{"query":"Deep Research Agent","filters":{"category":null,"platform":null,"track":null,"safety":null,"include_blocked":false,"min_stars":0},"total":10,"skills":[{"rank":1,"match_score":99,"raw_match_score":1000.8,"slug":"tarun7r-deep-research-agent","name":"Deep Research Agent","description":"Multi-agent autonomous research system using LangGraph and LangChain. Generates citation-backed reports with credibility scoring and web search","tagline":"Multi-agent autonomous research system using LangGraph and LangChain. Generates citation-backed reports with credibility scoring and web search","category":"research","tags":["deep-research","agent","research","agentic-ai","ai-agents","deepresearch","gemini","langchain","langgraph","ollama-api"],"author":{"name":"tarun7r","verified":false,"url":"https://github.com/tarun7r"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"tarun7r/deep-research-agent","creatorName":"tarun7r","creatorUrl":"https://github.com/tarun7r","sourceUrl":"https://github.com/tarun7r/deep-research-agent","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/tarun7r-deep-research-agent#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":173,"forks":29,"downloads":0,"rating":0,"review_count":0,"quality_score":46.38},"quality":{"score":74,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"173","tone":"neutral"},{"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":79,"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":"173 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"173 stars, 29 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":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":90,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":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 tarun7r/deep-research-agent"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":72,"weight":0.07,"status":"info","detail":"filesystem or document access, network or browser access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/tarun7r/deep-research-agent"},{"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":"173 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"173 stars, 29 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"pass","label":"Dependency/runtime risk","detail":"network or browser surface"},{"status":"pass","label":"Install availability","detail":"npx skills add tarun7r/deep-research-agent"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"filesystem or document access, network or browser access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/tarun7r/deep-research-agent"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Stars/forks activity: 173 stars, 29 forks; issue activity unavailable in current metadata"],"evidence":{"stars":"173 GitHub stars","repoActivity":"173 stars, 29 forks","lastPushed":"3mo since push","license":"MIT","repository":"https://github.com/tarun7r/deep-research-agent","install":"npx skills add tarun7r/deep-research-agent","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access, network or browser access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add tarun7r/deep-research-agent","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":["Python","Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Stars/forks activity: 173 stars, 29 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":["research","deep-research","agent","agentic-ai","ai-agents","deepresearch"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Stars/forks activity: 173 stars, 29 forks; issue activity unavailable in current metadata"]},"safety":{"score":65,"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":["Quality score needs review","65/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["Quality score needs review"],"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":["Quality score needs review","65/100 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":"research-agents","title":"Research agents"},{"slug":"github-automation","title":"GitHub automation"}]},"applicableAgents":["Claude Code","LangChain","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add tarun7r/deep-research-agent","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":173,"starsLabel":"173","forks":29,"license":"MIT","qualityScore":74,"trustScore":79,"auditScore":81},"maintenance":{"status":"active","label":"3mo since push","daysSincePush":90,"lastPushedAt":"2026-04-04T17:51:43+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Quality score needs review","Stars/forks activity: 173 stars, 29 forks; issue activity unavailable in current metadata","Needs review"]},"coverageTags":["Research","RAG and knowledge","deep-research","agent","agentic-ai","ai-agents","deepresearch","gemini"]},"audit":{"audit_score":81,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Stars/forks activity: 173 stars, 29 forks; issue activity unavailable in current metadata"]},"decision":{"readiness_score":73,"readiness_label":"Strong shortlist","headline":"Companion skill for RAG and knowledge","role":"Companion skill","primary_fit":"RAG and knowledge","best_for":["RAG and knowledge 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 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":"tarun7r-deep-research-agent","name":"Deep Research Agent","description":"Multi-agent autonomous research system using LangGraph and LangChain. Generates citation-backed reports with credibility scoring and web search","category":"research","url":"https://www.openagentskill.com/skills/tarun7r-deep-research-agent","repository":"https://github.com/tarun7r/deep-research-agent","github_repo":"tarun7r/deep-research-agent"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","builders willing to evaluate younger projects","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Search sources","Extract claims"],"suited_agents":["Python","Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","LangChain","CLI"],"install":{"command":"npx skills add tarun7r/deep-research-agent","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add tarun7r/deep-research-agent"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Deep Research Agent\" agent skill from https://github.com/tarun7r/deep-research-agent. 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: Multi-agent autonomous research system using LangGraph and LangChain. Generates citation-backed reports with credibility scoring and web search"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Deep Research Agent\" as a Claude Code skill from https://github.com/tarun7r/deep-research-agent. 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: Multi-agent autonomous research system using LangGraph and LangChain. Generates citation-backed reports with credibility scoring and web search"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Deep Research Agent\" from https://github.com/tarun7r/deep-research-agent 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: Multi-agent autonomous research system using LangGraph and LangChain. Generates citation-backed reports with credibility scoring and web search"}],"handoff_url":"https://www.openagentskill.com/api/skills/tarun7r-deep-research-agent/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/tarun7r-deep-research-agent"},"trust":{"score":79,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"173 GitHub stars","repoActivity":"173 stars, 29 forks","lastPushed":"3mo since push","license":"MIT","repository":"https://github.com/tarun7r/deep-research-agent","install":"npx skills add tarun7r/deep-research-agent","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access, network or browser access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","deep-research","agent","agentic-ai","ai-agents","deepresearch"],"known_risks":["Quality score needs review","Stars/forks activity: 173 stars, 29 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":81,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Stars/forks activity: 173 stars, 29 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":74,"label":"Strong"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","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","Quality score needs review","Stars/forks activity: 173 stars, 29 forks; issue activity unavailable in current metadata","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use Deep Research Agent in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 79/100 Strong shortlist","Audit: 81/100 Needs review","Safety: 65/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"tarun7r-deep-research-agent (Deep Research Agent)","install_command":"npx skills add tarun7r/deep-research-agent","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":"tarun7r-deep-research-agent","task":"Use Deep Research Agent 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/tarun7r-deep-research-agent","api":"https://www.openagentskill.com/api/agent/skills/tarun7r-deep-research-agent","audit":"https://www.openagentskill.com/skills/tarun7r-deep-research-agent/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=tarun7r-deep-research-agent&task=Use%20Deep%20Research%20Agent%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Deep%20Research%20Agent%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Deep%20Research%20Agent%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/tarun7r-deep-research-agent/install","manifest":"https://www.openagentskill.com/api/registry/manifest/tarun7r-deep-research-agent"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"tarun7r-deep-research-agent","name":"Deep Research Agent","description":"Multi-agent autonomous research system using LangGraph and LangChain. Generates citation-backed reports with credibility scoring and web search","category":"research","url":"https://www.openagentskill.com/skills/tarun7r-deep-research-agent","repository":"https://github.com/tarun7r/deep-research-agent","github_repo":"tarun7r/deep-research-agent"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","builders willing to evaluate younger projects","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Search sources","Extract claims"],"suited_agents":["Python","Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","LangChain","CLI"],"install":{"command":"npx skills add tarun7r/deep-research-agent","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add tarun7r/deep-research-agent"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Deep Research Agent\" agent skill from https://github.com/tarun7r/deep-research-agent. 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: Multi-agent autonomous research system using LangGraph and LangChain. Generates citation-backed reports with credibility scoring and web search"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Deep Research Agent\" as a Claude Code skill from https://github.com/tarun7r/deep-research-agent. 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: Multi-agent autonomous research system using LangGraph and LangChain. Generates citation-backed reports with credibility scoring and web search"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Deep Research Agent\" from https://github.com/tarun7r/deep-research-agent 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: Multi-agent autonomous research system using LangGraph and LangChain. Generates citation-backed reports with credibility scoring and web search"}],"handoff_url":"https://www.openagentskill.com/api/skills/tarun7r-deep-research-agent/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/tarun7r-deep-research-agent"},"trust":{"score":79,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"173 GitHub stars","repoActivity":"173 stars, 29 forks","lastPushed":"3mo since push","license":"MIT","repository":"https://github.com/tarun7r/deep-research-agent","install":"npx skills add tarun7r/deep-research-agent","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access, network or browser access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","deep-research","agent","agentic-ai","ai-agents","deepresearch"],"known_risks":["Quality score needs review","Stars/forks activity: 173 stars, 29 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":81,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Stars/forks activity: 173 stars, 29 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":74,"label":"Strong"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","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","Quality score needs review","Stars/forks activity: 173 stars, 29 forks; issue activity unavailable in current metadata","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use Deep Research Agent in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 79/100 Strong shortlist","Audit: 81/100 Needs review","Safety: 65/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"tarun7r-deep-research-agent (Deep Research Agent)","install_command":"npx skills add tarun7r/deep-research-agent","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":"tarun7r-deep-research-agent","task":"Use Deep Research Agent 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/tarun7r-deep-research-agent","api":"https://www.openagentskill.com/api/agent/skills/tarun7r-deep-research-agent","audit":"https://www.openagentskill.com/skills/tarun7r-deep-research-agent/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=tarun7r-deep-research-agent&task=Use%20Deep%20Research%20Agent%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Deep%20Research%20Agent%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Deep%20Research%20Agent%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/tarun7r-deep-research-agent/install","manifest":"https://www.openagentskill.com/api/registry/manifest/tarun7r-deep-research-agent"}},"platforms":["Python","Research Agent","Claude Code","LangChain"],"use_cases":[{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"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"}],"install":"npx skills add tarun7r/deep-research-agent","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add tarun7r/deep-research-agent","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Deep Research Agent\" agent skill from https://github.com/tarun7r/deep-research-agent. 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: Multi-agent autonomous research system using LangGraph and LangChain. Generates citation-backed reports with credibility scoring and web search","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 \"Deep Research Agent\" as a Claude Code skill from https://github.com/tarun7r/deep-research-agent. 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: Multi-agent autonomous research system using LangGraph and LangChain. Generates citation-backed reports with credibility scoring and web search","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 \"Deep Research Agent\" from https://github.com/tarun7r/deep-research-agent 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: Multi-agent autonomous research system using LangGraph and LangChain. Generates citation-backed reports with credibility scoring and web search","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/tarun7r/deep-research-agent","github_repo":"tarun7r/deep-research-agent","version":"1.0.0","license":"MIT","updated_at":"2026-06-21T06:49:26.597222+00:00","canonical_key":"tarun7r/deep-research-agent","recommendation_reasons":["Matches task terms: deep, research, agent","Install handoff is available","Repository freshness signal is available","Registry match score 99"],"urls":{"web":"https://www.openagentskill.com/skills/tarun7r-deep-research-agent","api":"https://www.openagentskill.com/api/agent/skills/tarun7r-deep-research-agent","install_api":"https://www.openagentskill.com/api/skills/tarun7r-deep-research-agent/install","audit":"https://www.openagentskill.com/skills/tarun7r-deep-research-agent/audit","repository":"https://github.com/tarun7r/deep-research-agent"}},{"rank":2,"match_score":73,"raw_match_score":742.5,"slug":"ai-agents-2030-awesome-deep-research-agent","name":"Awesome Deep Research Agent","description":"ai-agents-2030/awesome-deep-research-agent is a high-star GitHub project relevant to AI agent workflows.","tagline":"ai-agents-2030/awesome-deep-research-agent is a high-star GitHub project relevant to AI agent workflows.","category":"research","tags":["deep-research","agent","research","github"],"author":{"name":"ai-agents-2030","verified":false,"url":"https://github.com/ai-agents-2030"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"ai-agents-2030/awesome-deep-research-agent","creatorName":"ai-agents-2030","creatorUrl":"https://github.com/ai-agents-2030","sourceUrl":"https://github.com/ai-agents-2030/awesome-deep-research-agent","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/ai-agents-2030-awesome-deep-research-agent#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":620,"forks":56,"downloads":0,"rating":0,"review_count":0,"quality_score":42.25},"quality":{"score":62,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"620","tone":"positive"},{"label":"Freshness","value":"10mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":76,"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":76,"weight":0.13,"status":"info","detail":"620 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":71,"weight":0.08,"status":"info","detail":"620 stars, 56 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":62,"weight":0.14,"status":"info","detail":"10mo since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":90,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add ai-agents-2030/awesome-deep-research-agent"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/ai-agents-2030/awesome-deep-research-agent"},{"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":"620 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"620 stars, 56 