works with Claude Code, Codex, Gemini & opencode. macOS / Windows / Linux. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"timwuhaotian-the-pair\",\"task\":\"Install The Pair\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/timwuhaotian-the-pair/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/timwuhaotian-the-pair"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"339 GitHub stars","repoActivity":"339 stars, 25 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/timwuhaotian/the-pair","install":"npx skills add timwuhaotian/the-pair","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["coding-agents","developer-tools","automation","coding","ai","ai-agents"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 339 stars, 25 forks; issue activity unavailable in current metadata"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":79,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 339 stars, 25 forks; issue activity unavailable in current metadata"]},"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":71,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution","Quality score needs review","Documentation summary is thin","Stars/forks activity: 339 stars, 25 forks; issue activity unavailable in current metadata","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use The Pair in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 79/100 Needs review","Safety: 55/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"timwuhaotian-the-pair (The Pair)","install_command":"npx skills add timwuhaotian/the-pair","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":"timwuhaotian-the-pair","task":"Use The Pair 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/timwuhaotian-the-pair","api":"https://www.openagentskill.com/api/agent/skills/timwuhaotian-the-pair","audit":"https://www.openagentskill.com/skills/timwuhaotian-the-pair/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=timwuhaotian-the-pair&task=Use%20The%20Pair%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20The%20Pair%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20The%20Pair%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/timwuhaotian-the-pair/install","manifest":"https://www.openagentskill.com/api/registry/manifest/timwuhaotian-the-pair"}},"platforms":["TypeScript","Developer Tools","Claude Code","OpenAI Agents"],"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":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"install":"npx skills add timwuhaotian/the-pair","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install timwuhaotian-the-pair","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"The Pair\" agent skill from https://github.com/timwuhaotian/the-pair. 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 pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch AI hallucinations. Works with Claude Code, Codex, Gemini & opencode. macOS / Windows / Linux. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"timwuhaotian-the-pair\",\"task\":\"Install The Pair\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"The Pair\" as a Claude Code skill from https://github.com/timwuhaotian/the-pair. 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 pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch AI hallucinations. Works with Claude Code, Codex, Gemini & opencode. macOS / Windows / Linux. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"timwuhaotian-the-pair\",\"task\":\"Install The Pair\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"The Pair\" from https://github.com/timwuhaotian/the-pair 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 pair programming for desktop: a Mentor + Executor agent cross-check each other's code to catch AI hallucinations. Works with Claude Code, Codex, Gemini & opencode. macOS / Windows / Linux. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"timwuhaotian-the-pair\",\"task\":\"Install The Pair\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/timwuhaotian/the-pair","github_repo":"timwuhaotian/the-pair","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"timwuhaotian/the-pair","recommendation_reasons":["Matches task terms: pair","Install handoff is available","Repository freshness signal is available","Registry match score 99"],"urls":{"web":"https://www.openagentskill.com/skills/timwuhaotian-the-pair","api":"https://www.openagentskill.com/api/agent/skills/timwuhaotian-the-pair","install_api":"https://www.openagentskill.com/api/skills/timwuhaotian-the-pair/install","audit":"https://www.openagentskill.com/skills/timwuhaotian-the-pair/audit","repository":"https://github.com/timwuhaotian/the-pair"}},{"rank":2,"match_type":"related","match_score":16,"raw_match_score":106.5,"semantic_relevance":30,"slug":"nju-websoft-paircoder","name":"PairCoder","description":"A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement, ASE 2024  (Distinguished Paper Award)","tagline":"A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement, ASE 2024  (Distinguished Paper Award)","category":"agent-frameworks","tags":["llm-agent","agents","code-generation","large-language-models","multi-agent-system","pair-programing","program-synthesis","python","github"],"author":{"name":"nju-websoft","verified":false,"url":"https://github.com/nju-websoft"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"nju-websoft/PairCoder","creatorName":"nju-websoft","creatorUrl":"https://github.com/nju-websoft","sourceUrl":"https://github.com/nju-websoft/PairCoder","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/nju-websoft-paircoder#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":112,"forks":13,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":33.07},"quality":{"score":41,"tier":"review","label":"Needs review","summary":"Inspect the repository carefully before adding it to an agent workflow.","signals":[{"label":"GitHub stars","value":"112","tone":"neutral"},{"label":"Freshness","value":"2y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"GPL-3.0","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":72,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"112 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"112 stars, 13 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":38,"weight":0.14,"status":"fail","detail":"2y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"GPL-3.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":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 nju-websoft/PairCoder"},{"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/nju-websoft/PairCoder"},{"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":"112 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"112 stars, 13 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"2y since push"},{"status":"pass","label":"License clarity","detail":"GPL-3.0"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add nju-websoft/PairCoder"},{"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/nju-websoft/PairCoder"},{"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":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 112 stars, 13 forks; issue activity unavailable in current metadata","Recent maintenance: 2y since push"],"evidence":{"stars":"112 GitHub stars","repoActivity":"112 stars, 13 forks","lastPushed":"2y since push","license":"GPL-3.0","repository":"https://github.com/nju-websoft/PairCoder","install":"npx skills add nju-websoft/PairCoder","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add nju-websoft/PairCoder","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2y since push"]},"agentCompatibility":["Python","LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 112 stars, 13 forks; issue activity unavailable in current metadata","Recent maintenance: 2y since push"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["agent-frameworks","llm-agent","agents","code-generation","large-language-models","multi-agent-system"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 112 stars, 13 forks; issue activity unavailable in current metadata","Recent maintenance: 2y since push"]},"safety":{"score":52,"level":"avoid_auto_install","label":"Avoid automatic install","safety_tier":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","summary":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","auto_install_policy":"review","reasons":["Repository appears stale","52/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Repository appears stale"],"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":["Repository appears stale","52/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"github-automation","title":"GitHub automation"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add nju-websoft/PairCoder","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":112,"starsLabel":"112","forks":13,"license":"GPL-3.0","qualityScore":41,"trustScore":72,"auditScore":64},"maintenance":{"status":"stale","label":"2y since push","daysSincePush":632,"lastPushedAt":"2024-11-29T04:51:42+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 112 stars, 13 forks; issue activity unavailable in current metadata"]},"coverageTags":["Coding","Coding agents","agent-frameworks","llm-agent","agents","code-generation","large-language-models","multi-agent-system"]},"audit":{"audit_score":64,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 112 stars, 13 forks; issue activity unavailable in current metadata"]},"decision":{"readiness_score":31,"readiness_label":"Needs manual review","headline":"Needs validation for Coding agents","role":"Needs validation","primary_fit":"Coding agents","best_for":["Coding agents workflows","general agent builders","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":"nju-websoft-paircoder","name":"PairCoder","description":"A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement, ASE 2024  (Distinguished Paper Award)","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/nju-websoft-paircoder","repository":"https://github.com/nju-websoft/PairCoder","github_repo":"nju-websoft/PairCoder"},"suited_tasks":["Coding agents workflows","general agent builders","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add nju-websoft/PairCoder","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install nju-websoft-paircoder"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"PairCoder\" agent skill from https://github.com/nju-websoft/PairCoder. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement, ASE 2024 (Distinguished Paper Award) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"nju-websoft-paircoder\",\"task\":\"Install PairCoder\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"PairCoder\" as a Claude Code skill from https://github.com/nju-websoft/PairCoder. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement, ASE 2024 (Distinguished Paper Award) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"nju-websoft-paircoder\",\"task\":\"Install PairCoder\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"PairCoder\" from https://github.com/nju-websoft/PairCoder into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement, ASE 2024 (Distinguished Paper Award) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"nju-websoft-paircoder\",\"task\":\"Install PairCoder\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/nju-websoft-paircoder/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/nju-websoft-paircoder"},"trust":{"score":72,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"112 GitHub stars","repoActivity":"112 stars, 13 forks","lastPushed":"2y since push","license":"GPL-3.0","repository":"https://github.com/nju-websoft/PairCoder","install":"npx skills add nju-websoft/PairCoder","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["agent-frameworks","llm-agent","agents","code-generation","large-language-models","multi-agent-system"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 112 stars, 13 forks; issue activity unavailable in current metadata","Recent maintenance: 2y since push"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":64,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 112 stars, 13 forks; issue activity unavailable in current metadata","Recent maintenance: 2y since push"]},"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":41,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"2y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Repository appears stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 112 stars, 13 forks; issue activity unavailable in current metadata"],"agent_contract":{"task_input":"Use PairCoder 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: 72/100 Strong shortlist","Audit: 64/100 Needs review","Safety: 52/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"nju-websoft-paircoder (PairCoder)","install_command":"npx skills add nju-websoft/PairCoder","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":"nju-websoft-paircoder","task":"Use PairCoder 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/nju-websoft-paircoder","api":"https://www.openagentskill.com/api/agent/skills/nju-websoft-paircoder","audit":"https://www.openagentskill.com/skills/nju-websoft-paircoder/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=nju-websoft-paircoder&task=Use%20PairCoder%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20PairCoder%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20PairCoder%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/nju-websoft-paircoder/install","manifest":"https://www.openagentskill.com/api/registry/manifest/nju-websoft-paircoder"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"nju-websoft-paircoder","name":"PairCoder","description":"A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement, ASE 2024  (Distinguished Paper Award)","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/nju-websoft-paircoder","repository":"https://github.com/nju-websoft/PairCoder","github_repo":"nju-websoft/PairCoder"},"suited_tasks":["Coding agents workflows","general agent builders","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add nju-websoft/PairCoder","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install nju-websoft-paircoder"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"PairCoder\" agent skill from https://github.com/nju-websoft/PairCoder. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement, ASE 2024 (Distinguished Paper Award) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"nju-websoft-paircoder\",\"task\":\"Install PairCoder\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"PairCoder\" as a Claude Code skill from https://github.com/nju-websoft/PairCoder. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement, ASE 2024 (Distinguished Paper Award) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"nju-websoft-paircoder\",\"task\":\"Install PairCoder\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"PairCoder\" from https://github.com/nju-websoft/PairCoder into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement, ASE 2024 (Distinguished Paper Award) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"nju-websoft-paircoder\",\"task\":\"Install PairCoder\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/nju-websoft-paircoder/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/nju-websoft-paircoder"},"trust":{"score":72,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"112 GitHub stars","repoActivity":"112 stars, 13 forks","lastPushed":"2y since push","license":"GPL-3.0","repository":"https://github.com/nju-websoft/PairCoder","install":"npx skills add nju-websoft/PairCoder","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["agent-frameworks","llm-agent","agents","code-generation","large-language-models","multi-agent-system"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 112 stars, 13 forks; issue activity unavailable in current metadata","Recent maintenance: 2y since push"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":64,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 112 stars, 13 forks; issue activity unavailable in current metadata","Recent maintenance: 2y since push"]},"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":41,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"2y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Repository appears stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 112 stars, 13 forks; issue activity unavailable in current metadata"],"agent_contract":{"task_input":"Use PairCoder 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: 72/100 Strong shortlist","Audit: 64/100 Needs review","Safety: 52/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"nju-websoft-paircoder (PairCoder)","install_command":"npx skills add nju-websoft/PairCoder","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":"nju-websoft-paircoder","task":"Use PairCoder 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/nju-websoft-paircoder","api":"https://www.openagentskill.com/api/agent/skills/nju-websoft-paircoder","audit":"https://www.openagentskill.com/skills/nju-websoft-paircoder/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=nju-websoft-paircoder&task=Use%20PairCoder%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20PairCoder%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20PairCoder%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/nju-websoft-paircoder/install","manifest":"https://www.openagentskill.com/api/registry/manifest/nju-websoft-paircoder"}},"platforms":["Python","LLM"],"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"}],"install":"npx skills add nju-websoft/PairCoder","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install nju-websoft-paircoder","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"PairCoder\" agent skill from https://github.com/nju-websoft/PairCoder. