{"eval":{"version":"openagentskill-skill-eval-v1","slug":"ruc-nlpir-search-o1","name":"Search O1","generated_at":"2026-07-04T04:16:18.094Z","task_input":"Evaluate Search O1 before installing it in an AI agent workflow","status":"review","score":80,"risk_level":"medium","decision":{"recommendation":"manual_review","reason":"Require human approval before installing into a real workspace.","auto_install_allowed":false,"policy":"review","human_review_required":true},"task_fit":{"score":84,"suited_tasks":["RAG and knowledge workflows","Claude Code teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Inspect source files","Explain architecture"],"suited_agents":["Python","RAG","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"]},"install":{"command":"npx skills add RUC-NLPIR/Search-o1","ready":true,"policy":"review","safety_label":"Review before install","targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add RUC-NLPIR/Search-o1"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Search O1\" agent skill from https://github.com/RUC-NLPIR/Search-o1. 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: 🔍 Search-o1: Agentic Search-Enhanced Large Reasoning Models [EMNLP 2025]"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Search O1\" as a Claude Code skill from https://github.com/RUC-NLPIR/Search-o1. 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: 🔍 Search-o1: Agentic Search-Enhanced Large Reasoning Models [EMNLP 2025]"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Search O1\" from https://github.com/RUC-NLPIR/Search-o1 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: 🔍 Search-o1: Agentic Search-Enhanced Large Reasoning Models [EMNLP 2025]"}]},"trust":{"score":84,"label":"Strong shortlist","version":"trust-score-v4","evidence":{"stars":"1.2K GitHub stars","repoActivity":"1.2K stars, 107 forks","lastPushed":"8mo since push","license":"MIT","repository":"https://github.com/RUC-NLPIR/Search-o1","install":"npx skills add RUC-NLPIR/Search-o1","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"}},"audit":{"score":83,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review"]},"safety_gate":{"score":67,"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","blocked":false,"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"]},"checks":[{"id":"task_fit","label":"Task fit","status":"pass","score":84,"required_for_auto_install":true,"detail":"Task wording matches this skill metadata.","evidence":["Evaluate Search O1 before installing it in an AI agent workflow","rag-knowledge","RAG and knowledge workflows; Claude Code teams; teams that value GitHub adoption signals"]},{"id":"install_path","label":"Install path","status":"pass","score":92,"required_for_auto_install":true,"detail":"Install handoff is available.","evidence":["npx skills add RUC-NLPIR/Search-o1"]},{"id":"install_safety","label":"Install command safety","status":"pass","score":92,"required_for_auto_install":true,"detail":"standard package or runtime install path","evidence":["npx skills add RUC-NLPIR/Search-o1"]},{"id":"trust_score","label":"Trust score","status":"pass","score":84,"required_for_auto_install":true,"detail":"Good trust signals with a few areas worth checking before rollout.","evidence":["Strong shortlist","1.2K GitHub stars","MIT"]},{"id":"audit_score","label":"Audit score","status":"pass","score":83,"required_for_auto_install":true,"detail":"Safe to try","evidence":["Quality score needs review"]},{"id":"agent_safety_gate","label":"Agent safety gate","status":"warn","score":67,"required_for_auto_install":true,"detail":"Usable candidate, but the agent should surface permission and audit notes before installation.","evidence":["Require human approval before installing into a real workspace.","Quality score needs review"]},{"id":"readme_skillmd_completeness","label":"README/SKILL.md completeness","status":"warn","score":74,"required_for_auto_install":false,"detail":"Public metadata needs stronger README/SKILL.md context","evidence":["Usable metadata, review docs"]},{"id":"license_clarity","label":"License clarity","status":"pass","score":86,"required_for_auto_install":true,"detail":"MIT","evidence":["MIT"]},{"id":"recent_maintenance","label":"Recent maintenance","status":"warn","score":62,"required_for_auto_install":false,"detail":"8mo since push","evidence":["8mo since push"]},{"id":"permission_surface","label":"Permission surface","status":"pass","score":86,"required_for_auto_install":true,"detail":"filesystem or document access","evidence":["Network access: medium","Filesystem access: medium"]},{"id":"alternatives","label":"Alternatives available","status":"pass","score":82,"required_for_auto_install":false,"detail":"Alternative skills are available for comparison.","evidence":["microsoft-generative-ai-for-beginners","safishamsi-graphify","elastic-elasticsearch","egonex-ai-understand-anything"]}],"blockers":[],"warnings":["Agent safety gate: Usable candidate, but the agent should surface permission and audit notes before installation.","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Recent maintenance: 8mo since push","Quality score needs review"],"validation_plan":["Inspect repository, README/SKILL.md, license, and recent commits before production use.","Install in an isolated workspace or sandbox with no production secrets available.","Run the smallest representative task and record files touched, commands run, network access, and outputs.","Compare the selected skill against at least one alternative when the eval status is review or failed.","Promote only after the agent reports a successful verification result and unresolved warnings are accepted."],"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"],"alternatives":[{"slug":"microsoft-generative-ai-for-beginners","name":"Generative AI For Beginners","url":"https://www.openagentskill.com/skills/microsoft-generative-ai-for-beginners","stars":112223,"install_command":"npx skills add