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"10mo since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add ai-agents-2030/awesome-deep-research-agent"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/ai-agents-2030/awesome-deep-research-agent"},{"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","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["License is unclear","Quality score needs review","License clarity: Unknown"],"evidence":{"stars":"620 GitHub stars","repoActivity":"620 stars, 56 forks","lastPushed":"10mo since push","license":"Unknown","repository":"https://github.com/ai-agents-2030/awesome-deep-research-agent","install":"npx skills add ai-agents-2030/awesome-deep-research-agent","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add ai-agents-2030/awesome-deep-research-agent","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","No Agent Proven outcome evidence yet","10mo since push"]},"agentCompatibility":["Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Quality score needs review","License clarity: Unknown"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["research","deep-research","agent","github","Research Agent"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","Quality score needs review","License clarity: Unknown"]},"safety":{"score":57,"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":["License is unclear","57/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["License is unclear"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","reasons":["License is unclear","57/100 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":"research-agents","title":"Research agents"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","Research Agent"],"install":{"ready":true,"command":"npx skills add ai-agents-2030/awesome-deep-research-agent","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":620,"starsLabel":"620","forks":56,"license":"Unknown","qualityScore":62,"trustScore":76,"auditScore":73},"maintenance":{"status":"stable","label":"10mo since push","daysSincePush":288,"lastPushedAt":"2025-09-18T18:48:52+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["License is unclear","Quality score needs review","License clarity: Unknown","Needs review"]},"coverageTags":["Research","RAG and knowledge","deep-research","agent","github","Research Agent"]},"audit":{"audit_score":73,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Quality score needs review","License clarity: Unknown"]},"decision":{"readiness_score":64,"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","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one RAG and knowledge task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"ai-agents-2030-awesome-deep-research-agent","name":"Awesome Deep Research Agent","description":"ai-agents-2030/awesome-deep-research-agent is a high-star GitHub project relevant to AI agent workflows.","category":"research","url":"https://www.openagentskill.com/skills/ai-agents-2030-awesome-deep-research-agent","repository":"https://github.com/ai-agents-2030/awesome-deep-research-agent","github_repo":"ai-agents-2030/awesome-deep-research-agent"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Inspect source files","Explain architecture"],"suited_agents":["Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add ai-agents-2030/awesome-deep-research-agent","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add ai-agents-2030/awesome-deep-research-agent"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Awesome Deep Research Agent\" agent skill from https://github.com/ai-agents-2030/awesome-deep-research-agent. 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: ai-agents-2030/awesome-deep-research-agent is a high-star GitHub project relevant to AI agent workflows."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Awesome Deep Research Agent\" as a Claude Code skill from https://github.com/ai-agents-2030/awesome-deep-research-agent. 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: ai-agents-2030/awesome-deep-research-agent is a high-star GitHub project relevant to AI agent workflows."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Awesome Deep Research Agent\" from https://github.com/ai-agents-2030/awesome-deep-research-agent 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: ai-agents-2030/awesome-deep-research-agent is a high-star GitHub project relevant to AI agent workflows."}],"handoff_url":"https://www.openagentskill.com/api/skills/ai-agents-2030-awesome-deep-research-agent/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/ai-agents-2030-awesome-deep-research-agent"},"trust":{"score":76,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"620 GitHub stars","repoActivity":"620 stars, 56 forks","lastPushed":"10mo since push","license":"Unknown","repository":"https://github.com/ai-agents-2030/awesome-deep-research-agent","install":"npx skills add ai-agents-2030/awesome-deep-research-agent","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","deep-research","agent","github","Research Agent"],"known_risks":["License is unclear","Quality score needs review","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":73,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Quality score needs review","License clarity: Unknown"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":62,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"10mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Quality score needs review","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Awesome Deep Research Agent 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: 76/100 Strong shortlist","Audit: 73/100 Needs review","Safety: 57/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"ai-agents-2030-awesome-deep-research-agent (Awesome Deep Research Agent)","install_command":"npx skills add ai-agents-2030/awesome-deep-research-agent","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":"ai-agents-2030-awesome-deep-research-agent","task":"Use Awesome Deep Research Agent 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/ai-agents-2030-awesome-deep-research-agent","api":"https://www.openagentskill.com/api/agent/skills/ai-agents-2030-awesome-deep-research-agent","audit":"https://www.openagentskill.com/skills/ai-agents-2030-awesome-deep-research-agent/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=ai-agents-2030-awesome-deep-research-agent&task=Use%20Awesome%20Deep%20Research%20Agent%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Awesome%20Deep%20Research%20Agent%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Awesome%20Deep%20Research%20Agent%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/ai-agents-2030-awesome-deep-research-agent/install","manifest":"https://www.openagentskill.com/api/registry/manifest/ai-agents-2030-awesome-deep-research-agent"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"ai-agents-2030-awesome-deep-research-agent","name":"Awesome Deep Research Agent","description":"ai-agents-2030/awesome-deep-research-agent is a high-star GitHub project relevant to AI agent workflows.","category":"research","url":"https://www.openagentskill.com/skills/ai-agents-2030-awesome-deep-research-agent","repository":"https://github.com/ai-agents-2030/awesome-deep-research-agent","github_repo":"ai-agents-2030/awesome-deep-research-agent"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Inspect source files","Explain architecture"],"suited_agents":["Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add ai-agents-2030/awesome-deep-research-agent","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add ai-agents-2030/awesome-deep-research-agent"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Awesome Deep Research Agent\" agent skill from https://github.com/ai-agents-2030/awesome-deep-research-agent. 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: ai-agents-2030/awesome-deep-research-agent is a high-star GitHub project relevant to AI agent workflows."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Awesome Deep Research Agent\" as a Claude Code skill from https://github.com/ai-agents-2030/awesome-deep-research-agent. 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: ai-agents-2030/awesome-deep-research-agent is a high-star GitHub project relevant to AI agent workflows."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Awesome Deep Research Agent\" from https://github.com/ai-agents-2030/awesome-deep-research-agent 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: ai-agents-2030/awesome-deep-research-agent is a high-star GitHub project relevant to AI agent workflows."}],"handoff_url":"https://www.openagentskill.com/api/skills/ai-agents-2030-awesome-deep-research-agent/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/ai-agents-2030-awesome-deep-research-agent"},"trust":{"score":76,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"620 GitHub stars","repoActivity":"620 stars, 56 forks","lastPushed":"10mo since push","license":"Unknown","repository":"https://github.com/ai-agents-2030/awesome-deep-research-agent","install":"npx skills add ai-agents-2030/awesome-deep-research-agent","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","deep-research","agent","github","Research Agent"],"known_risks":["License is unclear","Quality score needs review","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":73,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Quality score needs review","License clarity: Unknown"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":62,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"10mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Quality score needs review","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Awesome Deep Research Agent 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: 76/100 Strong shortlist","Audit: 73/100 Needs review","Safety: 57/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"ai-agents-2030-awesome-deep-research-agent (Awesome Deep Research Agent)","install_command":"npx skills add ai-agents-2030/awesome-deep-research-agent","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":"ai-agents-2030-awesome-deep-research-agent","task":"Use Awesome Deep Research Agent 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/ai-agents-2030-awesome-deep-research-agent","api":"https://www.openagentskill.com/api/agent/skills/ai-agents-2030-awesome-deep-research-agent","audit":"https://www.openagentskill.com/skills/ai-agents-2030-awesome-deep-research-agent/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=ai-agents-2030-awesome-deep-research-agent&task=Use%20Awesome%20Deep%20Research%20Agent%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Awesome%20Deep%20Research%20Agent%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Awesome%20Deep%20Research%20Agent%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/ai-agents-2030-awesome-deep-research-agent/install","manifest":"https://www.openagentskill.com/api/registry/manifest/ai-agents-2030-awesome-deep-research-agent"}},"platforms":["Research Agent","Claude Code"],"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":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"install":"npx skills add ai-agents-2030/awesome-deep-research-agent","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add ai-agents-2030/awesome-deep-research-agent","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Awesome Deep Research Agent\" agent skill from https://github.com/ai-agents-2030/awesome-deep-research-agent. 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: ai-agents-2030/awesome-deep-research-agent is a high-star GitHub project relevant to AI agent workflows.","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 \"Awesome Deep Research Agent\" as a Claude Code skill from https://github.com/ai-agents-2030/awesome-deep-research-agent. 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: ai-agents-2030/awesome-deep-research-agent is a high-star GitHub project relevant to AI agent workflows.","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 \"Awesome Deep Research Agent\" from https://github.com/ai-agents-2030/awesome-deep-research-agent 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: ai-agents-2030/awesome-deep-research-agent is a high-star GitHub project relevant to AI agent workflows.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/ai-agents-2030/awesome-deep-research-agent","github_repo":"ai-agents-2030/awesome-deep-research-agent","version":"1.0.0","license":"Unknown","updated_at":"2026-06-14T13:01:04.438223+00:00","canonical_key":"ai-agents-2030/awesome-deep-research-agent","recommendation_reasons":["Matches task terms: deep, research, agent","Useful GitHub adoption: 620 stars","Install handoff is available","Repository freshness signal is available","Registry match score 73"],"urls":{"web":"https://www.openagentskill.com/skills/ai-agents-2030-awesome-deep-research-agent","api":"https://www.openagentskill.com/api/agent/skills/ai-agents-2030-awesome-deep-research-agent","install_api":"https://www.openagentskill.com/api/skills/ai-agents-2030-awesome-deep-research-agent/install","audit":"https://www.openagentskill.com/skills/ai-agents-2030-awesome-deep-research-agent/audit","repository":"https://github.com/ai-agents-2030/awesome-deep-research-agent"}},{"rank":3,"match_score":73,"raw_match_score":741.7,"slug":"liangdabiao-claude-code-stock-deep-research-agent","name":"Claude Code Stock Deep Research Agent","description":"本研究基于 Claude Code Deep Research 系统：  方法论: 8阶段股票投资尽调框架 智能体: 28个并行研究智能体 工具: WebSearch、WebFetch、综合分析 质量: 多空平衡、明确风险、数据验证。简单使用：/stock-research AAPL, I want a quick overview","tagline":"本研究基于 Claude Code Deep Research 系统：  方法论: 8阶段股票投资尽调框架 智能体: 28个并行研究智能体 工具: WebSearch、WebFetch、综合分析 质量: 多空平衡、明确风险、数据验证。简单使用：/stock-research AAPL, I want a quick overview","category":"research","tags":["deep-research","agent","research","claude-code","github"],"author":{"name":"liangdabiao","verified":false,"url":"https://github.com/liangdabiao"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"liangdabiao/Claude-Code-Stock-Deep-Research-Agent","creatorName":"liangdabiao","creatorUrl":"https://github.com/liangdabiao","sourceUrl":"https://github.com/liangdabiao/Claude-Code-Stock-Deep-Research-Agent","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/liangdabiao-claude-code-stock-deep-research-agent#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":332,"forks":76,"downloads":0,"rating":0,"review_count":0,"quality_score":44.36},"quality":{"score":67,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"332","tone":"neutral"},{"label":"Freshness","value":"4mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":76,"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":"332 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":62,"weight":0.08,"status":"info","detail":"332 stars, 76 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"4mo since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":90,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/liangdabiao/Claude-Code-Stock-Deep-Research-Agent"},{"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":"332 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"332 stars, 76 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"4mo since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/liangdabiao/Claude-Code-Stock-Deep-Research-Agent"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Install command has no obvious high-risk pattern"],"warnings":["License is unclear","Quality score needs review","License clarity: Unknown"],"evidence":{"stars":"332 GitHub stars","repoActivity":"332 stars, 76 forks","lastPushed":"4mo since push","license":"Unknown","repository":"https://github.com/liangdabiao/Claude-Code-Stock-Deep-Research-Agent","install":"npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","No Agent Proven outcome evidence yet","4mo since push"]},"agentCompatibility":["Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Quality score needs review","License clarity: Unknown"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["research","deep-research","agent","claude-code","github","Research Agent"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","Quality score needs review","License clarity: Unknown"]},"safety":{"score":60,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["License is unclear","60/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["License is unclear"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["License is unclear","60/100 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":"coding-agents","title":"Coding agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","Research Agent"],"install":{"ready":true,"command":"npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":332,"starsLabel":"332","forks":76,"license":"Unknown","qualityScore":67,"trustScore":76,"auditScore":76},"maintenance":{"status":"active","label":"4mo since push","daysSincePush":118,"lastPushedAt":"2026-03-07T16:48:07+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["License is unclear","Quality score needs review","License clarity: Unknown","Needs review"]},"coverageTags":["Research","RAG and knowledge","deep-research","agent","claude-code","github","Research Agent"]},"audit":{"audit_score":76,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Quality score needs review","License clarity: Unknown"]},"decision":{"readiness_score":66,"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":"liangdabiao-claude-code-stock-deep-research-agent","name":"Claude Code Stock Deep Research Agent","description":"本研究基于 Claude Code Deep Research 系统：  方法论: 8阶段股票投资尽调框架 智能体: 28个并行研究智能体 工具: WebSearch、WebFetch、综合分析 质量: 多空平衡、明确风险、数据验证。