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement, ASE 2024 (Distinguished Paper Award) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"nju-websoft-paircoder\",\"task\":\"Install PairCoder\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"PairCoder\" as a Claude Code skill from https://github.com/nju-websoft/PairCoder. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement, ASE 2024 (Distinguished Paper Award) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"nju-websoft-paircoder\",\"task\":\"Install PairCoder\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"PairCoder\" from https://github.com/nju-websoft/PairCoder into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A Pair Programming Framework for Code Generation via Multi-Plan Exploration and Feedback-Driven Refinement, ASE 2024 (Distinguished Paper Award) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"nju-websoft-paircoder\",\"task\":\"Install PairCoder\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/nju-websoft/PairCoder","github_repo":"nju-websoft/PairCoder","version":"1.0.0","license":"GPL-3.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"nju-websoft/paircoder","recommendation_reasons":["Matches task terms: pair","Install handoff is available","Repository freshness signal is available","Registry match score 16"],"urls":{"web":"https://www.openagentskill.com/skills/nju-websoft-paircoder","api":"https://www.openagentskill.com/api/agent/skills/nju-websoft-paircoder","install_api":"https://www.openagentskill.com/api/skills/nju-websoft-paircoder/install","audit":"https://www.openagentskill.com/skills/nju-websoft-paircoder/audit","repository":"https://github.com/nju-websoft/PairCoder"}},{"rank":3,"match_type":"related","match_score":13,"raw_match_score":88.7,"semantic_relevance":30,"slug":"marimo-team-marimo-pair","name":"Marimo Pair","description":"Drop agents inside running marimo notebook sessions","tagline":"Drop agents inside running marimo notebook sessions","category":"data-analysis","tags":["notebook","data-analysis","data","agents","ai","marimo","ml","shell","github"],"author":{"name":"marimo-team","verified":false,"url":"https://github.com/marimo-team"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"marimo-team/marimo-pair","creatorName":"marimo-team","creatorUrl":"https://github.com/marimo-team","sourceUrl":"https://github.com/marimo-team/marimo-pair","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/marimo-team-marimo-pair#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":329,"forks":20,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":48.33},"quality":{"score":70,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"329","tone":"neutral"},{"label":"Freshness","value":"3mo 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":73,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"329 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"329 stars, 20 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"3mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"command execution surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add marimo-team/marimo-pair"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":76,"weight":0.07,"status":"info","detail":"shell or command execution"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/marimo-team/marimo-pair"},{"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":"329 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"329 stars, 20 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface"},{"status":"pass","label":"Install availability","detail":"npx skills add marimo-team/marimo-pair"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"shell or command execution"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/marimo-team/marimo-pair"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 329 stars, 20 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"329 GitHub stars","repoActivity":"329 stars, 20 forks","lastPushed":"3mo since push","license":"Apache-2.0","repository":"https://github.com/marimo-team/marimo-pair","install":"npx skills add marimo-team/marimo-pair","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add marimo-team/marimo-pair","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3mo since push"]},"agentCompatibility":["Shell","Notebook","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 329 stars, 20 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["data-analysis","notebook","data","agents","ai","marimo"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 329 stars, 20 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":53,"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":["High-risk permission hints: Shell or command execution","53/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"shell","label":"Shell or command execution","reason":"Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.","severity":"high"},{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["High-risk permission hints: Shell or command execution","Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"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":["High-risk permission hints: Shell or command execution","53/100 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":"github-automation","title":"GitHub automation"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"research-agents","title":"Research agents"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Shell"],"install":{"ready":true,"command":"npx skills add marimo-team/marimo-pair","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":329,"starsLabel":"329","forks":20,"license":"Apache-2.0","qualityScore":70,"trustScore":73,"auditScore":77},"maintenance":{"status":"active","label":"3mo since push","daysSincePush":75,"lastPushedAt":"2026-06-08T15:02:10+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 329 stars, 20 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Needs review"]},"coverageTags":["Data","Data analysis","data-analysis","notebook","agents","ai","marimo","ml"]},"audit":{"audit_score":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 329 stars, 20 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"decision":{"readiness_score":69,"readiness_label":"Prototype first","headline":"Fallback candidate for GitHub automation","role":"Fallback candidate","primary_fit":"GitHub automation","best_for":["GitHub automation workflows","general agent builders","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one GitHub automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"marimo-team-marimo-pair","name":"Marimo Pair","description":"Drop agents inside running marimo notebook sessions","category":"data-analysis","url":"https://www.openagentskill.com/skills/marimo-team-marimo-pair","repository":"https://github.com/marimo-team/marimo-pair","github_repo":"marimo-team/marimo-pair"},"suited_tasks":["GitHub automation workflows","general agent builders","builders willing to evaluate younger projects","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Shell","Notebook","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add marimo-team/marimo-pair","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install marimo-team-marimo-pair"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Marimo Pair\" agent skill from https://github.com/marimo-team/marimo-pair. 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: Drop agents inside running marimo notebook sessions After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"marimo-team-marimo-pair\",\"task\":\"Install Marimo Pair\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Marimo Pair\" as a Claude Code skill from https://github.com/marimo-team/marimo-pair. 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: Drop agents inside running marimo notebook sessions After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"marimo-team-marimo-pair\",\"task\":\"Install Marimo Pair\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Marimo Pair\" from https://github.com/marimo-team/marimo-pair 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: Drop agents inside running marimo notebook sessions After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"marimo-team-marimo-pair\",\"task\":\"Install Marimo Pair\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/marimo-team-marimo-pair/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/marimo-team-marimo-pair"},"trust":{"score":73,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"329 GitHub stars","repoActivity":"329 stars, 20 forks","lastPushed":"3mo since push","license":"Apache-2.0","repository":"https://github.com/marimo-team/marimo-pair","install":"npx skills add marimo-team/marimo-pair","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["data-analysis","notebook","data","agents","ai","marimo"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 329 stars, 20 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 329 stars, 20 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":70,"label":"Strong"},"supply":{"track":"Data, BI, and analytics","scenario":"Data analysis","maintenance":"3mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution","Documentation summary is thin","Quality score needs review","Stars/forks activity: 329 stars, 20 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"agent_contract":{"task_input":"Use Marimo Pair 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: 73/100 Strong shortlist","Audit: 77/100 Needs review","Safety: 53/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"marimo-team-marimo-pair (Marimo Pair)","install_command":"npx skills add marimo-team/marimo-pair","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":"marimo-team-marimo-pair","task":"Use Marimo Pair 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/marimo-team-marimo-pair","api":"https://www.openagentskill.com/api/agent/skills/marimo-team-marimo-pair","audit":"https://www.openagentskill.com/skills/marimo-team-marimo-pair/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=marimo-team-marimo-pair&task=Use%20Marimo%20Pair%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Marimo%20Pair%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Marimo%20Pair%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/marimo-team-marimo-pair/install","manifest":"https://www.openagentskill.com/api/registry/manifest/marimo-team-marimo-pair"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"marimo-team-marimo-pair","name":"Marimo Pair","description":"Drop agents inside running marimo notebook sessions","category":"data-analysis","url":"https://www.openagentskill.com/skills/marimo-team-marimo-pair","repository":"https://github.com/marimo-team/marimo-pair","github_repo":"marimo-team/marimo-pair"},"suited_tasks":["GitHub automation workflows","general agent builders","builders willing to evaluate younger projects","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Shell","Notebook","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add marimo-team/marimo-pair","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install marimo-team-marimo-pair"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Marimo Pair\" agent skill from https://github.com/marimo-team/marimo-pair. 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: Drop agents inside running marimo notebook sessions After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"marimo-team-marimo-pair\",\"task\":\"Install Marimo Pair\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Marimo Pair\" as a Claude Code skill from https://github.com/marimo-team/marimo-pair. 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: Drop agents inside running marimo notebook sessions After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"marimo-team-marimo-pair\",\"task\":\"Install Marimo Pair\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Marimo Pair\" from https://github.com/marimo-team/marimo-pair 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: Drop agents inside running marimo notebook sessions After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"marimo-team-marimo-pair\",\"task\":\"Install Marimo Pair\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/marimo-team-marimo-pair/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/marimo-team-marimo-pair"},"trust":{"score":73,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"329 GitHub stars","repoActivity":"329 stars, 20 forks","lastPushed":"3mo since push","license":"Apache-2.0","repository":"https://github.com/marimo-team/marimo-pair","install":"npx skills add marimo-team/marimo-pair","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["data-analysis","notebook","data","agents","ai","marimo"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 329 stars, 20 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 329 stars, 20 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":70,"label":"Strong"},"supply":{"track":"Data, BI, and analytics","scenario":"Data analysis","maintenance":"3mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution","Documentation summary is thin","Quality score needs review","Stars/forks activity: 329 stars, 20 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"agent_contract":{"task_input":"Use Marimo Pair 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: 73/100 Strong shortlist","Audit: 77/100 Needs review","Safety: 53/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"marimo-team-marimo-pair (Marimo Pair)","install_command":"npx skills add marimo-team/marimo-pair","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":"marimo-team-marimo-pair","task":"Use Marimo Pair 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/marimo-team-marimo-pair","api":"https://www.openagentskill.com/api/agent/skills/marimo-team-marimo-pair","audit":"https://www.openagentskill.com/skills/marimo-team-marimo-pair/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=marimo-team-marimo-pair&task=Use%20Marimo%20Pair%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Marimo%20Pair%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Marimo%20Pair%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/marimo-team-marimo-pair/install","manifest":"https://www.openagentskill.com/api/registry/manifest/marimo-team-marimo-pair"}},"platforms":["Shell","Notebook"],"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":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"data-analysis","title":"Data analysis","url":"https://www.openagentskill.com/use-cases/data-analysis"}],"install":"npx skills add marimo-team/marimo-pair","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install marimo-team-marimo-pair","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Marimo Pair\" agent skill from https://github.com/marimo-team/marimo-pair. 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: Drop agents inside running marimo notebook sessions After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"marimo-team-marimo-pair\",\"task\":\"Install Marimo Pair\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Marimo Pair\" as a Claude Code skill from https://github.com/marimo-team/marimo-pair. 