microsoft/generative-ai-for-beginners","trust_score":92,"audit_score":95},{"slug":"safishamsi-graphify","name":"Graphify","url":"https://www.openagentskill.com/skills/safishamsi-graphify","stars":77174,"install_command":"npx skills add safishamsi/graphify","trust_score":89,"audit_score":93},{"slug":"elastic-elasticsearch","name":"Elasticsearch","url":"https://www.openagentskill.com/skills/elastic-elasticsearch","stars":76995,"install_command":"npx skills add elastic/elasticsearch","trust_score":88,"audit_score":92},{"slug":"egonex-ai-understand-anything","name":"Understand Anything","url":"https://www.openagentskill.com/skills/egonex-ai-understand-anything","stars":70671,"install_command":"npx skills add Egonex-AI/Understand-Anything","trust_score":90,"audit_score":93}],"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"ruc-nlpir-search-o1","name":"Search O1","description":"🔍 Search-o1: Agentic Search-Enhanced Large Reasoning Models [EMNLP 2025]","category":"rag-knowledge","url":"https://www.openagentskill.com/skills/ruc-nlpir-search-o1","repository":"https://github.com/RUC-NLPIR/Search-o1","github_repo":"RUC-NLPIR/Search-o1"},"suited_tasks":["RAG and knowledge workflows","Claude Code teams","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Inspect source files","Explain architecture"],"suited_agents":["Python","RAG","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add RUC-NLPIR/Search-o1","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add RUC-NLPIR/Search-o1"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Search O1\" agent skill from https://github.com/RUC-NLPIR/Search-o1. 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: 🔍 Search-o1: Agentic Search-Enhanced Large Reasoning Models [EMNLP 2025]"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Search O1\" as a Claude Code skill from https://github.com/RUC-NLPIR/Search-o1. 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: 🔍 Search-o1: Agentic Search-Enhanced Large Reasoning Models [EMNLP 2025]"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Search O1\" from https://github.com/RUC-NLPIR/Search-o1 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: 🔍 Search-o1: Agentic Search-Enhanced Large Reasoning Models [EMNLP 2025]"}],"handoff_url":"https://www.openagentskill.com/api/skills/ruc-nlpir-search-o1/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/ruc-nlpir-search-o1"},"trust":{"score":84,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"1.2K GitHub stars","repoActivity":"1.2K stars, 107 forks","lastPushed":"8mo since push","license":"MIT","repository":"https://github.com/RUC-NLPIR/Search-o1","install":"npx skills add RUC-NLPIR/Search-o1","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":["rag-knowledge","rag","retrieval","knowledge","aimo","amc"],"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":83,"risk_level":"safe_to_try","risk_label":"Safe to try","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":84,"label":"Strong"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"8mo since push","risk":"Safe to try"},"alternative_skills":[{"slug":"microsoft-generative-ai-for-beginners","name":"Generative AI For Beginners","url":"https://www.openagentskill.com/skills/microsoft-generative-ai-for-beginners","stars":112223,"install_command":"npx skills add microsoft/generative-ai-for-beginners","trust_score":92,"audit_score":95},{"slug":"safishamsi-graphify","name":"Graphify","url":"https://www.openagentskill.com/skills/safishamsi-graphify","stars":77174,"install_command":"npx skills add safishamsi/graphify","trust_score":89,"audit_score":93},{"slug":"elastic-elasticsearch","name":"Elasticsearch","url":"https://www.openagentskill.com/skills/elastic-elasticsearch","stars":76995,"install_command":"npx skills add elastic/elasticsearch","trust_score":88,"audit_score":92},{"slug":"egonex-ai-understand-anything","name":"Understand Anything","url":"https://www.openagentskill.com/skills/egonex-ai-understand-anything","stars":70671,"install_command":"npx skills add Egonex-AI/Understand-Anything","trust_score":90,"audit_score":93}],"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":"Evaluate Search O1 before installing it in an AI agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 84/100 Strong shortlist","Audit: 83/100 Safe to try","Safety: 67/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"ruc-nlpir-search-o1 (Search O1)","install_command":"npx skills add RUC-NLPIR/Search-o1","risk_summary":"Safe to try; Reviewed with permission notes; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"ruc-nlpir-search-o1","task":"Evaluate Search O1 before installing it in an AI 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/ruc-nlpir-search-o1","api":"https://www.openagentskill.com/api/agent/skills/ruc-nlpir-search-o1","audit":"https://www.openagentskill.com/skills/ruc-nlpir-search-o1/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=ruc-nlpir-search-o1&task=Evaluate%20Search%20O1%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Evaluate%20Search%20O1%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Evaluate%20Search%20O1%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/ruc-nlpir-search-o1/install","manifest":"https://www.openagentskill.com/api/registry/manifest/ruc-nlpir-search-o1"}},"endpoints":{"web":"https://www.openagentskill.com/skills/ruc-nlpir-search-o1","api":"https://www.openagentskill.com/api/agent/skills/ruc-nlpir-search-o1","eval":"https://www.openagentskill.com/api/agent/evals?slug=ruc-nlpir-search-o1","audit":"https://www.openagentskill.com/skills/ruc-nlpir-search-o1/audit","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Evaluate%20Search%20O1%20before%20installing%20it%20in%20an%20AI%20agent%20workflow&agent=codex&max_risk=medium"}},"meta":{"endpoint":"/api/agent/evals","mode":"skill_eval","purpose":"Pre-install eval contract for a single skill. Agents should read this before installing a reusable skill.","generated_at":"2026-07-04T04:16:18.094Z"}}