简单使用：/stock-research AAPL, I want a quick overview","category":"research","url":"https://www.openagentskill.com/skills/liangdabiao-claude-code-stock-deep-research-agent","repository":"https://github.com/liangdabiao/Claude-Code-Stock-Deep-Research-Agent","github_repo":"liangdabiao/Claude-Code-Stock-Deep-Research-Agent"},"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Chunk documents","Create embeddings"],"suited_agents":["Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Claude Code Stock Deep Research Agent\" agent skill from https://github.com/liangdabiao/Claude-Code-Stock-Deep-Research-Agent. 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: 本研究基于 Claude Code Deep Research 系统： 方法论: 8阶段股票投资尽调框架 智能体: 28个并行研究智能体 工具: WebSearch、WebFetch、综合分析 质量: 多空平衡、明确风险、数据验证。简单使用：/stock-research AAPL, I want a quick overview"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Claude Code Stock Deep Research Agent\" as a Claude Code skill from https://github.com/liangdabiao/Claude-Code-Stock-Deep-Research-Agent. 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: 本研究基于 Claude Code Deep Research 系统： 方法论: 8阶段股票投资尽调框架 智能体: 28个并行研究智能体 工具: WebSearch、WebFetch、综合分析 质量: 多空平衡、明确风险、数据验证。简单使用：/stock-research AAPL, I want a quick overview"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Claude Code Stock Deep Research Agent\" from https://github.com/liangdabiao/Claude-Code-Stock-Deep-Research-Agent 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: 本研究基于 Claude Code Deep Research 系统： 方法论: 8阶段股票投资尽调框架 智能体: 28个并行研究智能体 工具: WebSearch、WebFetch、综合分析 质量: 多空平衡、明确风险、数据验证。简单使用：/stock-research AAPL, I want a quick overview"}],"handoff_url":"https://www.openagentskill.com/api/skills/liangdabiao-claude-code-stock-deep-research-agent/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/liangdabiao-claude-code-stock-deep-research-agent"},"trust":{"score":76,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"332 GitHub stars","repoActivity":"332 stars, 76 forks","lastPushed":"4mo since push","license":"Unknown","repository":"https://github.com/liangdabiao/Claude-Code-Stock-Deep-Research-Agent","install":"npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","deep-research","agent","claude-code","github","Research Agent"],"known_risks":["License is unclear","Quality score needs review","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":76,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Quality score needs review","License clarity: Unknown"]},"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":67,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"4mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Quality score needs review","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Claude Code Stock Deep Research Agent in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 76/100 Strong shortlist","Audit: 76/100 Needs review","Safety: 60/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"liangdabiao-claude-code-stock-deep-research-agent (Claude Code Stock Deep Research Agent)","install_command":"npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent","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":"liangdabiao-claude-code-stock-deep-research-agent","task":"Use Claude Code Stock Deep Research Agent 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/liangdabiao-claude-code-stock-deep-research-agent","api":"https://www.openagentskill.com/api/agent/skills/liangdabiao-claude-code-stock-deep-research-agent","audit":"https://www.openagentskill.com/skills/liangdabiao-claude-code-stock-deep-research-agent/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=liangdabiao-claude-code-stock-deep-research-agent&task=Use%20Claude%20Code%20Stock%20Deep%20Research%20Agent%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Claude%20Code%20Stock%20Deep%20Research%20Agent%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Claude%20Code%20Stock%20Deep%20Research%20Agent%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/liangdabiao-claude-code-stock-deep-research-agent/install","manifest":"https://www.openagentskill.com/api/registry/manifest/liangdabiao-claude-code-stock-deep-research-agent"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"liangdabiao-claude-code-stock-deep-research-agent","name":"Claude Code Stock Deep Research Agent","description":"本研究基于 Claude Code Deep Research 系统：  方法论: 8阶段股票投资尽调框架 智能体: 28个并行研究智能体 工具: WebSearch、WebFetch、综合分析 质量: 多空平衡、明确风险、数据验证。简单使用：/stock-research AAPL, I want a quick overview","category":"research","url":"https://www.openagentskill.com/skills/liangdabiao-claude-code-stock-deep-research-agent","repository":"https://github.com/liangdabiao/Claude-Code-Stock-Deep-Research-Agent","github_repo":"liangdabiao/Claude-Code-Stock-Deep-Research-Agent"},"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Chunk documents","Create embeddings"],"suited_agents":["Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Claude Code Stock Deep Research Agent\" agent skill from https://github.com/liangdabiao/Claude-Code-Stock-Deep-Research-Agent. 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: 本研究基于 Claude Code Deep Research 系统： 方法论: 8阶段股票投资尽调框架 智能体: 28个并行研究智能体 工具: WebSearch、WebFetch、综合分析 质量: 多空平衡、明确风险、数据验证。简单使用：/stock-research AAPL, I want a quick overview"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Claude Code Stock Deep Research Agent\" as a Claude Code skill from https://github.com/liangdabiao/Claude-Code-Stock-Deep-Research-Agent. 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: 本研究基于 Claude Code Deep Research 系统： 方法论: 8阶段股票投资尽调框架 智能体: 28个并行研究智能体 工具: WebSearch、WebFetch、综合分析 质量: 多空平衡、明确风险、数据验证。简单使用：/stock-research AAPL, I want a quick overview"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Claude Code Stock Deep Research Agent\" from https://github.com/liangdabiao/Claude-Code-Stock-Deep-Research-Agent 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: 本研究基于 Claude Code Deep Research 系统： 方法论: 8阶段股票投资尽调框架 智能体: 28个并行研究智能体 工具: WebSearch、WebFetch、综合分析 质量: 多空平衡、明确风险、数据验证。简单使用：/stock-research AAPL, I want a quick overview"}],"handoff_url":"https://www.openagentskill.com/api/skills/liangdabiao-claude-code-stock-deep-research-agent/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/liangdabiao-claude-code-stock-deep-research-agent"},"trust":{"score":76,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"332 GitHub stars","repoActivity":"332 stars, 76 forks","lastPushed":"4mo since push","license":"Unknown","repository":"https://github.com/liangdabiao/Claude-Code-Stock-Deep-Research-Agent","install":"npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","deep-research","agent","claude-code","github","Research Agent"],"known_risks":["License is unclear","Quality score needs review","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":76,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Quality score needs review","License clarity: Unknown"]},"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":67,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"4mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Quality score needs review","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Claude Code Stock Deep Research Agent in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 76/100 Strong shortlist","Audit: 76/100 Needs review","Safety: 60/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"liangdabiao-claude-code-stock-deep-research-agent (Claude Code Stock Deep Research Agent)","install_command":"npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent","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":"liangdabiao-claude-code-stock-deep-research-agent","task":"Use Claude Code Stock Deep Research Agent 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/liangdabiao-claude-code-stock-deep-research-agent","api":"https://www.openagentskill.com/api/agent/skills/liangdabiao-claude-code-stock-deep-research-agent","audit":"https://www.openagentskill.com/skills/liangdabiao-claude-code-stock-deep-research-agent/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=liangdabiao-claude-code-stock-deep-research-agent&task=Use%20Claude%20Code%20Stock%20Deep%20Research%20Agent%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Claude%20Code%20Stock%20Deep%20Research%20Agent%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Claude%20Code%20Stock%20Deep%20Research%20Agent%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/liangdabiao-claude-code-stock-deep-research-agent/install","manifest":"https://www.openagentskill.com/api/registry/manifest/liangdabiao-claude-code-stock-deep-research-agent"}},"platforms":["Research Agent","Claude Code"],"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"}],"install":"npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add liangdabiao/Claude-Code-Stock-Deep-Research-Agent","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Claude Code Stock Deep Research Agent\" agent skill from https://github.com/liangdabiao/Claude-Code-Stock-Deep-Research-Agent. 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: 本研究基于 Claude Code Deep Research 系统： 方法论: 8阶段股票投资尽调框架 智能体: 28个并行研究智能体 工具: WebSearch、WebFetch、综合分析 质量: 多空平衡、明确风险、数据验证。简单使用：/stock-research AAPL, I want a quick overview","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 Code Stock Deep Research Agent\" as a Claude Code skill from https://github.com/liangdabiao/Claude-Code-Stock-Deep-Research-Agent. 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: 本研究基于 Claude Code Deep Research 系统： 方法论: 8阶段股票投资尽调框架 智能体: 28个并行研究智能体 工具: WebSearch、WebFetch、综合分析 质量: 多空平衡、明确风险、数据验证。简单使用：/stock-research AAPL, I want a quick overview","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 Code Stock Deep Research Agent\" from https://github.com/liangdabiao/Claude-Code-Stock-Deep-Research-Agent 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: 本研究基于 Claude Code Deep Research 系统： 方法论: 8阶段股票投资尽调框架 智能体: 28个并行研究智能体 工具: WebSearch、WebFetch、综合分析 质量: 多空平衡、明确风险、数据验证。简单使用：/stock-research AAPL, I want a quick overview","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/liangdabiao/Claude-Code-Stock-Deep-Research-Agent","github_repo":"liangdabiao/Claude-Code-Stock-Deep-Research-Agent","version":"1.0.0","license":"Unknown","updated_at":"2026-06-16T09:59:52.977662+00:00","canonical_key":"liangdabiao/claude-code-stock-deep-research-agent","recommendation_reasons":["Matches task terms: deep, research, agent","Install handoff is available","Repository freshness signal is available","Registry match score 73"],"urls":{"web":"https://www.openagentskill.com/skills/liangdabiao-claude-code-stock-deep-research-agent","api":"https://www.openagentskill.com/api/agent/skills/liangdabiao-claude-code-stock-deep-research-agent","install_api":"https://www.openagentskill.com/api/skills/liangdabiao-claude-code-stock-deep-research-agent/install","audit":"https://www.openagentskill.com/skills/liangdabiao-claude-code-stock-deep-research-agent/audit","repository":"https://github.com/liangdabiao/Claude-Code-Stock-Deep-Research-Agent"}},{"rank":4,"match_score":45,"raw_match_score":451.1,"slug":"ayanami0730-deep-research-bench","name":"Deep Research Bench","description":"DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents","tagline":"DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents","category":"research","tags":["deep-research","agent","research","benchmark","deepresearch","nlp","python","github"],"author":{"name":"Ayanami0730","verified":false,"url":"https://github.com/Ayanami0730"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"Ayanami0730/deep_research_bench","creatorName":"Ayanami0730","creatorUrl":"https://github.com/Ayanami0730","sourceUrl":"https://github.com/Ayanami0730/deep_research_bench","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/ayanami0730-deep-research-bench#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":753,"forks":82,"downloads":0,"rating":0,"review_count":0,"quality_score":50.84},"quality":{"score":80,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"753","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":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":76,"weight":0.13,"status":"info","detail":"753 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":71,"weight":0.08,"status":"info","detail":"753 stars, 82 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":74,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add Ayanami0730/deep_research_bench"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/Ayanami0730/deep_research_bench"},{"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":"753 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"753 stars, 82 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 Ayanami0730/deep_research_bench"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/Ayanami0730/deep_research_bench"},{"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","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review"],"evidence":{"stars":"753 GitHub stars","repoActivity":"753 stars, 82 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/Ayanami0730/deep_research_bench","install":"npx skills add Ayanami0730/deep_research_bench","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add Ayanami0730/deep_research_bench","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 Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review"]},"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","deep-research","agent","benchmark","deepresearch","nlp"],"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"]},"safety":{"score":68,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","68/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["Quality score needs review"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","68/100 agent safety score"]},"supply_profile":{"track":{"slug":"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":"research-agents","title":"Research agents"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","Python"],"install":{"ready":true,"command":"npx skills add Ayanami0730/deep_research_bench","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":753,"starsLabel":"753","forks":82,"license":"Apache-2.0","qualityScore":80,"trustScore":81,"auditScore":84},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":53,"lastPushedAt":"2026-05-11T06:14:30+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Quality score needs review"]},"coverageTags":["Research","RAG and knowledge","deep-research","agent","benchmark","deepresearch","nlp","python"]},"audit":{"audit_score":84,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review"]},"decision":{"readiness_score":91,"readiness_label":"Production-ready","headline":"Primary pick for RAG and knowledge","role":"Primary pick","primary_fit":"RAG and knowledge","best_for":["RAG and knowledge workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one RAG and knowledge task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"ayanami0730-deep-research-bench","name":"Deep Research Bench","description":"DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents","category":"research","url":"https://www.openagentskill.com/skills/ayanami0730-deep-research-bench","repository":"https://github.com/Ayanami0730/deep_research_bench","github_repo":"Ayanami0730/deep_research_bench"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Inspect source files","Explain architecture"],"suited_agents":["Python","Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add Ayanami0730/deep_research_bench","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add Ayanami0730/deep_research_bench"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Deep Research Bench\" agent skill from https://github.com/Ayanami0730/deep_research_bench. 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: DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Deep Research Bench\" as a Claude Code skill from https://github.com/Ayanami0730/deep_research_bench. 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: DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Deep Research Bench\" from https://github.com/Ayanami0730/deep_research_bench 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: DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents"}],"handoff_url":"https://www.openagentskill.com/api/skills/ayanami0730-deep-research-bench/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/ayanami0730-deep-research-bench"},"trust":{"score":81,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"753 GitHub stars","repoActivity":"753 stars, 82 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/Ayanami0730/deep_research_bench","install":"npx skills add Ayanami0730/deep_research_bench","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","deep-research","agent","benchmark","deepresearch","nlp"],"known_risks":["Quality score needs review"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":84,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":80,"label":"Strong"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","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","Quality score needs review","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use Deep Research Bench 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: 81/100 Strong shortlist","Audit: 84/100 Safe to try","Safety: 68/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"ayanami0730-deep-research-bench (Deep Research Bench)","install_command":"npx skills add Ayanami0730/deep_research_bench","risk_summary":"Safe to try; Reviewed; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"ayanami0730-deep-research-bench","task":"Use Deep Research Bench 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/ayanami0730-deep-research-bench","api":"https://www.openagentskill.com/api/agent/skills/ayanami0730-deep-research-bench","audit":"https://www.openagentskill.com/skills/ayanami0730-deep-research-bench/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=ayanami0730-deep-research-bench&task=Use%20Deep%20Research%20Bench%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Deep%20Research%20Bench%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Deep%20Research%20Bench%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/ayanami0730-deep-research-bench/install","manifest":"https://www.openagentskill.com/api/registry/manifest/ayanami0730-deep-research-bench"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"ayanami0730-deep-research-bench","name":"Deep Research Bench","description":"DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents","category":"research","url":"https://www.openagentskill.com/skills/ayanami0730-deep-research-bench","repository":"https://github.com/Ayanami0730/deep_research_bench","github_repo":"Ayanami0730/deep_research_bench"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Inspect source files","Explain architecture"],"suited_agents":["Python","Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add Ayanami0730/deep_research_bench","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add Ayanami0730/deep_research_bench"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Deep Research Bench\" agent skill from https://github.com/Ayanami0730/deep_research_bench. 