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: Drop agents inside running marimo notebook sessions After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"marimo-team-marimo-pair\",\"task\":\"Install Marimo Pair\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Marimo Pair\" from https://github.com/marimo-team/marimo-pair 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: Drop agents inside running marimo notebook sessions After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"marimo-team-marimo-pair\",\"task\":\"Install Marimo Pair\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/marimo-team/marimo-pair","github_repo":"marimo-team/marimo-pair","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"marimo-team/marimo-pair","recommendation_reasons":["Matches task terms: pair","Install handoff is available","Repository freshness signal is available","Registry match score 13"],"urls":{"web":"https://www.openagentskill.com/skills/marimo-team-marimo-pair","api":"https://www.openagentskill.com/api/agent/skills/marimo-team-marimo-pair","install_api":"https://www.openagentskill.com/api/skills/marimo-team-marimo-pair/install","audit":"https://www.openagentskill.com/skills/marimo-team-marimo-pair/audit","repository":"https://github.com/marimo-team/marimo-pair"}},{"rank":4,"match_type":"related","match_score":11,"raw_match_score":73.7,"semantic_relevance":30,"slug":"pair-code-lit","name":"Lit","description":"The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.","tagline":"The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.","category":"ml-automation","tags":["machine-learning","automation","ml-media","natural-language-processing","visualization","typescript","github"],"author":{"name":"PAIR-code","verified":true,"url":"https://github.com/PAIR-code"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"PAIR-code/lit","creatorName":"PAIR-code","creatorUrl":"https://github.com/PAIR-code","sourceUrl":"https://github.com/PAIR-code/lit","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/pair-code-lit#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":3655,"forks":370,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":63.64},"quality":{"score":95,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"3.7K","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":88,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"3.7K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"3.7K stars, 370 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add PAIR-code/lit"},{"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/PAIR-code/lit"},{"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":"3.7K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"3.7K stars, 370 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add PAIR-code/lit"},{"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/PAIR-code/lit"},{"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","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin"],"evidence":{"stars":"3.7K GitHub stars","repoActivity":"3.7K stars, 370 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/PAIR-code/lit","install":"npx skills add PAIR-code/lit","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add PAIR-code/lit","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["TypeScript","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["ml-automation","machine-learning","automation","ml-media","natural-language-processing","visualization"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin"]},"safety":{"score":79,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","79/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","79/100 agent safety score"]},"supply_profile":{"track":{"slug":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Multimodal media","description":"I need my agent to process images, video, or audio and extract useful information.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"github-automation","title":"GitHub automation"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","TypeScript"],"install":{"ready":true,"command":"npx skills add PAIR-code/lit","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":3655,"starsLabel":"3.7K","forks":370,"license":"Apache-2.0","qualityScore":95,"trustScore":88,"auditScore":91},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":74,"lastPushedAt":"2026-06-09T14:38:40+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Design","Multimodal media","ml-automation","machine-learning","automation","ml-media","natural-language-processing","visualization"]},"audit":{"audit_score":91,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Coding agents","role":"Primary pick","primary_fit":"Coding agents","best_for":["Coding agents workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"pair-code-lit","name":"Lit","description":"The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.","category":"ml-automation","url":"https://www.openagentskill.com/skills/pair-code-lit","repository":"https://github.com/PAIR-code/lit","github_repo":"PAIR-code/lit"},"suited_tasks":["Coding agents workflows","general agent builders","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Inspect repository metadata","Compare code changes"],"suited_agents":["TypeScript","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add PAIR-code/lit","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install pair-code-lit"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Lit\" agent skill from https://github.com/PAIR-code/lit. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"pair-code-lit\",\"task\":\"Install Lit\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Lit\" as a Claude Code skill from https://github.com/PAIR-code/lit. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"pair-code-lit\",\"task\":\"Install Lit\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Lit\" from https://github.com/PAIR-code/lit into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"pair-code-lit\",\"task\":\"Install Lit\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/pair-code-lit/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/pair-code-lit"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"3.7K GitHub stars","repoActivity":"3.7K stars, 370 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/PAIR-code/lit","install":"npx skills add PAIR-code/lit","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["ml-automation","machine-learning","automation","ml-media","natural-language-processing","visualization"],"known_risks":["Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":91,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":95,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Lit in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 88/100 Production candidate","Audit: 91/100 Safe to try","Safety: 79/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"pair-code-lit (Lit)","install_command":"npx skills add PAIR-code/lit","risk_summary":"Safe to try; Reviewed; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"pair-code-lit","task":"Use Lit 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/pair-code-lit","api":"https://www.openagentskill.com/api/agent/skills/pair-code-lit","audit":"https://www.openagentskill.com/skills/pair-code-lit/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=pair-code-lit&task=Use%20Lit%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Lit%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Lit%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/pair-code-lit/install","manifest":"https://www.openagentskill.com/api/registry/manifest/pair-code-lit"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"pair-code-lit","name":"Lit","description":"The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.","category":"ml-automation","url":"https://www.openagentskill.com/skills/pair-code-lit","repository":"https://github.com/PAIR-code/lit","github_repo":"PAIR-code/lit"},"suited_tasks":["Coding agents workflows","general agent builders","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Inspect repository metadata","Compare code changes"],"suited_agents":["TypeScript","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add PAIR-code/lit","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install pair-code-lit"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Lit\" agent skill from https://github.com/PAIR-code/lit. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"pair-code-lit\",\"task\":\"Install Lit\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Lit\" as a Claude Code skill from https://github.com/PAIR-code/lit. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"pair-code-lit\",\"task\":\"Install Lit\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Lit\" from https://github.com/PAIR-code/lit into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"pair-code-lit\",\"task\":\"Install Lit\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/pair-code-lit/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/pair-code-lit"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"3.7K GitHub stars","repoActivity":"3.7K stars, 370 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/PAIR-code/lit","install":"npx skills add PAIR-code/lit","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["ml-automation","machine-learning","automation","ml-media","natural-language-processing","visualization"],"known_risks":["Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":91,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":95,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Lit in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 88/100 Production candidate","Audit: 91/100 Safe to try","Safety: 79/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"pair-code-lit (Lit)","install_command":"npx skills add PAIR-code/lit","risk_summary":"Safe to try; Reviewed; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"pair-code-lit","task":"Use Lit 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/pair-code-lit","api":"https://www.openagentskill.com/api/agent/skills/pair-code-lit","audit":"https://www.openagentskill.com/skills/pair-code-lit/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=pair-code-lit&task=Use%20Lit%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Lit%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Lit%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/pair-code-lit/install","manifest":"https://www.openagentskill.com/api/registry/manifest/pair-code-lit"}},"platforms":["TypeScript","Machine Learning"],"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"install":"npx skills add PAIR-code/lit","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install pair-code-lit","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Lit\" agent skill from https://github.com/PAIR-code/lit. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"pair-code-lit\",\"task\":\"Install Lit\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Lit\" as a Claude Code skill from https://github.com/PAIR-code/lit. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"pair-code-lit\",\"task\":\"Install Lit\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Lit\" from https://github.com/PAIR-code/lit into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"pair-code-lit\",\"task\":\"Install Lit\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/PAIR-code/lit","github_repo":"PAIR-code/lit","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"pair-code/lit","recommendation_reasons":["Matches task terms: pair","Useful GitHub adoption: 3,655 stars","Install handoff is available","Repository freshness signal is available","Registry match score 11"],"urls":{"web":"https://www.openagentskill.com/skills/pair-code-lit","api":"https://www.openagentskill.com/api/agent/skills/pair-code-lit","install_api":"https://www.openagentskill.com/api/skills/pair-code-lit/install","audit":"https://www.openagentskill.com/skills/pair-code-lit/audit","repository":"https://github.com/PAIR-code/lit"}},{"rank":5,"match_type":"related","match_score":10,"raw_match_score":63.4,"semantic_relevance":30,"slug":"bjgreenberg-senior-engineering-partner","name":"Senior Engineering Partner","description":"A stack-agnostic Claude Code skill providing strict code review, pair programming, debugging, and mentoring with a security-first, phase-aware engineering workflow.","tagline":"A stack-agnostic Claude Code skill: strict code reviewer, pair programmer, debugger, and mentor (Python/Bash/Apps Script/JS). Security-first, phase-aware engineering discipline with a spec→plan→TDD→verify workflow.","category":"coding-agents","tags":["code-review","pair-programming","debugging","mentor","tdd"],"author":{"name":"bjgreenberg","verified":true,"url":"https://github.com/bjgreenberg"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"OpenAgentSkill auto-indexer","sourceDetail":"bjgreenberg/senior-engineering-partner","creatorName":"bjgreenberg","creatorUrl":"https://github.com/bjgreenberg","sourceUrl":"https://github.com/bjgreenberg/senior-engineering-partner","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/bjgreenberg-senior-engineering-partner#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":139,"forks":14,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":58.82},"quality":{"score":89,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"139","tone":"neutral"},{"label":"Freshness","value":"25d 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":81,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"139 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"139 stars, 14 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"25d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"command execution surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add bjgreenberg/senior-engineering-partner"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":76,"weight":0.07,"status":"info","detail":"shell or command execution"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/bjgreenberg/senior-engineering-partner"},{"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":"139 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"139 stars, 14 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"25d since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface"},{"status":"pass","label":"Install availability","detail":"npx skills add bjgreenberg/senior-engineering-partner"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"shell or command execution"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/bjgreenberg/senior-engineering-partner"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin","Stars/forks activity: 139 stars, 14 forks; issue activity unavailable in current metadata"],"evidence":{"stars":"139 GitHub stars","repoActivity":"139 stars, 14 forks","lastPushed":"25d since push","license":"Apache-2.0","repository":"https://github.com/bjgreenberg/senior-engineering-partner","install":"npx skills add bjgreenberg/senior-engineering-partner","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add bjgreenberg/senior-engineering-partner","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","25d since push"]},"agentCompatibility":["Python","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Documentation summary is thin","Stars/forks activity: 139 stars, 14 forks; issue activity unavailable in current metadata"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["coding-agents","code-review","pair-programming","debugging","mentor","tdd"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Documentation summary is thin","Stars/forks activity: 139 stars, 14 forks; issue activity unavailable in current metadata"]},"safety":{"score":64,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["High-risk permission hints: Shell or command execution","64/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"shell","label":"Shell or command execution","reason":"Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.","severity":"high"},{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["High-risk permission hints: Shell or command execution","Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["High-risk permission hints: Shell or command execution","64/100 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":"testing-qa","title":"Testing and QA"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","Python"],"install":{"ready":true,"command":"npx skills add bjgreenberg/senior-engineering-partner","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":139,"starsLabel":"139","forks":14,"license":"Apache-2.0","qualityScore":89,"trustScore":81,"auditScore":88},"maintenance":{"status":"fresh","label":"25d since push","daysSincePush":25,"lastPushedAt":"2026-07-28T12:48:38+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin","Stars/forks activity: 139 stars, 14 forks; issue activity unavailable in current metadata"]},"coverageTags":["Coding","Coding agents","coding-agents","code-review","pair-programming","debugging","mentor","tdd"]},"audit":{"audit_score":88,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","Stars/forks activity: 139 stars, 14 forks; issue activity unavailable in current metadata"]},"decision":{"readiness_score":88,"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","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"bjgreenberg-senior-engineering-partner","name":"Senior Engineering Partner","description":"A stack-agnostic Claude Code skill providing strict code review, pair programming, debugging, and mentoring with a security-first, phase-aware engineering workflow.","category":"coding-agents","url":"https://www.openagentskill.com/skills/bjgreenberg-senior-engineering-partner","repository":"https://github.com/bjgreenberg/senior-engineering-partner","github_repo":"bjgreenberg/senior-engineering-partner"},"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add bjgreenberg/senior-engineering-partner","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install bjgreenberg-senior-engineering-partner"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Senior Engineering Partner\" agent skill from https://github.com/bjgreenberg/senior-engineering-partner. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A stack-agnostic Claude Code skill providing strict code review, pair programming, debugging, and mentoring with a security-first, phase-aware engineering workflow. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bjgreenberg-senior-engineering-partner\",\"task\":\"Install Senior Engineering Partner\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Senior Engineering Partner\" as a Claude Code skill from https://github.com/bjgreenberg/senior-engineering-partner. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A stack-agnostic Claude Code skill providing strict code review, pair programming, debugging, and mentoring with a security-first, phase-aware engineering workflow. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bjgreenberg-senior-engineering-partner\",\"task\":\"Install Senior Engineering Partner\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Senior Engineering Partner\" from https://github.com/bjgreenberg/senior-engineering-partner into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A stack-agnostic Claude Code skill providing strict code review, pair programming, debugging, and mentoring with a security-first, phase-aware engineering workflow. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bjgreenberg-senior-engineering-partner\",\"task\":\"Install Senior Engineering Partner\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/bjgreenberg-senior-engineering-partner/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/bjgreenberg-senior-engineering-partner"},"trust":{"score":81,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"139 GitHub stars","repoActivity":"139 stars, 14 forks","lastPushed":"25d since push","license":"Apache-2.0","repository":"https://github.com/bjgreenberg/senior-engineering-partner","install":"npx skills add bjgreenberg/senior-engineering-partner","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["coding-agents","code-review","pair-programming","debugging","mentor","tdd"],"known_risks":["Documentation summary is thin","Stars/forks activity: 139 stars, 14 forks; issue activity unavailable in current metadata"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":88,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","Stars/forks activity: 139 stars, 14 forks; issue activity unavailable in current metadata"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":89,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"25d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution","Documentation summary is thin","Stars/forks activity: 139 stars, 14 forks; issue activity unavailable in current metadata","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Senior Engineering Partner in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 81/100 Strong shortlist","Audit: 88/100 Safe to try","Safety: 64/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"bjgreenberg-senior-engineering-partner (Senior Engineering Partner)","install_command":"npx skills add bjgreenberg/senior-engineering-partner","risk_summary":"Safe to try; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"bjgreenberg-senior-engineering-partner","task":"Use Senior Engineering Partner 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/bjgreenberg-senior-engineering-partner","api":"https://www.openagentskill.com/api/agent/skills/bjgreenberg-senior-engineering-partner","audit":"https://www.openagentskill.com/skills/bjgreenberg-senior-engineering-partner/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=bjgreenberg-senior-engineering-partner&task=Use%20Senior%20Engineering%20Partner%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Senior%20Engineering%20Partner%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Senior%20Engineering%20Partner%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/bjgreenberg-senior-engineering-partner/install","manifest":"https://www.openagentskill.com/api/registry/manifest/bjgreenberg-senior-engineering-partner"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"bjgreenberg-senior-engineering-partner","name":"Senior Engineering Partner","description":"A stack-agnostic Claude Code skill providing strict code review, pair programming, debugging, and mentoring with a security-first, phase-aware engineering workflow.","category":"coding-agents","url":"https://www.openagentskill.com/skills/bjgreenberg-senior-engineering-partner","repository":"https://github.com/bjgreenberg/senior-engineering-partner","github_repo":"bjgreenberg/senior-engineering-partner"},"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add bjgreenberg/senior-engineering-partner","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install bjgreenberg-senior-engineering-partner"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Senior Engineering Partner\" agent skill from https://github.com/bjgreenberg/senior-engineering-partner. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A stack-agnostic Claude Code skill providing strict code review, pair programming, debugging, and mentoring with a security-first, phase-aware engineering workflow. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bjgreenberg-senior-engineering-partner\",\"task\":\"Install Senior Engineering Partner\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Senior Engineering Partner\" as a Claude Code skill from https://github.com/bjgreenberg/senior-engineering-partner. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A stack-agnostic Claude Code skill providing strict code review, pair programming, debugging, and mentoring with a security-first, phase-aware engineering workflow. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bjgreenberg-senior-engineering-partner\",\"task\":\"Install Senior Engineering Partner\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Senior Engineering Partner\" from https://github.com/bjgreenberg/senior-engineering-partner into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A stack-agnostic Claude Code skill providing strict code review, pair programming, debugging, and mentoring with a security-first, phase-aware engineering workflow. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bjgreenberg-senior-engineering-partner\",\"task\":\"Install Senior Engineering Partner\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/bjgreenberg-senior-engineering-partner/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/bjgreenberg-senior-engineering-partner"},"trust":{"score":81,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"139 GitHub stars","repoActivity":"139 stars, 14 forks","lastPushed":"25d since push","license":"Apache-2.0","repository":"https://github.com/bjgreenberg/senior-engineering-partner","install":"npx skills add bjgreenberg/senior-engineering-partner","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["coding-agents","code-review","pair-programming","debugging","mentor","tdd"],"known_risks":["Documentation summary is thin","Stars/forks activity: 139 stars, 14 forks; issue activity unavailable in current metadata"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":88,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","Stars/forks activity: 139 stars, 14 forks; issue activity unavailable in current metadata"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":89,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"25d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution","Documentation summary is thin","Stars/forks activity: 139 stars, 14 forks; issue activity unavailable in current metadata","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Senior Engineering Partner in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 81/100 Strong shortlist","Audit: 88/100 Safe to try","Safety: 64/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"bjgreenberg-senior-engineering-partner (Senior Engineering Partner)","install_command":"npx skills add bjgreenberg/senior-engineering-partner","risk_summary":"Safe to try; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"bjgreenberg-senior-engineering-partner","task":"Use Senior Engineering Partner 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/bjgreenberg-senior-engineering-partner","api":"https://www.openagentskill.com/api/agent/skills/bjgreenberg-senior-engineering-partner","audit":"https://www.openagentskill.com/skills/bjgreenberg-senior-engineering-partner/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=bjgreenberg-senior-engineering-partner&task=Use%20Senior%20Engineering%20Partner%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Senior%20Engineering%20Partner%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Senior%20Engineering%20Partner%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/bjgreenberg-senior-engineering-partner/install","manifest":"https://www.openagentskill.com/api/registry/manifest/bjgreenberg-senior-engineering-partner"}},"platforms":["Python","Claude Code"],"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":"testing-qa","title":"Testing and QA","url":"https://www.openagentskill.com/use-cases/testing-qa"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"install":"npx skills add bjgreenberg/senior-engineering-partner","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install bjgreenberg-senior-engineering-partner","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Senior Engineering Partner\" agent skill from https://github.com/bjgreenberg/senior-engineering-partner. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A stack-agnostic Claude Code skill providing strict code review, pair programming, debugging, and mentoring with a security-first, phase-aware engineering workflow. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bjgreenberg-senior-engineering-partner\",\"task\":\"Install Senior Engineering Partner\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Senior Engineering Partner\" as a Claude Code skill from https://github.com/bjgreenberg/senior-engineering-partner. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A stack-agnostic Claude Code skill providing strict code review, pair programming, debugging, and mentoring with a security-first, phase-aware engineering workflow. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bjgreenberg-senior-engineering-partner\",\"task\":\"Install Senior Engineering Partner\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Senior Engineering Partner\" from https://github.com/bjgreenberg/senior-engineering-partner into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A stack-agnostic Claude Code skill providing strict code review, pair programming, debugging, and mentoring with a security-first, phase-aware engineering workflow. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bjgreenberg-senior-engineering-partner\",\"task\":\"Install Senior Engineering Partner\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/bjgreenberg/senior-engineering-partner","github_repo":"bjgreenberg/senior-engineering-partner","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"bjgreenberg/senior-engineering-partner","recommendation_reasons":["Matches task terms: pair","Install handoff is available","Repository freshness signal is available","Registry match score 10"],"urls":{"web":"https://www.openagentskill.com/skills/bjgreenberg-senior-engineering-partner","api":"https://www.openagentskill.com/api/agent/skills/bjgreenberg-senior-engineering-partner","install_api":"https://www.openagentskill.com/api/skills/bjgreenberg-senior-engineering-partner/install","audit":"https://www.openagentskill.com/skills/bjgreenberg-senior-engineering-partner/audit","repository":"https://github.com/bjgreenberg/senior-engineering-partner"}},{"rank":6,"match_type":"related","match_score":9,"raw_match_score":57.3,"semantic_relevance":30,"slug":"pair-code-lumi","name":"Lumi","description":"Lumi uses AI-powered features to help you read arXiv papers.","tagline":"Lumi uses AI-powered features to help you read arXiv papers.","category":"research","tags":["research","papers","arxiv","ai","arxiv-papers","demo-app","gemini-api","reading","reading-comprehension","research-paper"],"author":{"name":"PAIR-code","verified":false,"url":"https://github.com/PAIR-code"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"PAIR-code/lumi","creatorName":"PAIR-code","creatorUrl":"https://github.com/PAIR-code","sourceUrl":"https://github.com/PAIR-code/lumi","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/pair-code-lumi#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":204,"forks":32,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":46.88},"quality":{"score":68,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"204","tone":"neutral"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":75,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"204 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"204 stars, 32 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":82,"weight":0.12,"status":"pass","detail":"network or browser surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add PAIR-code/lumi"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/PAIR-code/lumi"},{"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":"204 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"204 stars, 32 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add PAIR-code/lumi"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/PAIR-code/lumi"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 204 stars, 32 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"204 GitHub stars","repoActivity":"204 stars, 32 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/PAIR-code/lumi","install":"npx skills add PAIR-code/lumi","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add PAIR-code/lumi","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Python","Research","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 204 stars, 32 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["research","papers","arxiv","ai","arxiv-papers","demo-app"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 204 stars, 32 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":66,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Documentation summary is thin","66/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Documentation summary is thin","66/100 agent safety score"]},"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"Research agents","description":"I need my agent to research a topic, compare sources, and produce a concise report.","useCases":[{"slug":"research-agents","title":"Research agents"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add PAIR-code/lumi","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":204,"starsLabel":"204","forks":32,"license":"Apache-2.0","qualityScore":68,"trustScore":75,"auditScore":78},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":63,"lastPushedAt":"2026-06-20T13:58:08+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 204 stars, 32 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Needs review"]},"coverageTags":["Research","Research agents","papers","arxiv","ai","arxiv-papers","demo-app","gemini-api"]},"audit":{"audit_score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 204 stars, 32 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"decision":{"readiness_score":67,"readiness_label":"Prototype first","headline":"Fallback candidate for Research agents","role":"Fallback candidate","primary_fit":"Research agents","best_for":["Research agents workflows","general agent builders","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Research agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"pair-code-lumi","name":"Lumi","description":"Lumi uses AI-powered features to help you read arXiv papers.","category":"research","url":"https://www.openagentskill.com/skills/pair-code-lumi","repository":"https://github.com/PAIR-code/lumi","github_repo":"PAIR-code/lumi"},"suited_tasks":["Research agents workflows","general agent builders","builders willing to evaluate younger projects","Search sources","Extract claims","Synthesize findings","Inspect source files","Explain architecture"],"suited_agents":["Python","Research","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add PAIR-code/lumi","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install pair-code-lumi"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Lumi\" agent skill from https://github.com/PAIR-code/lumi. 