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: DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Deep Research Bench\" as a Claude Code skill from https://github.com/Ayanami0730/deep_research_bench. 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: DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Deep Research Bench\" from https://github.com/Ayanami0730/deep_research_bench 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: DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents"}],"handoff_url":"https://www.openagentskill.com/api/skills/ayanami0730-deep-research-bench/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/ayanami0730-deep-research-bench"},"trust":{"score":81,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"753 GitHub stars","repoActivity":"753 stars, 82 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/Ayanami0730/deep_research_bench","install":"npx skills add Ayanami0730/deep_research_bench","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","deep-research","agent","benchmark","deepresearch","nlp"],"known_risks":["Quality score needs review"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":84,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":80,"label":"Strong"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","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","Quality score needs review","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use Deep Research Bench 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: 81/100 Strong shortlist","Audit: 84/100 Safe to try","Safety: 68/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"ayanami0730-deep-research-bench (Deep Research Bench)","install_command":"npx skills add Ayanami0730/deep_research_bench","risk_summary":"Safe to try; Reviewed; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"ayanami0730-deep-research-bench","task":"Use Deep Research Bench 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/ayanami0730-deep-research-bench","api":"https://www.openagentskill.com/api/agent/skills/ayanami0730-deep-research-bench","audit":"https://www.openagentskill.com/skills/ayanami0730-deep-research-bench/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=ayanami0730-deep-research-bench&task=Use%20Deep%20Research%20Bench%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Deep%20Research%20Bench%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Deep%20Research%20Bench%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/ayanami0730-deep-research-bench/install","manifest":"https://www.openagentskill.com/api/registry/manifest/ayanami0730-deep-research-bench"}},"platforms":["Python","Research Agent","Claude Code"],"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":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"install":"npx skills add Ayanami0730/deep_research_bench","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add Ayanami0730/deep_research_bench","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Deep Research Bench\" agent skill from https://github.com/Ayanami0730/deep_research_bench. 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: DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents","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 \"Deep Research Bench\" as a Claude Code skill from https://github.com/Ayanami0730/deep_research_bench. 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: DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents","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 \"Deep Research Bench\" from https://github.com/Ayanami0730/deep_research_bench 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: DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/Ayanami0730/deep_research_bench","github_repo":"Ayanami0730/deep_research_bench","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-06-14T13:01:04.200426+00:00","canonical_key":"ayanami0730/deep_research_bench","recommendation_reasons":["Matches task terms: deep, research, agent","Useful GitHub adoption: 753 stars","Install handoff is available","Repository freshness signal is available","Registry match score 45"],"urls":{"web":"https://www.openagentskill.com/skills/ayanami0730-deep-research-bench","api":"https://www.openagentskill.com/api/agent/skills/ayanami0730-deep-research-bench","install_api":"https://www.openagentskill.com/api/skills/ayanami0730-deep-research-bench/install","audit":"https://www.openagentskill.com/skills/ayanami0730-deep-research-bench/audit","repository":"https://github.com/Ayanami0730/deep_research_bench"}},{"rank":5,"match_score":44,"raw_match_score":446.4,"slug":"dair-ai-m2-deep-research","name":"M2 Deep Research","description":"Deep research agents using MiniMax M2.1 interleaved thinking","tagline":"Deep research agents using MiniMax M2.1 interleaved thinking","category":"research","tags":["deep-research","agent","research","python","github"],"author":{"name":"dair-ai","verified":false,"url":"https://github.com/dair-ai"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"dair-ai/m2-deep-research","creatorName":"dair-ai","creatorUrl":"https://github.com/dair-ai","sourceUrl":"https://github.com/dair-ai/m2-deep-research","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/dair-ai-m2-deep-research#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":216,"forks":24,"downloads":0,"rating":0,"review_count":0,"quality_score":43.06},"quality":{"score":62,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"216","tone":"neutral"},{"label":"Freshness","value":"6mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":[]},"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":"216 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"216 stars, 24 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":62,"weight":0.14,"status":"info","detail":"6mo since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":74,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add dair-ai/m2-deep-research"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/dair-ai/m2-deep-research"},{"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":"216 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"216 stars, 24 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"6mo since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add dair-ai/m2-deep-research"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/dair-ai/m2-deep-research"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Install command has no obvious high-risk pattern"],"warnings":["License is unclear","Quality score needs review","Stars/forks activity: 216 stars, 24 forks; issue activity unavailable in current metadata","License clarity: Unknown"],"evidence":{"stars":"216 GitHub stars","repoActivity":"216 stars, 24 forks","lastPushed":"6mo since push","license":"Unknown","repository":"https://github.com/dair-ai/m2-deep-research","install":"npx skills add dair-ai/m2-deep-research","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add dair-ai/m2-deep-research","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","No Agent Proven outcome evidence yet","6mo since push"]},"agentCompatibility":["Python","Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Quality score needs review","Stars/forks activity: 216 stars, 24 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["research","deep-research","agent","python","github","Research Agent"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","Quality score needs review","Stars/forks activity: 216 stars, 24 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"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":["License is unclear","55/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["License is unclear"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","reasons":["License is unclear","55/100 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":"research-agents","title":"Research agents"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","Python"],"install":{"ready":true,"command":"npx skills add dair-ai/m2-deep-research","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":216,"starsLabel":"216","forks":24,"license":"Unknown","qualityScore":62,"trustScore":72,"auditScore":71},"maintenance":{"status":"stable","label":"6mo since push","daysSincePush":192,"lastPushedAt":"2025-12-23T16:20:45+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["License is unclear","Quality score needs review","Stars/forks activity: 216 stars, 24 forks; issue activity unavailable in current metadata","License clarity: Unknown","Needs review"]},"coverageTags":["Research","RAG and knowledge","deep-research","agent","python","github","Research Agent"]},"audit":{"audit_score":71,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Quality score needs review","Stars/forks activity: 216 stars, 24 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"decision":{"readiness_score":52,"readiness_label":"Needs manual review","headline":"Needs validation for RAG and knowledge","role":"Needs validation","primary_fit":"RAG and knowledge","best_for":["RAG and knowledge 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 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":"dair-ai-m2-deep-research","name":"M2 Deep Research","description":"Deep research agents using MiniMax M2.1 interleaved thinking","category":"research","url":"https://www.openagentskill.com/skills/dair-ai-m2-deep-research","repository":"https://github.com/dair-ai/m2-deep-research","github_repo":"dair-ai/m2-deep-research"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","builders willing to evaluate younger projects","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Inspect source files","Explain architecture"],"suited_agents":["Python","Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add dair-ai/m2-deep-research","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add dair-ai/m2-deep-research"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"M2 Deep Research\" agent skill from https://github.com/dair-ai/m2-deep-research. 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: Deep research agents using MiniMax M2.1 interleaved thinking"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"M2 Deep Research\" as a Claude Code skill from https://github.com/dair-ai/m2-deep-research. 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: Deep research agents using MiniMax M2.1 interleaved thinking"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"M2 Deep Research\" from https://github.com/dair-ai/m2-deep-research 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: Deep research agents using MiniMax M2.1 interleaved thinking"}],"handoff_url":"https://www.openagentskill.com/api/skills/dair-ai-m2-deep-research/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/dair-ai-m2-deep-research"},"trust":{"score":72,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"216 GitHub stars","repoActivity":"216 stars, 24 forks","lastPushed":"6mo since push","license":"Unknown","repository":"https://github.com/dair-ai/m2-deep-research","install":"npx skills add dair-ai/m2-deep-research","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","deep-research","agent","python","github","Research Agent"],"known_risks":["License is unclear","Quality score needs review","Stars/forks activity: 216 stars, 24 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":71,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Quality score needs review","Stars/forks activity: 216 stars, 24 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":62,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"6mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Quality score needs review","Stars/forks activity: 216 stars, 24 forks; issue activity unavailable in current metadata","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use M2 Deep Research 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: 71/100 Needs review","Safety: 55/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"dair-ai-m2-deep-research (M2 Deep Research)","install_command":"npx skills add dair-ai/m2-deep-research","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":"dair-ai-m2-deep-research","task":"Use M2 Deep Research 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/dair-ai-m2-deep-research","api":"https://www.openagentskill.com/api/agent/skills/dair-ai-m2-deep-research","audit":"https://www.openagentskill.com/skills/dair-ai-m2-deep-research/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=dair-ai-m2-deep-research&task=Use%20M2%20Deep%20Research%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20M2%20Deep%20Research%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20M2%20Deep%20Research%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/dair-ai-m2-deep-research/install","manifest":"https://www.openagentskill.com/api/registry/manifest/dair-ai-m2-deep-research"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"dair-ai-m2-deep-research","name":"M2 Deep Research","description":"Deep research agents using MiniMax M2.1 interleaved thinking","category":"research","url":"https://www.openagentskill.com/skills/dair-ai-m2-deep-research","repository":"https://github.com/dair-ai/m2-deep-research","github_repo":"dair-ai/m2-deep-research"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","builders willing to evaluate younger projects","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Inspect source files","Explain architecture"],"suited_agents":["Python","Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add dair-ai/m2-deep-research","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add dair-ai/m2-deep-research"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"M2 Deep Research\" agent skill from https://github.com/dair-ai/m2-deep-research. 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: Deep research agents using MiniMax M2.1 interleaved thinking"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"M2 Deep Research\" as a Claude Code skill from https://github.com/dair-ai/m2-deep-research. 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: Deep research agents using MiniMax M2.1 interleaved thinking"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"M2 Deep Research\" from https://github.com/dair-ai/m2-deep-research 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: Deep research agents using MiniMax M2.1 interleaved thinking"}],"handoff_url":"https://www.openagentskill.com/api/skills/dair-ai-m2-deep-research/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/dair-ai-m2-deep-research"},"trust":{"score":72,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"216 GitHub stars","repoActivity":"216 stars, 24 forks","lastPushed":"6mo since push","license":"Unknown","repository":"https://github.com/dair-ai/m2-deep-research","install":"npx skills add dair-ai/m2-deep-research","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","deep-research","agent","python","github","Research Agent"],"known_risks":["License is unclear","Quality score needs review","Stars/forks activity: 216 stars, 24 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":71,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Quality score needs review","Stars/forks activity: 216 stars, 24 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":62,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"6mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Quality score needs review","Stars/forks activity: 216 stars, 24 forks; issue activity unavailable in current metadata","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use M2 Deep Research 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: 71/100 Needs review","Safety: 55/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"dair-ai-m2-deep-research (M2 Deep Research)","install_command":"npx skills add dair-ai/m2-deep-research","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":"dair-ai-m2-deep-research","task":"Use M2 Deep Research 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/dair-ai-m2-deep-research","api":"https://www.openagentskill.com/api/agent/skills/dair-ai-m2-deep-research","audit":"https://www.openagentskill.com/skills/dair-ai-m2-deep-research/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=dair-ai-m2-deep-research&task=Use%20M2%20Deep%20Research%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20M2%20Deep%20Research%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20M2%20Deep%20Research%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/dair-ai-m2-deep-research/install","manifest":"https://www.openagentskill.com/api/registry/manifest/dair-ai-m2-deep-research"}},"platforms":["Python","Research Agent","Claude Code"],"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":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"install":"npx skills add dair-ai/m2-deep-research","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add dair-ai/m2-deep-research","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"M2 Deep Research\" agent skill from https://github.com/dair-ai/m2-deep-research. 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: Deep research agents using MiniMax M2.1 interleaved thinking","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 \"M2 Deep Research\" as a Claude Code skill from https://github.com/dair-ai/m2-deep-research. 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: Deep research agents using MiniMax M2.1 interleaved thinking","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 \"M2 Deep Research\" from https://github.com/dair-ai/m2-deep-research 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: Deep research agents using MiniMax M2.1 interleaved thinking","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/dair-ai/m2-deep-research","github_repo":"dair-ai/m2-deep-research","version":"1.0.0","license":"Unknown","updated_at":"2026-06-21T06:49:26.798224+00:00","canonical_key":"dair-ai/m2-deep-research","recommendation_reasons":["Matches task terms: deep, research, agent","Install handoff is available","Repository freshness signal is available","Registry match score 44"],"urls":{"web":"https://www.openagentskill.com/skills/dair-ai-m2-deep-research","api":"https://www.openagentskill.com/api/agent/skills/dair-ai-m2-deep-research","install_api":"https://www.openagentskill.com/api/skills/dair-ai-m2-deep-research/install","audit":"https://www.openagentskill.com/skills/dair-ai-m2-deep-research/audit","repository":"https://github.com/dair-ai/m2-deep-research"}},{"rank":6,"match_score":44,"raw_match_score":444.5,"slug":"liyuan24-nanodeepresearch","name":"NanoDeepResearch","description":"A Deep Research agent from scratch","tagline":"A Deep Research agent from scratch","category":"research","tags":["deep-research","agent","research","python","github"],"author":{"name":"liyuan24","verified":false,"url":"https://github.com/liyuan24"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"liyuan24/nanoDeepResearch","creatorName":"liyuan24","creatorUrl":"https://github.com/liyuan24","sourceUrl":"https://github.com/liyuan24/nanoDeepResearch","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/liyuan24-nanodeepresearch#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":221,"forks":33,"downloads":0,"rating":0,"review_count":0,"quality_score":35.12},"quality":{"score":45,"tier":"review","label":"Needs review","summary":"Inspect the repository carefully before adding it to an agent workflow.","signals":[{"label":"GitHub stars","value":"221","tone":"neutral"},{"label":"Freshness","value":"1y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":69,"tier":"review","label":"Manual review","summary":"Potentially useful, but at least one trust signal needs human inspection.","recommendedAction":"Inspect the repository, license, and recent activity before connecting it to agent workflows.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"221 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"221 stars, 33 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":38,"weight":0.14,"status":"fail","detail":"1y since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":74,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add liyuan24/nanoDeepResearch"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/liyuan24/nanoDeepResearch"},{"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":"221 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"221 stars, 33 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"1y since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add liyuan24/nanoDeepResearch"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/liyuan24/nanoDeepResearch"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Install command has no obvious high-risk pattern"],"warnings":["License is unclear","Repository looks stale","Quality score needs review","Stars/forks activity: 221 stars, 33 forks; issue activity unavailable in current metadata","Recent maintenance: 1y since push","License clarity: Unknown"],"evidence":{"stars":"221 GitHub stars","repoActivity":"221 stars, 33 forks","lastPushed":"1y since push","license":"Unknown","repository":"https://github.com/liyuan24/nanoDeepResearch","install":"npx skills add liyuan24/nanoDeepResearch","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add liyuan24/nanoDeepResearch","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","No Agent Proven outcome evidence yet","1y since push"]},"agentCompatibility":["Python","Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Repository looks stale","Quality score needs review","Stars/forks activity: 221 stars, 33 forks; issue activity unavailable in current metadata","Recent maintenance: 1y since push"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["research","deep-research","agent","python","github","Research Agent"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","Repository looks stale","Quality score needs review","Stars/forks activity: 221 stars, 33 forks; issue activity unavailable in current metadata","Recent maintenance: 1y since push","License clarity: Unknown"]},"safety":{"score":46,"level":"avoid_auto_install","label":"Avoid automatic install","safety_tier":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","summary":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","auto_install_policy":"review","reasons":["License is unclear","46/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["License is unclear"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","reasons":["License is unclear","46/100 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":"research-agents","title":"Research agents"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","Python"],"install":{"ready":true,"command":"npx skills add liyuan24/nanoDeepResearch","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":221,"starsLabel":"221","forks":33,"license":"Unknown","qualityScore":45,"trustScore":69,"auditScore":62},"maintenance":{"status":"stale","label":"1y since push","daysSincePush":411,"lastPushedAt":"2025-05-18T17:56:28+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["License is unclear","Repository appears stale","Repository looks stale","Quality score needs review","Stars/forks activity: 221 stars, 33 forks; issue activity unavailable in current metadata"]},"coverageTags":["Research","RAG and knowledge","deep-research","agent","python","github","Research Agent"]},"audit":{"audit_score":62,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Repository appears stale","Repository looks stale","Quality score needs review","Stars/forks activity: 221 stars, 33 forks; issue activity unavailable in current metadata"]},"decision":{"readiness_score":35,"readiness_label":"Needs manual review","headline":"Needs validation for RAG and knowledge","role":"Needs validation","primary_fit":"RAG and knowledge","best_for":["RAG and knowledge workflows","Claude Code teams","builders willing to evaluate younger projects"],"risks":["Repository looks stale","No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one 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":"liyuan24-nanodeepresearch","name":"NanoDeepResearch","description":"A Deep Research agent from scratch","category":"research","url":"https://www.openagentskill.com/skills/liyuan24-nanodeepresearch","repository":"https://github.com/liyuan24/nanoDeepResearch","github_repo":"liyuan24/nanoDeepResearch"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","builders willing to evaluate younger projects","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Inspect source files","Explain architecture"],"suited_agents":["Python","Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add liyuan24/nanoDeepResearch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add liyuan24/nanoDeepResearch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"NanoDeepResearch\" agent skill from https://github.com/liyuan24/nanoDeepResearch. 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 Deep Research agent from scratch"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"NanoDeepResearch\" as a Claude Code skill from https://github.com/liyuan24/nanoDeepResearch. 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 Deep Research agent from scratch"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"NanoDeepResearch\" from https://github.com/liyuan24/nanoDeepResearch 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 Deep Research agent from scratch"}],"handoff_url":"https://www.openagentskill.com/api/skills/liyuan24-nanodeepresearch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/liyuan24-nanodeepresearch"},"trust":{"score":69,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"221 GitHub stars","repoActivity":"221 stars, 33 forks","lastPushed":"1y since push","license":"Unknown","repository":"https://github.com/liyuan24/nanoDeepResearch","install":"npx skills add liyuan24/nanoDeepResearch","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","deep-research","agent","python","github","Research Agent"],"known_risks":["License is unclear","Repository looks stale","Quality score needs review","Stars/forks activity: 221 stars, 33 forks; issue activity unavailable in current metadata","Recent maintenance: 1y since push","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":62,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Repository appears stale","Repository looks stale","Quality score needs review","Stars/forks activity: 221 stars, 33 forks; issue activity unavailable in current metadata","Recent maintenance: 1y since push","License clarity: Unknown"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":45,"label":"Needs review"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"1y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","License is unclear","Repository appears stale","Quality score needs review","Stars/forks activity: 221 stars, 33 forks; issue activity unavailable in current metadata"],"agent_contract":{"task_input":"Use NanoDeepResearch in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 69/100 Manual review","Audit: 62/100 Needs review","Safety: 46/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"liyuan24-nanodeepresearch (NanoDeepResearch)","install_command":"npx skills add liyuan24/nanoDeepResearch","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":"liyuan24-nanodeepresearch","task":"Use NanoDeepResearch 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/liyuan24-nanodeepresearch","api":"https://www.openagentskill.com/api/agent/skills/liyuan24-nanodeepresearch","audit":"https://www.openagentskill.com/skills/liyuan24-nanodeepresearch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=liyuan24-nanodeepresearch&task=Use%20NanoDeepResearch%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20NanoDeepResearch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20NanoDeepResearch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/liyuan24-nanodeepresearch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/liyuan24-nanodeepresearch"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"liyuan24-nanodeepresearch","name":"NanoDeepResearch","description":"A Deep Research agent from scratch","category":"research","url":"https://www.openagentskill.com/skills/liyuan24-nanodeepresearch","repository":"https://github.com/liyuan24/nanoDeepResearch","github_repo":"liyuan24/nanoDeepResearch"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","builders willing to evaluate younger projects","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Inspect source files","Explain architecture"],"suited_agents":["Python","Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add liyuan24/nanoDeepResearch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add liyuan24/nanoDeepResearch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"NanoDeepResearch\" agent skill from https://github.com/liyuan24/nanoDeepResearch. 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 Deep Research agent from scratch"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"NanoDeepResearch\" as a Claude Code skill from https://github.com/liyuan24/nanoDeepResearch. 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 Deep Research agent from scratch"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"NanoDeepResearch\" from https://github.com/liyuan24/nanoDeepResearch 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 Deep Research agent from scratch"}],"handoff_url":"https://www.openagentskill.com/api/skills/liyuan24-nanodeepresearch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/liyuan24-nanodeepresearch"},"trust":{"score":69,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"221 GitHub stars","repoActivity":"221 stars, 33 forks","lastPushed":"1y since push","license":"Unknown","repository":"https://github.com/liyuan24/nanoDeepResearch","install":"npx skills add liyuan24/nanoDeepResearch","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","deep-research","agent","python","github","Research Agent"],"known_risks":["License is unclear","Repository looks stale","Quality score needs review","Stars/forks activity: 221 stars, 33 forks; issue activity unavailable in current metadata","Recent maintenance: 1y since push","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":62,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Repository appears stale","Repository looks stale","Quality score needs review","Stars/forks activity: 221 stars, 33 forks; issue activity unavailable in current metadata","Recent maintenance: 1y since push","License clarity: Unknown"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":45,"label":"Needs review"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"1y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","License is unclear","Repository appears stale","Quality score needs review","Stars/forks activity: 221 stars, 33 forks; issue activity unavailable in current metadata"],"agent_contract":{"task_input":"Use NanoDeepResearch in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 69/100 Manual review","Audit: 62/100 Needs review","Safety: 46/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"liyuan24-nanodeepresearch (NanoDeepResearch)","install_command":"npx skills add liyuan24/nanoDeepResearch","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":"liyuan24-nanodeepresearch","task":"Use NanoDeepResearch 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/liyuan24-nanodeepresearch","api":"https://www.openagentskill.com/api/agent/skills/liyuan24-nanodeepresearch","audit":"https://www.openagentskill.com/skills/liyuan24-nanodeepresearch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=liyuan24-nanodeepresearch&task=Use%20NanoDeepResearch%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20NanoDeepResearch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20NanoDeepResearch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/liyuan24-nanodeepresearch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/liyuan24-nanodeepresearch"}},"platforms":["Python","Research Agent","Claude Code"],"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":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"install":"npx skills add liyuan24/nanoDeepResearch","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add liyuan24/nanoDeepResearch","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"NanoDeepResearch\" agent skill from https://github.com/liyuan24/nanoDeepResearch. 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 Deep Research agent from scratch","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 \"NanoDeepResearch\" as a Claude Code skill from https://github.com/liyuan24/nanoDeepResearch. 