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: Lumi uses AI-powered features to help you read arXiv papers. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"pair-code-lumi\",\"task\":\"Install Lumi\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Lumi\" as a Claude Code skill from https://github.com/PAIR-code/lumi. 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: Lumi uses AI-powered features to help you read arXiv papers. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"pair-code-lumi\",\"task\":\"Install Lumi\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Lumi\" from https://github.com/PAIR-code/lumi 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: Lumi uses AI-powered features to help you read arXiv papers. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"pair-code-lumi\",\"task\":\"Install Lumi\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/pair-code-lumi/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/pair-code-lumi"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"204 GitHub stars","repoActivity":"204 stars, 32 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/PAIR-code/lumi","install":"npx skills add PAIR-code/lumi","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","papers","arxiv","ai","arxiv-papers","demo-app"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 204 stars, 32 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 204 stars, 32 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":68,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Quality score needs review","Stars/forks activity: 204 stars, 32 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use Lumi in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 78/100 Needs review","Safety: 66/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"pair-code-lumi (Lumi)","install_command":"npx skills add PAIR-code/lumi","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"pair-code-lumi","task":"Use Lumi 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/pair-code-lumi","api":"https://www.openagentskill.com/api/agent/skills/pair-code-lumi","audit":"https://www.openagentskill.com/skills/pair-code-lumi/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=pair-code-lumi&task=Use%20Lumi%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Lumi%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Lumi%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/pair-code-lumi/install","manifest":"https://www.openagentskill.com/api/registry/manifest/pair-code-lumi"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"pair-code-lumi","name":"Lumi","description":"Lumi uses AI-powered features to help you read arXiv papers.","category":"research","url":"https://www.openagentskill.com/skills/pair-code-lumi","repository":"https://github.com/PAIR-code/lumi","github_repo":"PAIR-code/lumi"},"suited_tasks":["Research agents workflows","general agent builders","builders willing to evaluate younger projects","Search sources","Extract claims","Synthesize findings","Inspect source files","Explain architecture"],"suited_agents":["Python","Research","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add PAIR-code/lumi","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install pair-code-lumi"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Lumi\" agent skill from https://github.com/PAIR-code/lumi. 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: Lumi uses AI-powered features to help you read arXiv papers. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"pair-code-lumi\",\"task\":\"Install Lumi\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Lumi\" as a Claude Code skill from https://github.com/PAIR-code/lumi. 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: Lumi uses AI-powered features to help you read arXiv papers. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"pair-code-lumi\",\"task\":\"Install Lumi\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Lumi\" from https://github.com/PAIR-code/lumi 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: Lumi uses AI-powered features to help you read arXiv papers. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"pair-code-lumi\",\"task\":\"Install Lumi\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/pair-code-lumi/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/pair-code-lumi"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"204 GitHub stars","repoActivity":"204 stars, 32 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/PAIR-code/lumi","install":"npx skills add PAIR-code/lumi","installSafety":"standard package or runtime install path","permissionSurface":"network or browser access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","papers","arxiv","ai","arxiv-papers","demo-app"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 204 stars, 32 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 204 stars, 32 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":68,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Quality score needs review","Stars/forks activity: 204 stars, 32 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use Lumi in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 78/100 Needs review","Safety: 66/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"pair-code-lumi (Lumi)","install_command":"npx skills add PAIR-code/lumi","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"pair-code-lumi","task":"Use Lumi 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/pair-code-lumi","api":"https://www.openagentskill.com/api/agent/skills/pair-code-lumi","audit":"https://www.openagentskill.com/skills/pair-code-lumi/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=pair-code-lumi&task=Use%20Lumi%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Lumi%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Lumi%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/pair-code-lumi/install","manifest":"https://www.openagentskill.com/api/registry/manifest/pair-code-lumi"}},"platforms":["Python","Research"],"use_cases":[{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"}],"install":"npx skills add PAIR-code/lumi","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install pair-code-lumi","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Lumi\" agent skill from https://github.com/PAIR-code/lumi. 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: Lumi uses AI-powered features to help you read arXiv papers. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"pair-code-lumi\",\"task\":\"Install Lumi\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Lumi\" as a Claude Code skill from https://github.com/PAIR-code/lumi. 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: Lumi uses AI-powered features to help you read arXiv papers. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"pair-code-lumi\",\"task\":\"Install Lumi\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Lumi\" from https://github.com/PAIR-code/lumi 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: Lumi uses AI-powered features to help you read arXiv papers. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"pair-code-lumi\",\"task\":\"Install Lumi\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/PAIR-code/lumi","github_repo":"PAIR-code/lumi","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"pair-code/lumi","recommendation_reasons":["Matches task terms: pair","Install handoff is available","Repository freshness signal is available","Registry match score 9"],"urls":{"web":"https://www.openagentskill.com/skills/pair-code-lumi","api":"https://www.openagentskill.com/api/agent/skills/pair-code-lumi","install_api":"https://www.openagentskill.com/api/skills/pair-code-lumi/install","audit":"https://www.openagentskill.com/skills/pair-code-lumi/audit","repository":"https://github.com/PAIR-code/lumi"}},{"rank":7,"match_type":"related","match_score":7,"raw_match_score":49.6,"semantic_relevance":30,"slug":"jeffallan-claude-skills","name":"Claude Skills","description":"66 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer.","tagline":"66 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer.","category":"development","tags":["claude-code","agent-skills","developer-tools","ai-agents","claude","claude-marketplace","claude-skills","python","github"],"author":{"name":"Jeffallan","verified":true,"url":"https://github.com/Jeffallan"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"Jeffallan/claude-skills","creatorName":"Jeffallan","creatorUrl":"https://github.com/Jeffallan","sourceUrl":"https://github.com/Jeffallan/claude-skills","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/jeffallan-claude-skills#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":9882,"forks":865,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":62.66},"quality":{"score":95,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"9.9K","tone":"positive"},{"label":"Freshness","value":"3mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":87,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"weight":0.13,"status":"pass","detail":"9.9K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"9.9K stars, 865 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"3mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add Jeffallan/claude-skills"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/Jeffallan/claude-skills"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"9.9K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"9.9K stars, 865 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"3mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add Jeffallan/claude-skills"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/Jeffallan/claude-skills"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin"],"evidence":{"stars":"9.9K GitHub stars","repoActivity":"9.9K stars, 865 forks","lastPushed":"3mo since push","license":"MIT","repository":"https://github.com/Jeffallan/claude-skills","install":"npx skills add Jeffallan/claude-skills","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add Jeffallan/claude-skills","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","3mo since push"]},"agentCompatibility":["Python","Claude Code","Codex","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["development","claude-code","agent-skills","developer-tools","ai-agents","claude"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin"]},"safety":{"score":76,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","76/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","76/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"github-automation","title":"GitHub automation"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","Python"],"install":{"ready":true,"command":"npx skills add Jeffallan/claude-skills","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":9882,"starsLabel":"9.9K","forks":865,"license":"MIT","qualityScore":95,"trustScore":87,"auditScore":88},"maintenance":{"status":"active","label":"3mo since push","daysSincePush":94,"lastPushedAt":"2026-05-20T13:35:05+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Coding","Coding agents","development","claude-code","agent-skills","developer-tools","ai-agents","claude"]},"audit":{"audit_score":88,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Coding agents","role":"Primary pick","primary_fit":"Coding agents","best_for":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"jeffallan-claude-skills","name":"Claude Skills","description":"66 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer.","category":"development","url":"https://www.openagentskill.com/skills/jeffallan-claude-skills","repository":"https://github.com/Jeffallan/claude-skills","github_repo":"Jeffallan/claude-skills"},"suited_tasks":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","Claude Code","Codex","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add Jeffallan/claude-skills","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install jeffallan-claude-skills"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Claude Skills\" agent skill from https://github.com/Jeffallan/claude-skills. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: 66 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeffallan-claude-skills\",\"task\":\"Install Claude Skills\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Claude Skills\" as a Claude Code skill from https://github.com/Jeffallan/claude-skills. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: 66 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeffallan-claude-skills\",\"task\":\"Install Claude Skills\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Claude Skills\" from https://github.com/Jeffallan/claude-skills into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: 66 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeffallan-claude-skills\",\"task\":\"Install Claude Skills\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/jeffallan-claude-skills/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/jeffallan-claude-skills"},"trust":{"score":87,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"9.9K GitHub stars","repoActivity":"9.9K stars, 865 forks","lastPushed":"3mo since push","license":"MIT","repository":"https://github.com/Jeffallan/claude-skills","install":"npx skills add Jeffallan/claude-skills","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["development","claude-code","agent-skills","developer-tools","ai-agents","claude"],"known_risks":["Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":88,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":95,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"3mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","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 Claude Skills in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 87/100 Production candidate","Audit: 88/100 Safe to try","Safety: 76/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"jeffallan-claude-skills (Claude Skills)","install_command":"npx skills add Jeffallan/claude-skills","risk_summary":"Safe to try; Reviewed; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"jeffallan-claude-skills","task":"Use Claude Skills in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/jeffallan-claude-skills","api":"https://www.openagentskill.com/api/agent/skills/jeffallan-claude-skills","audit":"https://www.openagentskill.com/skills/jeffallan-claude-skills/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=jeffallan-claude-skills&task=Use%20Claude%20Skills%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Claude%20Skills%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Claude%20Skills%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/jeffallan-claude-skills/install","manifest":"https://www.openagentskill.com/api/registry/manifest/jeffallan-claude-skills"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"jeffallan-claude-skills","name":"Claude Skills","description":"66 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer.","category":"development","url":"https://www.openagentskill.com/skills/jeffallan-claude-skills","repository":"https://github.com/Jeffallan/claude-skills","github_repo":"Jeffallan/claude-skills"},"suited_tasks":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","Claude Code","Codex","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add Jeffallan/claude-skills","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install jeffallan-claude-skills"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Claude Skills\" agent skill from https://github.com/Jeffallan/claude-skills. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: 66 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeffallan-claude-skills\",\"task\":\"Install Claude Skills\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Claude Skills\" as a Claude Code skill from https://github.com/Jeffallan/claude-skills. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: 66 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeffallan-claude-skills\",\"task\":\"Install Claude Skills\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Claude Skills\" from https://github.com/Jeffallan/claude-skills into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: 66 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeffallan-claude-skills\",\"task\":\"Install Claude Skills\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/jeffallan-claude-skills/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/jeffallan-claude-skills"},"trust":{"score":87,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"9.9K GitHub stars","repoActivity":"9.9K stars, 865 forks","lastPushed":"3mo since push","license":"MIT","repository":"https://github.com/Jeffallan/claude-skills","install":"npx skills add Jeffallan/claude-skills","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["development","claude-code","agent-skills","developer-tools","ai-agents","claude"],"known_risks":["Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":88,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":95,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"3mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","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 Claude Skills in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 87/100 Production candidate","Audit: 88/100 Safe to try","Safety: 76/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"jeffallan-claude-skills (Claude Skills)","install_command":"npx skills add Jeffallan/claude-skills","risk_summary":"Safe to try; Reviewed; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"jeffallan-claude-skills","task":"Use Claude Skills in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/jeffallan-claude-skills","api":"https://www.openagentskill.com/api/agent/skills/jeffallan-claude-skills","audit":"https://www.openagentskill.com/skills/jeffallan-claude-skills/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=jeffallan-claude-skills&task=Use%20Claude%20Skills%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Claude%20Skills%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Claude%20Skills%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/jeffallan-claude-skills/install","manifest":"https://www.openagentskill.com/api/registry/manifest/jeffallan-claude-skills"}},"platforms":["Python","Claude Code"],"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"}],"install":"npx skills add Jeffallan/claude-skills","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install jeffallan-claude-skills","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Claude Skills\" agent skill from https://github.com/Jeffallan/claude-skills. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: 66 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeffallan-claude-skills\",\"task\":\"Install Claude Skills\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Claude Skills\" as a Claude Code skill from https://github.com/Jeffallan/claude-skills. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: 66 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeffallan-claude-skills\",\"task\":\"Install Claude Skills\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Claude Skills\" from https://github.com/Jeffallan/claude-skills into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: 66 Specialized Skills for Full-Stack Developers. Transform Claude Code into your expert pair programmer. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"jeffallan-claude-skills\",\"task\":\"Install Claude Skills\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/Jeffallan/claude-skills","github_repo":"Jeffallan/claude-skills","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"jeffallan/claude-skills","recommendation_reasons":["Matches task terms: pair","Useful GitHub adoption: 9,882 stars","Install handoff is available","Repository freshness signal is available","Registry match score 7"],"urls":{"web":"https://www.openagentskill.com/skills/jeffallan-claude-skills","api":"https://www.openagentskill.com/api/agent/skills/jeffallan-claude-skills","install_api":"https://www.openagentskill.com/api/skills/jeffallan-claude-skills/install","audit":"https://www.openagentskill.com/skills/jeffallan-claude-skills/audit","repository":"https://github.com/Jeffallan/claude-skills"}},{"rank":8,"match_type":"related","match_score":7,"raw_match_score":48.1,"semantic_relevance":30,"slug":"je-suis-tm-quant-trading","name":"Quant Trading","description":"Python quantitative trading strategies including VIX Calculator, Pattern Recognition, Commodity Trading Advisor, Monte Carlo, Options Straddle, Shooting Star, London Breakout, Heikin-Ashi, Pair Trading, RSI, Bollinger Bands, Parabolic SAR, Dual Thrust, Awesome, MACD","tagline":"Python quantitative trading strategies including VIX Calculator, Pattern Recognition, Commodity Trading Advisor, Monte Carlo, Options Straddle, Shooting Star, London Breakout, Heikin-Ashi, Pair Trading, RSI, Bollinger Bands, Parabolic SAR, Dual Thrust, Awesome, MACD","category":"finance","tags":["finance","quant","research","algorithmic-trading","bollinger-bands","commodity-trading","macd","momentum-strategy","momentum-trading-strategy","options-strategies"],"author":{"name":"je-suis-tm","verified":true,"url":"https://github.com/je-suis-tm"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"je-suis-tm/quant-trading","creatorName":"je-suis-tm","creatorUrl":"https://github.com/je-suis-tm","sourceUrl":"https://github.com/je-suis-tm/quant-trading","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/je-suis-tm-quant-trading#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":10105,"forks":1818,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":56.23},"quality":{"score":82,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"10K","tone":"positive"},{"label":"Freshness","value":"2y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":82,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"10K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"10K stars, 1.8K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":22,"weight":0.14,"status":"fail","detail":"2y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add je-suis-tm/quant-trading"},{"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/je-suis-tm/quant-trading"},{"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":"10K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"10K stars, 1.8K forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"2y since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add je-suis-tm/quant-trading"},{"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/je-suis-tm/quant-trading"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Financial research output is not financial advice; require human review before any live investment decision.","Repository looks stale","Documentation summary is thin","Recent maintenance: 2y since push"],"evidence":{"stars":"10K GitHub stars","repoActivity":"10K stars, 1.8K forks","lastPushed":"2y since push","license":"Apache-2.0","repository":"https://github.com/je-suis-tm/quant-trading","install":"npx skills add je-suis-tm/quant-trading","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add je-suis-tm/quant-trading","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2y since push","Financial domain: human review is required before use in a live investment workflow."]},"agentCompatibility":["Python","Finance","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Financial research output is not financial advice; require human review before any live investment decision.","Repository looks stale","Documentation summary is thin","Recent maintenance: 2y since push"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["finance","quant","research","algorithmic-trading","bollinger-bands","commodity-trading"],"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","Autonomous investment, trading, tax, or suitability decisions without a qualified human review"],"knownRisks":["Financial research output is not financial advice; require human review before any live investment decision.","Repository looks stale","Documentation summary is thin","Recent maintenance: 2y since push"]},"safety":{"score":64,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Repository appears stale","64/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Repository appears stale"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Repository appears stale","64/100 agent safety score"]},"supply_profile":{"track":{"slug":"finance","label":"Finance and quant workflows","shortLabel":"Finance","description":"Market data, SEC filings, portfolio analysis, quant research, backtesting, and risk workflows."},"scenario":{"label":"Finance and quant","description":"I need my agent to analyze markets, financial data, filings, portfolios, and quant strategies.","useCases":[{"slug":"finance-quant","title":"Finance and quant"},{"slug":"research-agents","title":"Research agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add je-suis-tm/quant-trading","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":10105,"starsLabel":"10K","forks":1818,"license":"Apache-2.0","qualityScore":82,"trustScore":82,"auditScore":76},"maintenance":{"status":"stale","label":"2y since push","daysSincePush":860,"lastPushedAt":"2024-04-14T13:06:59+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Repository appears stale","Financial research output is not financial advice; require human review before any live investment decision","Repository looks stale","Financial research output is not financial advice; require human review before any live investment decision.","Documentation summary is thin"]},"coverageTags":["Finance","Finance and quant","quant","research","algorithmic-trading","bollinger-bands","commodity-trading","macd"]},"audit":{"audit_score":76,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Repository appears stale","Financial research output is not financial advice; require human review before any live investment decision","Repository looks stale","Financial research output is not financial advice; require human review before any live investment decision.","Documentation summary is thin"]},"decision":{"readiness_score":84,"readiness_label":"Production-ready","headline":"Primary pick for Finance and quant","role":"Primary pick","primary_fit":"Finance and quant","best_for":["Finance and quant workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["Repository looks stale","No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Finance and quant 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":"je-suis-tm-quant-trading","name":"Quant Trading","description":"Python quantitative trading strategies including VIX Calculator, Pattern Recognition, Commodity Trading Advisor, Monte Carlo, Options Straddle, Shooting Star, London Breakout, Heikin-Ashi, Pair Trading, RSI, Bollinger Bands, Parabolic SAR, Dual Thrust, Awesome, MACD","category":"finance","url":"https://www.openagentskill.com/skills/je-suis-tm-quant-trading","repository":"https://github.com/je-suis-tm/quant-trading","github_repo":"je-suis-tm/quant-trading"},"suited_tasks":["Finance and quant workflows","general agent builders","teams that value GitHub adoption signals","Retrieve market data","Compare financial signals","Generate investor-ready analysis","Search sources","Extract claims"],"suited_agents":["Python","Finance","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add je-suis-tm/quant-trading","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install je-suis-tm-quant-trading"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Quant Trading\" agent skill from https://github.com/je-suis-tm/quant-trading. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Python quantitative trading strategies including VIX Calculator, Pattern Recognition, Commodity Trading Advisor, Monte Carlo, Options Straddle, Shooting Star, London Breakout, Heikin-Ashi, Pair Trading, RSI, Bollinger Bands, Parabolic SAR, Dual Thrust, Awesome, MACD After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"je-suis-tm-quant-trading\",\"task\":\"Install Quant Trading\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Quant Trading\" as a Claude Code skill from https://github.com/je-suis-tm/quant-trading. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Python quantitative trading strategies including VIX Calculator, Pattern Recognition, Commodity Trading Advisor, Monte Carlo, Options Straddle, Shooting Star, London Breakout, Heikin-Ashi, Pair Trading, RSI, Bollinger Bands, Parabolic SAR, Dual Thrust, Awesome, MACD After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"je-suis-tm-quant-trading\",\"task\":\"Install Quant Trading\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Quant Trading\" from https://github.com/je-suis-tm/quant-trading into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Python quantitative trading strategies including VIX Calculator, Pattern Recognition, Commodity Trading Advisor, Monte Carlo, Options Straddle, Shooting Star, London Breakout, Heikin-Ashi, Pair Trading, RSI, Bollinger Bands, Parabolic SAR, Dual Thrust, Awesome, MACD After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"je-suis-tm-quant-trading\",\"task\":\"Install Quant Trading\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/je-suis-tm-quant-trading/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/je-suis-tm-quant-trading"},"trust":{"score":82,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"10K GitHub stars","repoActivity":"10K stars, 1.8K forks","lastPushed":"2y since push","license":"Apache-2.0","repository":"https://github.com/je-suis-tm/quant-trading","install":"npx skills add je-suis-tm/quant-trading","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["finance","quant","research","algorithmic-trading","bollinger-bands","commodity-trading"],"known_risks":["Financial research output is not financial advice; require human review before any live investment decision.","Repository looks stale","Documentation summary is thin","Recent maintenance: 2y since push"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":76,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Repository appears stale","Financial research output is not financial advice; require human review before any live investment decision","Repository looks stale","Financial research output is not financial advice; require human review before any live investment decision.","Documentation summary is thin","Recent maintenance: 2y since push"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":82,"label":"Strong"},"supply":{"track":"Finance and quant workflows","scenario":"Finance and quant","maintenance":"2y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Repository appears stale","Financial research output is not financial advice; require human review before any live investment decision","Financial research output is not financial advice; require human review before any live investment decision.","Documentation summary is thin"],"agent_contract":{"task_input":"Use Quant Trading in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 82/100 Strong shortlist","Audit: 76/100 Needs review","Safety: 64/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"je-suis-tm-quant-trading (Quant Trading)","install_command":"npx skills add je-suis-tm/quant-trading","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"je-suis-tm-quant-trading","task":"Use Quant Trading 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/je-suis-tm-quant-trading","api":"https://www.openagentskill.com/api/agent/skills/je-suis-tm-quant-trading","audit":"https://www.openagentskill.com/skills/je-suis-tm-quant-trading/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=je-suis-tm-quant-trading&task=Use%20Quant%20Trading%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Quant%20Trading%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Quant%20Trading%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/je-suis-tm-quant-trading/install","manifest":"https://www.openagentskill.com/api/registry/manifest/je-suis-tm-quant-trading"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"je-suis-tm-quant-trading","name":"Quant Trading","description":"Python quantitative trading strategies including VIX Calculator, Pattern Recognition, Commodity Trading Advisor, Monte Carlo, Options Straddle, Shooting Star, London Breakout, Heikin-Ashi, Pair Trading, RSI, Bollinger Bands, Parabolic SAR, Dual Thrust, Awesome, MACD","category":"finance","url":"https://www.openagentskill.com/skills/je-suis-tm-quant-trading","repository":"https://github.com/je-suis-tm/quant-trading","github_repo":"je-suis-tm/quant-trading"},"suited_tasks":["Finance and quant workflows","general agent builders","teams that value GitHub adoption signals","Retrieve market data","Compare financial signals","Generate investor-ready analysis","Search sources","Extract claims"],"suited_agents":["Python","Finance","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add je-suis-tm/quant-trading","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install je-suis-tm-quant-trading"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Quant Trading\" agent skill from https://github.com/je-suis-tm/quant-trading. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Python quantitative trading strategies including VIX Calculator, Pattern Recognition, Commodity Trading Advisor, Monte Carlo, Options Straddle, Shooting Star, London Breakout, Heikin-Ashi, Pair Trading, RSI, Bollinger Bands, Parabolic SAR, Dual Thrust, Awesome, MACD After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"je-suis-tm-quant-trading\",\"task\":\"Install Quant Trading\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Quant Trading\" as a Claude Code skill from https://github.com/je-suis-tm/quant-trading. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Python quantitative trading strategies including VIX Calculator, Pattern Recognition, Commodity Trading Advisor, Monte Carlo, Options Straddle, Shooting Star, London Breakout, Heikin-Ashi, Pair Trading, RSI, Bollinger Bands, Parabolic SAR, Dual Thrust, Awesome, MACD After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"je-suis-tm-quant-trading\",\"task\":\"Install Quant Trading\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Quant Trading\" from https://github.com/je-suis-tm/quant-trading into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Python quantitative trading strategies including VIX Calculator, Pattern Recognition, Commodity Trading Advisor, Monte Carlo, Options Straddle, Shooting Star, London Breakout, Heikin-Ashi, Pair Trading, RSI, Bollinger Bands, Parabolic SAR, Dual Thrust, Awesome, MACD After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"je-suis-tm-quant-trading\",\"task\":\"Install Quant Trading\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/je-suis-tm-quant-trading/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/je-suis-tm-quant-trading"},"trust":{"score":82,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"10K GitHub stars","repoActivity":"10K stars, 1.8K forks","lastPushed":"2y since push","license":"Apache-2.0","repository":"https://github.com/je-suis-tm/quant-trading","install":"npx skills add je-suis-tm/quant-trading","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["finance","quant","research","algorithmic-trading","bollinger-bands","commodity-trading"],"known_risks":["Financial research output is not financial advice; require human review before any live investment decision.","Repository looks stale","Documentation summary is thin","Recent maintenance: 2y since push"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":76,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Repository appears stale","Financial research output is not financial advice; require human review before any live investment decision","Repository looks stale","Financial research output is not financial advice; require human review before any live investment decision.","Documentation summary is thin","Recent maintenance: 2y since push"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":82,"label":"Strong"},"supply":{"track":"Finance and quant workflows","scenario":"Finance and quant","maintenance":"2y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Repository appears stale","Financial research output is not financial advice; require human review before any live investment decision","Financial research output is not financial advice; require human review before any live investment decision.","Documentation summary is thin"],"agent_contract":{"task_input":"Use Quant Trading in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 82/100 Strong shortlist","Audit: 76/100 Needs review","Safety: 64/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"je-suis-tm-quant-trading (Quant Trading)","install_command":"npx skills add je-suis-tm/quant-trading","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"je-suis-tm-quant-trading","task":"Use Quant Trading 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/je-suis-tm-quant-trading","api":"https://www.openagentskill.com/api/agent/skills/je-suis-tm-quant-trading","audit":"https://www.openagentskill.com/skills/je-suis-tm-quant-trading/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=je-suis-tm-quant-trading&task=Use%20Quant%20Trading%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Quant%20Trading%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Quant%20Trading%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/je-suis-tm-quant-trading/install","manifest":"https://www.openagentskill.com/api/registry/manifest/je-suis-tm-quant-trading"}},"platforms":["Python","Finance"],"use_cases":[{"slug":"finance-quant","title":"Finance and quant","url":"https://www.openagentskill.com/use-cases/finance-quant"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"install":"npx skills add je-suis-tm/quant-trading","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install je-suis-tm-quant-trading","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Quant Trading\" agent skill from https://github.com/je-suis-tm/quant-trading. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Python quantitative trading strategies including VIX Calculator, Pattern Recognition, Commodity Trading Advisor, Monte Carlo, Options Straddle, Shooting Star, London Breakout, Heikin-Ashi, Pair Trading, RSI, Bollinger Bands, Parabolic SAR, Dual Thrust, Awesome, MACD After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"je-suis-tm-quant-trading\",\"task\":\"Install Quant Trading\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Quant Trading\" as a Claude Code skill from https://github.com/je-suis-tm/quant-trading. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Python quantitative trading strategies including VIX Calculator, Pattern Recognition, Commodity Trading Advisor, Monte Carlo, Options Straddle, Shooting Star, London Breakout, Heikin-Ashi, Pair Trading, RSI, Bollinger Bands, Parabolic SAR, Dual Thrust, Awesome, MACD After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"je-suis-tm-quant-trading\",\"task\":\"Install Quant Trading\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Quant Trading\" from https://github.com/je-suis-tm/quant-trading into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Python quantitative trading strategies including VIX Calculator, Pattern Recognition, Commodity Trading Advisor, Monte Carlo, Options Straddle, Shooting Star, London Breakout, Heikin-Ashi, Pair Trading, RSI, Bollinger Bands, Parabolic SAR, Dual Thrust, Awesome, MACD After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"je-suis-tm-quant-trading\",\"task\":\"Install Quant Trading\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/je-suis-tm/quant-trading","github_repo":"je-suis-tm/quant-trading","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"je-suis-tm/quant-trading","recommendation_reasons":["Matches task terms: pair","Strong GitHub adoption: 10,105 stars","Install handoff is available","Repository freshness signal is available","Registry match score 7"],"urls":{"web":"https://www.openagentskill.com/skills/je-suis-tm-quant-trading","api":"https://www.openagentskill.com/api/agent/skills/je-suis-tm-quant-trading","install_api":"https://www.openagentskill.com/api/skills/je-suis-tm-quant-trading/install","audit":"https://www.openagentskill.com/skills/je-suis-tm-quant-trading/audit","repository":"https://github.com/je-suis-tm/quant-trading"}},{"rank":9,"match_type":"related","match_score":7,"raw_match_score":44.6,"semantic_relevance":30,"slug":"entropy-research-devon","name":"Devon","description":"Devon: An open-source pair programmer","tagline":"Devon: An open-source pair programmer","category":"coding-agents","tags":["developer-tools","automation","coding","agent","agent-based-framework","agent-based-model","ai","ai-developer","ai-software","ai-software-engineer"],"author":{"name":"entropy-research","verified":true,"url":"https://github.com/entropy-research"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"entropy-research/Devon","creatorName":"entropy-research","creatorUrl":"https://github.com/entropy-research","sourceUrl":"https://github.com/entropy-research/Devon","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/entropy-research-devon#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":3449,"forks":282,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":51.46},"quality":{"score":70,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"3.4K","tone":"positive"},{"label":"Freshness","value":"1y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"AGPL-3.0","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":80,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"3.4K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"3.4K stars, 282 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":38,"weight":0.14,"status":"fail","detail":"1y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"AGPL-3.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":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 entropy-research/Devon"},{"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/entropy-research/Devon"},{"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":"3.4K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"3.4K stars, 282 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"1y since push"},{"status":"pass","label":"License clarity","detail":"AGPL-3.0"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add entropy-research/Devon"},{"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/entropy-research/Devon"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"3.4K GitHub stars","repoActivity":"3.4K stars, 282 forks","lastPushed":"1y since push","license":"AGPL-3.0","repository":"https://github.com/entropy-research/Devon","install":"npx skills add entropy-research/Devon","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add entropy-research/Devon","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","1y since push"]},"agentCompatibility":["Python","Developer Tools","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["coding-agents","developer-tools","automation","coding","agent","agent-based-framework"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":62,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Documentation summary is thin","62/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Documentation summary is thin","62/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"research-agents","title":"Research agents"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add entropy-research/Devon","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":3449,"starsLabel":"3.4K","forks":282,"license":"AGPL-3.0","qualityScore":70,"trustScore":80,"auditScore":74},"maintenance":{"status":"stale","label":"1y since push","daysSincePush":454,"lastPushedAt":"2025-05-26T05:47:27+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push"]},"coverageTags":["Coding","Coding agents","coding-agents","developer-tools","automation","agent","agent-based-framework","agent-based-model"]},"audit":{"audit_score":74,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push"]},"decision":{"readiness_score":72,"readiness_label":"Strong shortlist","headline":"Companion skill for Research agents","role":"Companion skill","primary_fit":"Research agents","best_for":["Research agents workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["Repository looks stale","No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Research agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"entropy-research-devon","name":"Devon","description":"Devon: An open-source pair programmer","category":"coding-agents","url":"https://www.openagentskill.com/skills/entropy-research-devon","repository":"https://github.com/entropy-research/Devon","github_repo":"entropy-research/Devon"},"suited_tasks":["Research agents workflows","general agent builders","teams that value GitHub adoption signals","Search sources","Extract claims","Synthesize findings","Inspect source files","Explain architecture"],"suited_agents":["Python","Developer Tools","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add entropy-research/Devon","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install entropy-research-devon"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Devon\" agent skill from https://github.com/entropy-research/Devon. 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: Devon: An open-source pair programmer After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"entropy-research-devon\",\"task\":\"Install Devon\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Devon\" as a Claude Code skill from https://github.com/entropy-research/Devon. 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: Devon: An open-source pair programmer After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"entropy-research-devon\",\"task\":\"Install Devon\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Devon\" from https://github.com/entropy-research/Devon 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: Devon: An open-source pair programmer After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"entropy-research-devon\",\"task\":\"Install Devon\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/entropy-research-devon/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/entropy-research-devon"},"trust":{"score":80,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"3.4K GitHub stars","repoActivity":"3.4K stars, 282 forks","lastPushed":"1y since push","license":"AGPL-3.0","repository":"https://github.com/entropy-research/Devon","install":"npx skills add entropy-research/Devon","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["coding-agents","developer-tools","automation","coding","agent","agent-based-framework"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":74,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":70,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"1y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Documentation summary is thin","Repository appears stale","Quality score needs review","Recent maintenance: 1y since push"],"agent_contract":{"task_input":"Use Devon in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 80/100 Strong shortlist","Audit: 74/100 Needs review","Safety: 62/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"entropy-research-devon (Devon)","install_command":"npx skills add entropy-research/Devon","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"entropy-research-devon","task":"Use Devon 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/entropy-research-devon","api":"https://www.openagentskill.com/api/agent/skills/entropy-research-devon","audit":"https://www.openagentskill.com/skills/entropy-research-devon/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=entropy-research-devon&task=Use%20Devon%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Devon%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Devon%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/entropy-research-devon/install","manifest":"https://www.openagentskill.com/api/registry/manifest/entropy-research-devon"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"entropy-research-devon","name":"Devon","description":"Devon: An open-source pair programmer","category":"coding-agents","url":"https://www.openagentskill.com/skills/entropy-research-devon","repository":"https://github.com/entropy-research/Devon","github_repo":"entropy-research/Devon"},"suited_tasks":["Research agents workflows","general agent builders","teams that value GitHub adoption signals","Search sources","Extract claims","Synthesize findings","Inspect source files","Explain architecture"],"suited_agents":["Python","Developer Tools","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add entropy-research/Devon","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install entropy-research-devon"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Devon\" agent skill from https://github.com/entropy-research/Devon. 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: Devon: An open-source pair programmer After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"entropy-research-devon\",\"task\":\"Install Devon\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Devon\" as a Claude Code skill from https://github.com/entropy-research/Devon. 