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 Deep Research agent from scratch","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 \"NanoDeepResearch\" from https://github.com/liyuan24/nanoDeepResearch 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 Deep Research agent from scratch","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/liyuan24/nanoDeepResearch","github_repo":"liyuan24/nanoDeepResearch","version":"1.0.0","license":"Unknown","updated_at":"2026-06-21T06:49:26.953001+00:00","canonical_key":"liyuan24/nanodeepresearch","recommendation_reasons":["Matches task terms: deep, research, agent","Install handoff is available","Repository freshness signal is available","Registry match score 44"],"urls":{"web":"https://www.openagentskill.com/skills/liyuan24-nanodeepresearch","api":"https://www.openagentskill.com/api/agent/skills/liyuan24-nanodeepresearch","install_api":"https://www.openagentskill.com/api/skills/liyuan24-nanodeepresearch/install","audit":"https://www.openagentskill.com/skills/liyuan24-nanodeepresearch/audit","repository":"https://github.com/liyuan24/nanoDeepResearch"}},{"rank":7,"match_score":39,"raw_match_score":396.3,"slug":"zamalali-deepgit","name":"DeepGit","description":"Deep research agent to help you find the best GitHub repositories 🕵️!","tagline":"Deep research agent to help you find the best GitHub repositories 🕵️!","category":"research","tags":["deep-research","agent","research","github-search","langchain","langgraph","llm","nlp","open-source","python"],"author":{"name":"zamalali","verified":false,"url":"https://github.com/zamalali"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"zamalali/DeepGit","creatorName":"zamalali","creatorUrl":"https://github.com/zamalali","sourceUrl":"https://github.com/zamalali/DeepGit","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/zamalali-deepgit#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":882,"forks":95,"downloads":0,"rating":0,"review_count":0,"quality_score":54.32},"quality":{"score":82,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"882","tone":"positive"},{"label":"Freshness","value":"24d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":79,"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":76,"weight":0.13,"status":"info","detail":"882 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":71,"weight":0.08,"status":"info","detail":"882 stars, 95 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"24d since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":74,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add zamalali/DeepGit"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/zamalali/DeepGit"},{"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":"882 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"882 stars, 95 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"24d since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add zamalali/DeepGit"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/zamalali/DeepGit"},{"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","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["License is unclear","Quality score needs review","License clarity: Unknown"],"evidence":{"stars":"882 GitHub stars","repoActivity":"882 stars, 95 forks","lastPushed":"24d since push","license":"Unknown","repository":"https://github.com/zamalali/DeepGit","install":"npx skills add zamalali/DeepGit","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add zamalali/DeepGit","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","No Agent Proven outcome evidence yet","24d since push"]},"agentCompatibility":["Python","Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Quality score needs review","License clarity: Unknown"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["research","deep-research","agent","github-search","langchain","langgraph"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","Quality score needs review","License clarity: Unknown"]},"safety":{"score":68,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","68/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["License is unclear"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","68/100 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":"research-agents","title":"Research agents"},{"slug":"coding-agents","title":"Coding agents"}]},"applicableAgents":["Claude Code","LangChain","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add zamalali/DeepGit","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":882,"starsLabel":"882","forks":95,"license":"Unknown","qualityScore":82,"trustScore":79,"auditScore":84},"maintenance":{"status":"fresh","label":"24d since push","daysSincePush":24,"lastPushedAt":"2026-06-09T18:24:08+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["License is unclear","Quality score needs review","License clarity: Unknown"]},"coverageTags":["Research","RAG and knowledge","deep-research","agent","github-search","langchain","langgraph","llm"]},"audit":{"audit_score":84,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","Quality score needs review","License clarity: Unknown"]},"decision":{"readiness_score":93,"readiness_label":"Production-ready","headline":"Primary pick for RAG and knowledge","role":"Primary pick","primary_fit":"RAG and knowledge","best_for":["RAG and knowledge workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one RAG and knowledge task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"zamalali-deepgit","name":"DeepGit","description":"Deep research agent to help you find the best GitHub repositories 🕵️!","category":"research","url":"https://www.openagentskill.com/skills/zamalali-deepgit","repository":"https://github.com/zamalali/DeepGit","github_repo":"zamalali/DeepGit"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Search sources","Extract claims"],"suited_agents":["Python","Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","LangChain","CLI"],"install":{"command":"npx skills add zamalali/DeepGit","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add zamalali/DeepGit"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"DeepGit\" agent skill from https://github.com/zamalali/DeepGit. 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: Deep research agent to help you find the best GitHub repositories 🕵️!"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"DeepGit\" as a Claude Code skill from https://github.com/zamalali/DeepGit. 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: Deep research agent to help you find the best GitHub repositories 🕵️!"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"DeepGit\" from https://github.com/zamalali/DeepGit 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: Deep research agent to help you find the best GitHub repositories 🕵️!"}],"handoff_url":"https://www.openagentskill.com/api/skills/zamalali-deepgit/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/zamalali-deepgit"},"trust":{"score":79,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"882 GitHub stars","repoActivity":"882 stars, 95 forks","lastPushed":"24d since push","license":"Unknown","repository":"https://github.com/zamalali/DeepGit","install":"npx skills add zamalali/DeepGit","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","deep-research","agent","github-search","langchain","langgraph"],"known_risks":["License is unclear","Quality score needs review","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":84,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","Quality score needs review","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":82,"label":"Strong"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"24d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Quality score needs review","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use DeepGit 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: 79/100 Strong shortlist","Audit: 84/100 Safe to try","Safety: 68/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"zamalali-deepgit (DeepGit)","install_command":"npx skills add zamalali/DeepGit","risk_summary":"Safe to try; Reviewed; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"zamalali-deepgit","task":"Use DeepGit 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/zamalali-deepgit","api":"https://www.openagentskill.com/api/agent/skills/zamalali-deepgit","audit":"https://www.openagentskill.com/skills/zamalali-deepgit/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=zamalali-deepgit&task=Use%20DeepGit%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20DeepGit%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20DeepGit%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/zamalali-deepgit/install","manifest":"https://www.openagentskill.com/api/registry/manifest/zamalali-deepgit"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"zamalali-deepgit","name":"DeepGit","description":"Deep research agent to help you find the best GitHub repositories 🕵️!","category":"research","url":"https://www.openagentskill.com/skills/zamalali-deepgit","repository":"https://github.com/zamalali/DeepGit","github_repo":"zamalali/DeepGit"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Search sources","Extract claims"],"suited_agents":["Python","Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","LangChain","CLI"],"install":{"command":"npx skills add zamalali/DeepGit","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add zamalali/DeepGit"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"DeepGit\" agent skill from https://github.com/zamalali/DeepGit. 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: Deep research agent to help you find the best GitHub repositories 🕵️!"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"DeepGit\" as a Claude Code skill from https://github.com/zamalali/DeepGit. 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: Deep research agent to help you find the best GitHub repositories 🕵️!"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"DeepGit\" from https://github.com/zamalali/DeepGit 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: Deep research agent to help you find the best GitHub repositories 🕵️!"}],"handoff_url":"https://www.openagentskill.com/api/skills/zamalali-deepgit/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/zamalali-deepgit"},"trust":{"score":79,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"882 GitHub stars","repoActivity":"882 stars, 95 forks","lastPushed":"24d since push","license":"Unknown","repository":"https://github.com/zamalali/DeepGit","install":"npx skills add zamalali/DeepGit","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","deep-research","agent","github-search","langchain","langgraph"],"known_risks":["License is unclear","Quality score needs review","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":84,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","Quality score needs review","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":82,"label":"Strong"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"24d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Quality score needs review","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use DeepGit 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: 79/100 Strong shortlist","Audit: 84/100 Safe to try","Safety: 68/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"zamalali-deepgit (DeepGit)","install_command":"npx skills add zamalali/DeepGit","risk_summary":"Safe to try; Reviewed; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"zamalali-deepgit","task":"Use DeepGit 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/zamalali-deepgit","api":"https://www.openagentskill.com/api/agent/skills/zamalali-deepgit","audit":"https://www.openagentskill.com/skills/zamalali-deepgit/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=zamalali-deepgit&task=Use%20DeepGit%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20DeepGit%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20DeepGit%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/zamalali-deepgit/install","manifest":"https://www.openagentskill.com/api/registry/manifest/zamalali-deepgit"}},"platforms":["Python","Research Agent","Claude Code","LangChain"],"use_cases":[{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"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":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"install":"npx skills add zamalali/DeepGit","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add zamalali/DeepGit","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"DeepGit\" agent skill from https://github.com/zamalali/DeepGit. 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: Deep research agent to help you find the best GitHub repositories 🕵️!","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 \"DeepGit\" as a Claude Code skill from https://github.com/zamalali/DeepGit. 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: Deep research agent to help you find the best GitHub repositories 🕵️!","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 \"DeepGit\" from https://github.com/zamalali/DeepGit 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: Deep research agent to help you find the best GitHub repositories 🕵️!","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/zamalali/DeepGit","github_repo":"zamalali/DeepGit","version":"1.0.0","license":"Unknown","updated_at":"2026-06-14T13:01:04.119466+00:00","canonical_key":"zamalali/deepgit","recommendation_reasons":["Matches task terms: deep, research, agent","Useful GitHub adoption: 882 stars","Install handoff is available","Repository freshness signal is available","Registry match score 39"],"urls":{"web":"https://www.openagentskill.com/skills/zamalali-deepgit","api":"https://www.openagentskill.com/api/agent/skills/zamalali-deepgit","install_api":"https://www.openagentskill.com/api/skills/zamalali-deepgit/install","audit":"https://www.openagentskill.com/skills/zamalali-deepgit/audit","repository":"https://github.com/zamalali/DeepGit"}},{"rank":8,"match_score":39,"raw_match_score":391.9,"slug":"aq-medai-medresearcher-r1","name":"MedResearcher R1","description":"MedResearcher-R1 is a deep research agent for medical scenarios, built on a knowledge-informed trajectory synthesis framework.","tagline":"MedResearcher-R1 is a deep research agent for medical scenarios, built on a knowledge-informed trajectory synthesis framework.","category":"research","tags":["deep-research","agent","research","deepresearch","llm","medical-ai","python","github"],"author":{"name":"AQ-MedAI","verified":false,"url":"https://github.com/AQ-MedAI"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"AQ-MedAI/MedResearcher-R1","creatorName":"AQ-MedAI","creatorUrl":"https://github.com/AQ-MedAI","sourceUrl":"https://github.com/AQ-MedAI/MedResearcher-R1","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/aq-medai-medresearcher-r1#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":507,"forks":44,"downloads":0,"rating":0,"review_count":0,"quality_score":41.64},"quality":{"score":66,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"507","tone":"positive"},{"label":"Freshness","value":"10mo 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":79,"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":76,"weight":0.13,"status":"info","detail":"507 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":65,"weight":0.08,"status":"info","detail":"507 stars, 44 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":62,"weight":0.14,"status":"info","detail":"10mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":90,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add AQ-MedAI/MedResearcher-R1"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/AQ-MedAI/MedResearcher-R1"},{"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":"507 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"507 stars, 44 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"10mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add AQ-MedAI/MedResearcher-R1"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/AQ-MedAI/MedResearcher-R1"},{"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","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review"],"evidence":{"stars":"507 GitHub stars","repoActivity":"507 stars, 44 forks","lastPushed":"10mo since push","license":"Apache-2.0","repository":"https://github.com/AQ-MedAI/MedResearcher-R1","install":"npx skills add AQ-MedAI/MedResearcher-R1","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add AQ-MedAI/MedResearcher-R1","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","10mo since push"]},"agentCompatibility":["Python","Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review"]},"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","deep-research","agent","deepresearch","llm","medical-ai"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review"]},"safety":{"score":60,"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":["Quality score needs review","60/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["Quality score needs review"],"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":["Quality score needs review","60/100 agent safety score"]},"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"RAG and knowledge","description":"I need my agent to build a RAG workflow over documents and retrieve reliable context.","useCases":[{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"coding-agents","title":"Coding agents"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","Python"],"install":{"ready":true,"command":"npx skills add AQ-MedAI/MedResearcher-R1","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":507,"starsLabel":"507","forks":44,"license":"Apache-2.0","qualityScore":66,"trustScore":79,"auditScore":76},"maintenance":{"status":"stable","label":"10mo since push","daysSincePush":305,"lastPushedAt":"2025-09-01T02:58:52+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Quality score needs review","Needs review"]},"coverageTags":["Research","RAG and knowledge","deep-research","agent","deepresearch","llm","medical-ai","python"]},"audit":{"audit_score":76,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review"]},"decision":{"readiness_score":68,"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","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one RAG and knowledge task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"aq-medai-medresearcher-r1","name":"MedResearcher R1","description":"MedResearcher-R1 is a deep research agent for medical scenarios, built on a knowledge-informed trajectory synthesis framework.","category":"research","url":"https://www.openagentskill.com/skills/aq-medai-medresearcher-r1","repository":"https://github.com/AQ-MedAI/MedResearcher-R1","github_repo":"AQ-MedAI/MedResearcher-R1"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Navigate pages","Click and type safely"],"suited_agents":["Python","Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add AQ-MedAI/MedResearcher-R1","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add AQ-MedAI/MedResearcher-R1"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"MedResearcher R1\" agent skill from https://github.com/AQ-MedAI/MedResearcher-R1. 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: MedResearcher-R1 is a deep research agent for medical scenarios, built on a knowledge-informed trajectory synthesis framework."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"MedResearcher R1\" as a Claude Code skill from https://github.com/AQ-MedAI/MedResearcher-R1. 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: MedResearcher-R1 is a deep research agent for medical scenarios, built on a knowledge-informed trajectory synthesis framework."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"MedResearcher R1\" from https://github.com/AQ-MedAI/MedResearcher-R1 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: MedResearcher-R1 is a deep research agent for medical scenarios, built on a knowledge-informed trajectory synthesis framework."}],"handoff_url":"https://www.openagentskill.com/api/skills/aq-medai-medresearcher-r1/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/aq-medai-medresearcher-r1"},"trust":{"score":79,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"507 GitHub stars","repoActivity":"507 stars, 44 forks","lastPushed":"10mo since push","license":"Apache-2.0","repository":"https://github.com/AQ-MedAI/MedResearcher-R1","install":"npx skills add AQ-MedAI/MedResearcher-R1","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","deep-research","agent","deepresearch","llm","medical-ai"],"known_risks":["Quality score needs review"]},"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":["Quality score needs review"]},"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":66,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"10mo 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","Quality score needs review","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","production agents without a sandbox test and repository review"],"agent_contract":{"task_input":"Use MedResearcher R1 in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 79/100 Strong shortlist","Audit: 76/100 Needs review","Safety: 60/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"aq-medai-medresearcher-r1 (MedResearcher R1)","install_command":"npx skills add AQ-MedAI/MedResearcher-R1","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":"aq-medai-medresearcher-r1","task":"Use MedResearcher R1 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/aq-medai-medresearcher-r1","api":"https://www.openagentskill.com/api/agent/skills/aq-medai-medresearcher-r1","audit":"https://www.openagentskill.com/skills/aq-medai-medresearcher-r1/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=aq-medai-medresearcher-r1&task=Use%20MedResearcher%20R1%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20MedResearcher%20R1%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20MedResearcher%20R1%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/aq-medai-medresearcher-r1/install","manifest":"https://www.openagentskill.com/api/registry/manifest/aq-medai-medresearcher-r1"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"aq-medai-medresearcher-r1","name":"MedResearcher R1","description":"MedResearcher-R1 is a deep research agent for medical scenarios, built on a knowledge-informed trajectory synthesis framework.","category":"research","url":"https://www.openagentskill.com/skills/aq-medai-medresearcher-r1","repository":"https://github.com/AQ-MedAI/MedResearcher-R1","github_repo":"AQ-MedAI/MedResearcher-R1"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Navigate pages","Click and type safely"],"suited_agents":["Python","Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add AQ-MedAI/MedResearcher-R1","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add AQ-MedAI/MedResearcher-R1"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"MedResearcher R1\" agent skill from https://github.com/AQ-MedAI/MedResearcher-R1. 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: MedResearcher-R1 is a deep research agent for medical scenarios, built on a knowledge-informed trajectory synthesis framework."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"MedResearcher R1\" as a Claude Code skill from https://github.com/AQ-MedAI/MedResearcher-R1. 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: MedResearcher-R1 is a deep research agent for medical scenarios, built on a knowledge-informed trajectory synthesis framework."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"MedResearcher R1\" from https://github.com/AQ-MedAI/MedResearcher-R1 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: MedResearcher-R1 is a deep research agent for medical scenarios, built on a knowledge-informed trajectory synthesis framework."}],"handoff_url":"https://www.openagentskill.com/api/skills/aq-medai-medresearcher-r1/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/aq-medai-medresearcher-r1"},"trust":{"score":79,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"507 GitHub stars","repoActivity":"507 stars, 44 forks","lastPushed":"10mo since push","license":"Apache-2.0","repository":"https://github.com/AQ-MedAI/MedResearcher-R1","install":"npx skills add AQ-MedAI/MedResearcher-R1","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","deep-research","agent","deepresearch","llm","medical-ai"],"known_risks":["Quality score needs review"]},"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":["Quality score needs review"]},"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":66,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"10mo 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","Quality score needs review","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","production agents without a sandbox test and repository review"],"agent_contract":{"task_input":"Use MedResearcher R1 in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 79/100 Strong shortlist","Audit: 76/100 Needs review","Safety: 60/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"aq-medai-medresearcher-r1 (MedResearcher R1)","install_command":"npx skills add AQ-MedAI/MedResearcher-R1","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":"aq-medai-medresearcher-r1","task":"Use MedResearcher R1 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/aq-medai-medresearcher-r1","api":"https://www.openagentskill.com/api/agent/skills/aq-medai-medresearcher-r1","audit":"https://www.openagentskill.com/skills/aq-medai-medresearcher-r1/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=aq-medai-medresearcher-r1&task=Use%20MedResearcher%20R1%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20MedResearcher%20R1%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20MedResearcher%20R1%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/aq-medai-medresearcher-r1/install","manifest":"https://www.openagentskill.com/api/registry/manifest/aq-medai-medresearcher-r1"}},"platforms":["Python","Research Agent","Claude Code"],"use_cases":[{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"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"}],"install":"npx skills add AQ-MedAI/MedResearcher-R1","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add AQ-MedAI/MedResearcher-R1","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"MedResearcher R1\" agent skill from https://github.com/AQ-MedAI/MedResearcher-R1. 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: MedResearcher-R1 is a deep research agent for medical scenarios, built on a knowledge-informed trajectory synthesis framework.","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 \"MedResearcher R1\" as a Claude Code skill from https://github.com/AQ-MedAI/MedResearcher-R1. 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: MedResearcher-R1 is a deep research agent for medical scenarios, built on a knowledge-informed trajectory synthesis framework.","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 \"MedResearcher R1\" from https://github.com/AQ-MedAI/MedResearcher-R1 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: MedResearcher-R1 is a deep research agent for medical scenarios, built on a knowledge-informed trajectory synthesis framework.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/AQ-MedAI/MedResearcher-R1","github_repo":"AQ-MedAI/MedResearcher-R1","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-06-14T13:01:04.465456+00:00","canonical_key":"aq-medai/medresearcher-r1","recommendation_reasons":["Matches task terms: deep, research, agent","Useful GitHub adoption: 507 stars","Install handoff is available","Repository freshness signal is available","Registry match score 39"],"urls":{"web":"https://www.openagentskill.com/skills/aq-medai-medresearcher-r1","api":"https://www.openagentskill.com/api/agent/skills/aq-medai-medresearcher-r1","install_api":"https://www.openagentskill.com/api/skills/aq-medai-medresearcher-r1/install","audit":"https://www.openagentskill.com/skills/aq-medai-medresearcher-r1/audit","repository":"https://github.com/AQ-MedAI/MedResearcher-R1"}},{"rank":9,"match_score":38,"raw_match_score":388.3,"slug":"g4brym-workers-research","name":"Workers Research","description":"A serverless, AI-powered deep research agent built with Cloudflare Workers and Google Gemini 2.5","tagline":"A serverless, AI-powered deep research agent built with Cloudflare Workers and Google Gemini 2.5","category":"research","tags":["deep-research","agent","research","ai","ai-agent","cloudflare","cloudflare-workers","durable-objects","google-gemini","openai"],"author":{"name":"G4brym","verified":false,"url":"https://github.com/G4brym"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"G4brym/workers-research","creatorName":"G4brym","creatorUrl":"https://github.com/G4brym","sourceUrl":"https://github.com/G4brym/workers-research","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/g4brym-workers-research#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":104,"forks":18,"downloads":0,"rating":0,"review_count":0,"quality_score":40.85},"quality":{"score":67,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"104","tone":"neutral"},{"label":"Freshness","value":"4mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":79,"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":"104 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"104 stars, 18 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"4mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":90,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add G4brym/workers-research"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/G4brym/workers-research"},{"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":"104 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"104 stars, 18 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"4mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add G4brym/workers-research"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/G4brym/workers-research"},{"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":["Quality score needs review","Stars/forks activity: 104 stars, 18 forks; issue activity unavailable in current metadata"],"evidence":{"stars":"104 GitHub stars","repoActivity":"104 stars, 18 forks","lastPushed":"4mo since push","license":"MIT","repository":"https://github.com/G4brym/workers-research","install":"npx skills add G4brym/workers-research","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add G4brym/workers-research","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","4mo since push"]},"agentCompatibility":["TypeScript","Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Stars/forks activity: 104 stars, 18 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":["research","deep-research","agent","ai","ai-agent","cloudflare"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Stars/forks activity: 104 stars, 18 forks; issue activity unavailable in current metadata"]},"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":["Quality score needs review","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"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["Quality score needs review"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed 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":["Quality score needs review","62/100 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":"browser-automation","title":"Browser automation"}]},"applicableAgents":["Claude Code","OpenAI Agents","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add G4brym/workers-research","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":104,"starsLabel":"104","forks":18,"license":"MIT","qualityScore":67,"trustScore":79,"auditScore":78},"maintenance":{"status":"active","label":"4mo since push","daysSincePush":110,"lastPushedAt":"2026-03-15T21:28:32+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Quality score needs review","Stars/forks activity: 104 stars, 18 forks; issue activity unavailable in current metadata","Needs review"]},"coverageTags":["Research","RAG and knowledge","deep-research","agent","ai","ai-agent","cloudflare","cloudflare-workers"]},"audit":{"audit_score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Stars/forks activity: 104 stars, 18 forks; issue activity unavailable in current metadata"]},"decision":{"readiness_score":66,"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","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 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":"g4brym-workers-research","name":"Workers Research","description":"A serverless, AI-powered deep research agent built with Cloudflare Workers and Google Gemini 2.5","category":"research","url":"https://www.openagentskill.com/skills/g4brym-workers-research","repository":"https://github.com/G4brym/workers-research","github_repo":"G4brym/workers-research"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","builders willing to evaluate younger projects","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Inspect source files","Explain architecture"],"suited_agents":["TypeScript","Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add G4brym/workers-research","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add G4brym/workers-research"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Workers Research\" agent skill from https://github.com/G4brym/workers-research. 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 serverless, AI-powered deep research agent built with Cloudflare Workers and Google Gemini 2.5"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Workers Research\" as a Claude Code skill from https://github.com/G4brym/workers-research. 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 serverless, AI-powered deep research agent built with Cloudflare Workers and Google Gemini 2.5"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Workers Research\" from https://github.com/G4brym/workers-research 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 serverless, AI-powered deep research agent built with Cloudflare Workers and Google Gemini 2.5"}],"handoff_url":"https://www.openagentskill.com/api/skills/g4brym-workers-research/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/g4brym-workers-research"},"trust":{"score":79,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"104 GitHub stars","repoActivity":"104 stars, 18 forks","lastPushed":"4mo since push","license":"MIT","repository":"https://github.com/G4brym/workers-research","install":"npx skills add G4brym/workers-research","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","deep-research","agent","ai","ai-agent","cloudflare"],"known_risks":["Quality score needs review","Stars/forks activity: 104 stars, 18 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":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Stars/forks activity: 104 stars, 18 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":67,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"4mo 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","Quality score needs review","Stars/forks activity: 104 stars, 18 forks; issue activity unavailable in current metadata","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use Workers Research in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 79/100 Strong shortlist","Audit: 78/100 Needs review","Safety: 62/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"g4brym-workers-research (Workers Research)","install_command":"npx skills add G4brym/workers-research","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":"g4brym-workers-research","task":"Use Workers Research 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/g4brym-workers-research","api":"https://www.openagentskill.com/api/agent/skills/g4brym-workers-research","audit":"https://www.openagentskill.com/skills/g4brym-workers-research/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=g4brym-workers-research&task=Use%20Workers%20Research%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Workers%20Research%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Workers%20Research%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/g4brym-workers-research/install","manifest":"https://www.openagentskill.com/api/registry/manifest/g4brym-workers-research"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"g4brym-workers-research","name":"Workers Research","description":"A serverless, AI-powered deep research agent built with Cloudflare Workers and Google Gemini 2.5","category":"research","url":"https://www.openagentskill.com/skills/g4brym-workers-research","repository":"https://github.com/G4brym/workers-research","github_repo":"G4brym/workers-research"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","builders willing to evaluate younger projects","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Inspect source files","Explain architecture"],"suited_agents":["TypeScript","Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add G4brym/workers-research","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add G4brym/workers-research"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Workers Research\" agent skill from https://github.com/G4brym/workers-research. 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 serverless, AI-powered deep research agent built with Cloudflare Workers and Google Gemini 2.5"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Workers Research\" as a Claude Code skill from https://github.com/G4brym/workers-research. 