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: Devon: An open-source pair programmer After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"entropy-research-devon\",\"task\":\"Install Devon\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Devon\" from https://github.com/entropy-research/Devon 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: Devon: An open-source pair programmer After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"entropy-research-devon\",\"task\":\"Install Devon\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/entropy-research-devon/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/entropy-research-devon"},"trust":{"score":80,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"3.4K GitHub stars","repoActivity":"3.4K stars, 282 forks","lastPushed":"1y since push","license":"AGPL-3.0","repository":"https://github.com/entropy-research/Devon","install":"npx skills add entropy-research/Devon","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["coding-agents","developer-tools","automation","coding","agent","agent-based-framework"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":74,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 1y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":70,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"1y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Documentation summary is thin","Repository appears stale","Quality score needs review","Recent maintenance: 1y since push"],"agent_contract":{"task_input":"Use Devon in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 80/100 Strong shortlist","Audit: 74/100 Needs review","Safety: 62/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"entropy-research-devon (Devon)","install_command":"npx skills add entropy-research/Devon","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"entropy-research-devon","task":"Use Devon 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/entropy-research-devon","api":"https://www.openagentskill.com/api/agent/skills/entropy-research-devon","audit":"https://www.openagentskill.com/skills/entropy-research-devon/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=entropy-research-devon&task=Use%20Devon%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Devon%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Devon%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/entropy-research-devon/install","manifest":"https://www.openagentskill.com/api/registry/manifest/entropy-research-devon"}},"platforms":["Python","Developer Tools"],"use_cases":[{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"install":"npx skills add entropy-research/Devon","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install entropy-research-devon","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Devon\" agent skill from https://github.com/entropy-research/Devon. 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: Devon: An open-source pair programmer After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"entropy-research-devon\",\"task\":\"Install Devon\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Devon\" as a Claude Code skill from https://github.com/entropy-research/Devon. 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: Devon: An open-source pair programmer After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"entropy-research-devon\",\"task\":\"Install Devon\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Devon\" from https://github.com/entropy-research/Devon 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: Devon: An open-source pair programmer After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"entropy-research-devon\",\"task\":\"Install Devon\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/entropy-research/Devon","github_repo":"entropy-research/Devon","version":"1.0.0","license":"AGPL-3.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"entropy-research/devon","recommendation_reasons":["Matches task terms: pair","Useful GitHub adoption: 3,449 stars","Install handoff is available","Repository freshness signal is available","Registry match score 7"],"urls":{"web":"https://www.openagentskill.com/skills/entropy-research-devon","api":"https://www.openagentskill.com/api/agent/skills/entropy-research-devon","install_api":"https://www.openagentskill.com/api/skills/entropy-research-devon/install","audit":"https://www.openagentskill.com/skills/entropy-research-devon/audit","repository":"https://github.com/entropy-research/Devon"}},{"rank":10,"match_type":"related","match_score":6,"raw_match_score":41.5,"semantic_relevance":30,"slug":"bheinzerling-bpemb","name":"Bpemb","description":"Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)","tagline":"Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)","category":"rag-knowledge","tags":["embeddings","retrieval","knowledge","multilingual","natural-language-processing","nlp","subword-embeddings","python","github"],"author":{"name":"bheinzerling","verified":true,"url":"https://github.com/bheinzerling"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"bheinzerling/bpemb","creatorName":"bheinzerling","creatorUrl":"https://github.com/bheinzerling","sourceUrl":"https://github.com/bheinzerling/bpemb","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/bheinzerling-bpemb#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":1220,"forks":100,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":48.31},"quality":{"score":65,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"1.2K","tone":"positive"},{"label":"Freshness","value":"2y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":81,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"1.2K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":77,"weight":0.08,"status":"info","detail":"1.2K stars, 100 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":38,"weight":0.14,"status":"fail","detail":"2y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add bheinzerling/bpemb"},{"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/bheinzerling/bpemb"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"1.2K GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"1.2K stars, 100 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"2y 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 bheinzerling/bpemb"},{"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/bheinzerling/bpemb"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 2y since push"],"evidence":{"stars":"1.2K GitHub stars","repoActivity":"1.2K stars, 100 forks","lastPushed":"2y since push","license":"MIT","repository":"https://github.com/bheinzerling/bpemb","install":"npx skills add bheinzerling/bpemb","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add bheinzerling/bpemb","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2y since push"]},"agentCompatibility":["Python","Embeddings","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 2y since push"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["rag-knowledge","embeddings","retrieval","knowledge","multilingual","natural-language-processing"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 2y since push"]},"safety":{"score":61,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Documentation summary is thin","61/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Documentation summary is thin","61/100 agent safety score"]},"supply_profile":{"track":{"slug":"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":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add bheinzerling/bpemb","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":1220,"starsLabel":"1.2K","forks":100,"license":"MIT","qualityScore":65,"trustScore":81,"auditScore":73},"maintenance":{"status":"stale","label":"2y since push","daysSincePush":691,"lastPushedAt":"2024-10-01T02:49:47+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 2y since push"]},"coverageTags":["Research","RAG and knowledge","rag-knowledge","embeddings","retrieval","knowledge","multilingual","natural-language-processing"]},"audit":{"audit_score":73,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 2y since push"]},"decision":{"readiness_score":67,"readiness_label":"Prototype first","headline":"Fallback candidate for RAG and knowledge","role":"Fallback candidate","primary_fit":"RAG and knowledge","best_for":["RAG and knowledge workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["Repository looks stale","No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one 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":"bheinzerling-bpemb","name":"Bpemb","description":"Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)","category":"rag-knowledge","url":"https://www.openagentskill.com/skills/bheinzerling-bpemb","repository":"https://github.com/bheinzerling/bpemb","github_repo":"bheinzerling/bpemb"},"suited_tasks":["RAG and knowledge workflows","general agent builders","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Inspect source files","Explain architecture"],"suited_agents":["Python","Embeddings","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add bheinzerling/bpemb","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install bheinzerling-bpemb"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Bpemb\" agent skill from https://github.com/bheinzerling/bpemb. 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: Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bheinzerling-bpemb\",\"task\":\"Install Bpemb\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Bpemb\" as a Claude Code skill from https://github.com/bheinzerling/bpemb. 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: Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bheinzerling-bpemb\",\"task\":\"Install Bpemb\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Bpemb\" from https://github.com/bheinzerling/bpemb 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: Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bheinzerling-bpemb\",\"task\":\"Install Bpemb\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/bheinzerling-bpemb/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/bheinzerling-bpemb"},"trust":{"score":81,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"1.2K GitHub stars","repoActivity":"1.2K stars, 100 forks","lastPushed":"2y since push","license":"MIT","repository":"https://github.com/bheinzerling/bpemb","install":"npx skills add bheinzerling/bpemb","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["rag-knowledge","embeddings","retrieval","knowledge","multilingual","natural-language-processing"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 2y since push"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":73,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 2y since push"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":65,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"2y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Documentation summary is thin","Repository appears stale","Quality score needs review","Recent maintenance: 2y since push"],"agent_contract":{"task_input":"Use Bpemb in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 81/100 Strong shortlist","Audit: 73/100 Needs review","Safety: 61/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"bheinzerling-bpemb (Bpemb)","install_command":"npx skills add bheinzerling/bpemb","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"bheinzerling-bpemb","task":"Use Bpemb 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/bheinzerling-bpemb","api":"https://www.openagentskill.com/api/agent/skills/bheinzerling-bpemb","audit":"https://www.openagentskill.com/skills/bheinzerling-bpemb/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=bheinzerling-bpemb&task=Use%20Bpemb%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Bpemb%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Bpemb%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/bheinzerling-bpemb/install","manifest":"https://www.openagentskill.com/api/registry/manifest/bheinzerling-bpemb"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"bheinzerling-bpemb","name":"Bpemb","description":"Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)","category":"rag-knowledge","url":"https://www.openagentskill.com/skills/bheinzerling-bpemb","repository":"https://github.com/bheinzerling/bpemb","github_repo":"bheinzerling/bpemb"},"suited_tasks":["RAG and knowledge workflows","general agent builders","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Inspect source files","Explain architecture"],"suited_agents":["Python","Embeddings","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add bheinzerling/bpemb","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install bheinzerling-bpemb"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Bpemb\" agent skill from https://github.com/bheinzerling/bpemb. 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: Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bheinzerling-bpemb\",\"task\":\"Install Bpemb\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Bpemb\" as a Claude Code skill from https://github.com/bheinzerling/bpemb. 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: Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bheinzerling-bpemb\",\"task\":\"Install Bpemb\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Bpemb\" from https://github.com/bheinzerling/bpemb 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: Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bheinzerling-bpemb\",\"task\":\"Install Bpemb\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/bheinzerling-bpemb/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/bheinzerling-bpemb"},"trust":{"score":81,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"1.2K GitHub stars","repoActivity":"1.2K stars, 100 forks","lastPushed":"2y since push","license":"MIT","repository":"https://github.com/bheinzerling/bpemb","install":"npx skills add bheinzerling/bpemb","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["rag-knowledge","embeddings","retrieval","knowledge","multilingual","natural-language-processing"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 2y since push"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":73,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 2y since push"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":65,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"2y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Documentation summary is thin","Repository appears stale","Quality score needs review","Recent maintenance: 2y since push"],"agent_contract":{"task_input":"Use Bpemb in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 81/100 Strong shortlist","Audit: 73/100 Needs review","Safety: 61/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"bheinzerling-bpemb (Bpemb)","install_command":"npx skills add bheinzerling/bpemb","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"bheinzerling-bpemb","task":"Use Bpemb 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/bheinzerling-bpemb","api":"https://www.openagentskill.com/api/agent/skills/bheinzerling-bpemb","audit":"https://www.openagentskill.com/skills/bheinzerling-bpemb/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=bheinzerling-bpemb&task=Use%20Bpemb%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Bpemb%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Bpemb%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/bheinzerling-bpemb/install","manifest":"https://www.openagentskill.com/api/registry/manifest/bheinzerling-bpemb"}},"platforms":["Python","Embeddings"],"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":"customer-support","title":"Customer support","url":"https://www.openagentskill.com/use-cases/customer-support"}],"install":"npx skills add bheinzerling/bpemb","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install bheinzerling-bpemb","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Bpemb\" agent skill from https://github.com/bheinzerling/bpemb. 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: Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bheinzerling-bpemb\",\"task\":\"Install Bpemb\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Bpemb\" as a Claude Code skill from https://github.com/bheinzerling/bpemb. 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: Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bheinzerling-bpemb\",\"task\":\"Install Bpemb\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Bpemb\" from https://github.com/bheinzerling/bpemb 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: Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE) After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"bheinzerling-bpemb\",\"task\":\"Install Bpemb\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/bheinzerling/bpemb","github_repo":"bheinzerling/bpemb","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"bheinzerling/bpemb","recommendation_reasons":["Matches task terms: pair","Useful GitHub adoption: 1,220 stars","Install handoff is available","Repository freshness signal is available","Registry match score 6"],"urls":{"web":"https://www.openagentskill.com/skills/bheinzerling-bpemb","api":"https://www.openagentskill.com/api/agent/skills/bheinzerling-bpemb","install_api":"https://www.openagentskill.com/api/skills/bheinzerling-bpemb/install","audit":"https://www.openagentskill.com/skills/bheinzerling-bpemb/audit","repository":"https://github.com/bheinzerling/bpemb"}}],"meta":{"endpoint":"/api/skills/search","canonical_agent_endpoint":"/api/agent/resolve","lookup_intent":false,"exact_match_found":true,"match_counts":{"exact":1,"near":0,"related":9},"no_match_message":null,"safety_policy":"Blocked candidates are excluded by default. Pass include_blocked=true only for manual audit workflows.","agent_friendly":true,"api_version":"1.0","generated_at":"2026-08-23T08:07:05.222Z"}}