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 serverless, AI-powered deep research agent built with Cloudflare Workers and Google Gemini 2.5"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Workers Research\" from https://github.com/G4brym/workers-research 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 serverless, AI-powered deep research agent built with Cloudflare Workers and Google Gemini 2.5"}],"handoff_url":"https://www.openagentskill.com/api/skills/g4brym-workers-research/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/g4brym-workers-research"},"trust":{"score":79,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"104 GitHub stars","repoActivity":"104 stars, 18 forks","lastPushed":"4mo since push","license":"MIT","repository":"https://github.com/G4brym/workers-research","install":"npx skills add G4brym/workers-research","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["research","deep-research","agent","ai","ai-agent","cloudflare"],"known_risks":["Quality score needs review","Stars/forks activity: 104 stars, 18 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":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Stars/forks activity: 104 stars, 18 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":67,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"4mo 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","Quality score needs review","Stars/forks activity: 104 stars, 18 forks; issue activity unavailable in current metadata","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use Workers Research in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 79/100 Strong shortlist","Audit: 78/100 Needs review","Safety: 62/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"g4brym-workers-research (Workers Research)","install_command":"npx skills add G4brym/workers-research","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":"g4brym-workers-research","task":"Use Workers Research 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/g4brym-workers-research","api":"https://www.openagentskill.com/api/agent/skills/g4brym-workers-research","audit":"https://www.openagentskill.com/skills/g4brym-workers-research/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=g4brym-workers-research&task=Use%20Workers%20Research%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Workers%20Research%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Workers%20Research%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/g4brym-workers-research/install","manifest":"https://www.openagentskill.com/api/registry/manifest/g4brym-workers-research"}},"platforms":["TypeScript","Research Agent","Claude Code","OpenAI Agents"],"use_cases":[{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"}],"install":"npx skills add G4brym/workers-research","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add G4brym/workers-research","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Workers Research\" agent skill from https://github.com/G4brym/workers-research. 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 serverless, AI-powered deep research agent built with Cloudflare Workers and Google Gemini 2.5","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 \"Workers Research\" as a Claude Code skill from https://github.com/G4brym/workers-research. 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 serverless, AI-powered deep research agent built with Cloudflare Workers and Google Gemini 2.5","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 \"Workers Research\" from https://github.com/G4brym/workers-research 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 serverless, AI-powered deep research agent built with Cloudflare Workers and Google Gemini 2.5","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/G4brym/workers-research","github_repo":"G4brym/workers-research","version":"1.0.0","license":"MIT","updated_at":"2026-06-21T06:49:26.625574+00:00","canonical_key":"g4brym/workers-research","recommendation_reasons":["Matches task terms: deep, research, agent","Install handoff is available","Repository freshness signal is available","Registry match score 38"],"urls":{"web":"https://www.openagentskill.com/skills/g4brym-workers-research","api":"https://www.openagentskill.com/api/agent/skills/g4brym-workers-research","install_api":"https://www.openagentskill.com/api/skills/g4brym-workers-research/install","audit":"https://www.openagentskill.com/skills/g4brym-workers-research/audit","repository":"https://github.com/G4brym/workers-research"}},{"rank":10,"match_score":35,"raw_match_score":354.1,"slug":"miromindai-mirothinker","name":"MiroThinker","description":"MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.","tagline":"MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.","category":"research","tags":["research","agent","agent-framework","browsecomp","deep-research","futurex","gaia","hle","research-agent","search-agent"],"author":{"name":"MiroMindAI","verified":true,"url":"https://github.com/MiroMindAI"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"MiroMindAI/MiroThinker","creatorName":"MiroMindAI","creatorUrl":"https://github.com/MiroMindAI","sourceUrl":"https://github.com/MiroMindAI/MiroThinker","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/miromindai-mirothinker#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":8279,"forks":639,"downloads":0,"rating":0,"review_count":0,"quality_score":66.13},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"8.3K","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":91,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"weight":0.13,"status":"pass","detail":"8.3K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"8.3K stars, 639 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":90,"weight":0.14,"status":"pass","detail":"Metadata includes enough usage and workflow context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add MiroMindAI/MiroThinker"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/MiroMindAI/MiroThinker"},{"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":"8.3K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"8.3K stars, 639 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":"pass","label":"README/SKILL.md completeness","detail":"Metadata includes enough usage and workflow context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add MiroMindAI/MiroThinker"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/MiroMindAI/MiroThinker"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":[],"evidence":{"stars":"8.3K GitHub stars","repoActivity":"8.3K stars, 639 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/MiroMindAI/MiroThinker","install":"npx skills add MiroMindAI/MiroThinker","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add MiroMindAI/MiroThinker","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Python","Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["No major trust warnings detected from available metadata"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["research","agent","agent-framework","browsecomp","deep-research","futurex"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":[]},"safety":{"score":85,"level":"safe_to_install","label":"Safe to install with normal review","safety_tier":{"tier":"verified","label":"Verified","badge":"VERIFIED","summary":"Strong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","auto_install_policy":"allow","reasons":["Verified listing","Safe-to-try audit","85/100 agent safety score"]},"auto_install_allowed":true,"human_review_required":false,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":[],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"verified","label":"Verified","badge":"VERIFIED","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","reasons":["Verified listing","Safe-to-try audit","85/100 agent safety score"]},"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"RAG and knowledge","description":"I need my agent to build a RAG workflow over documents and retrieve reliable context.","useCases":[{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"workflow-automation","title":"Workflow automation"},{"slug":"sports-analytics","title":"Sports analytics"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","Python"],"install":{"ready":true,"command":"npx skills add MiroMindAI/MiroThinker","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":8279,"starsLabel":"8.3K","forks":639,"license":"Apache-2.0","qualityScore":100,"trustScore":91,"auditScore":93},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":69,"lastPushedAt":"2026-04-25T05:23:54+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":false,"notes":["No major risk signals from available metadata"]},"coverageTags":["Research","RAG and knowledge","agent","agent-framework","browsecomp","deep-research","futurex","gaia"]},"audit":{"audit_score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for RAG and knowledge","role":"Primary pick","primary_fit":"RAG and knowledge","best_for":["RAG and knowledge workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one RAG and knowledge task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"miromindai-mirothinker","name":"MiroThinker","description":"MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.","category":"research","url":"https://www.openagentskill.com/skills/miromindai-mirothinker","repository":"https://github.com/MiroMindAI/MiroThinker","github_repo":"MiroMindAI/MiroThinker"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Move data between tools","Transform files"],"suited_agents":["Python","Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add MiroMindAI/MiroThinker","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add MiroMindAI/MiroThinker"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"MiroThinker\" agent skill from https://github.com/MiroMindAI/MiroThinker. 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: MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"MiroThinker\" as a Claude Code skill from https://github.com/MiroMindAI/MiroThinker. 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: MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"MiroThinker\" from https://github.com/MiroMindAI/MiroThinker 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: MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively."}],"handoff_url":"https://www.openagentskill.com/api/skills/miromindai-mirothinker/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/miromindai-mirothinker"},"trust":{"score":91,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"8.3K GitHub stars","repoActivity":"8.3K stars, 639 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/MiroMindAI/MiroThinker","install":"npx skills add MiroMindAI/MiroThinker","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["research","agent","agent-framework","browsecomp","deep-research","futurex"],"known_risks":[]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety_gate":{"tier":"verified","label":"Verified","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","No major trust warnings detected from available metadata","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use MiroThinker in an agent workflow","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","install_policy":"allow","minimum_review_before_use":["Trust: 91/100 Production candidate","Audit: 93/100 Safe to try","Safety: 85/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"miromindai-mirothinker (MiroThinker)","install_command":"npx skills add MiroMindAI/MiroThinker","risk_summary":"Safe to try; Verified; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"miromindai-mirothinker","task":"Use MiroThinker 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/miromindai-mirothinker","api":"https://www.openagentskill.com/api/agent/skills/miromindai-mirothinker","audit":"https://www.openagentskill.com/skills/miromindai-mirothinker/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=miromindai-mirothinker&task=Use%20MiroThinker%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20MiroThinker%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20MiroThinker%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/miromindai-mirothinker/install","manifest":"https://www.openagentskill.com/api/registry/manifest/miromindai-mirothinker"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"miromindai-mirothinker","name":"MiroThinker","description":"MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.","category":"research","url":"https://www.openagentskill.com/skills/miromindai-mirothinker","repository":"https://github.com/MiroMindAI/MiroThinker","github_repo":"MiroMindAI/MiroThinker"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Move data between tools","Transform files"],"suited_agents":["Python","Research Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add MiroMindAI/MiroThinker","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add MiroMindAI/MiroThinker"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"MiroThinker\" agent skill from https://github.com/MiroMindAI/MiroThinker. 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: MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"MiroThinker\" as a Claude Code skill from https://github.com/MiroMindAI/MiroThinker. 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: MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"MiroThinker\" from https://github.com/MiroMindAI/MiroThinker 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: MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively."}],"handoff_url":"https://www.openagentskill.com/api/skills/miromindai-mirothinker/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/miromindai-mirothinker"},"trust":{"score":91,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"8.3K GitHub stars","repoActivity":"8.3K stars, 639 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/MiroMindAI/MiroThinker","install":"npx skills add MiroMindAI/MiroThinker","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Strong README/SKILL.md context","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["research","agent","agent-framework","browsecomp","deep-research","futurex"],"known_risks":[]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"safety_gate":{"tier":"verified","label":"Verified","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","No major trust warnings detected from available metadata","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use MiroThinker in an agent workflow","recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","install_policy":"allow","minimum_review_before_use":["Trust: 91/100 Production candidate","Audit: 93/100 Safe to try","Safety: 85/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"miromindai-mirothinker (MiroThinker)","install_command":"npx skills add MiroMindAI/MiroThinker","risk_summary":"Safe to try; Verified; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"miromindai-mirothinker","task":"Use MiroThinker 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/miromindai-mirothinker","api":"https://www.openagentskill.com/api/agent/skills/miromindai-mirothinker","audit":"https://www.openagentskill.com/skills/miromindai-mirothinker/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=miromindai-mirothinker&task=Use%20MiroThinker%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20MiroThinker%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20MiroThinker%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/miromindai-mirothinker/install","manifest":"https://www.openagentskill.com/api/registry/manifest/miromindai-mirothinker"}},"platforms":["Python","Research Agent","Claude Code"],"use_cases":[{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"slug":"sports-analytics","title":"Sports analytics","url":"https://www.openagentskill.com/use-cases/sports-analytics"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"}],"install":"npx skills add MiroMindAI/MiroThinker","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add MiroMindAI/MiroThinker","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"MiroThinker\" agent skill from https://github.com/MiroMindAI/MiroThinker. 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: MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.","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 \"MiroThinker\" as a Claude Code skill from https://github.com/MiroMindAI/MiroThinker. 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: MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.","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 \"MiroThinker\" from https://github.com/MiroMindAI/MiroThinker 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: MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/MiroMindAI/MiroThinker","github_repo":"MiroMindAI/MiroThinker","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-06-14T13:00:58.42179+00:00","canonical_key":"miromindai/mirothinker","recommendation_reasons":["Matches task terms: deep, research, agent","Useful GitHub adoption: 8,279 stars","Install handoff is available","Repository freshness signal is available","Registry match score 35"],"urls":{"web":"https://www.openagentskill.com/skills/miromindai-mirothinker","api":"https://www.openagentskill.com/api/agent/skills/miromindai-mirothinker","install_api":"https://www.openagentskill.com/api/skills/miromindai-mirothinker/install","audit":"https://www.openagentskill.com/skills/miromindai-mirothinker/audit","repository":"https://github.com/MiroMindAI/MiroThinker"}}],"meta":{"endpoint":"/api/skills/search","canonical_agent_endpoint":"/api/agent/resolve","safety_policy":"Blocked candidates are excluded by default. Pass include_blocked=true only for manual audit workflows.","agent_friendly":true,"api_version":"1.0","generated_at":"2026-07-03T22:01:32.759Z"}}