{"query":"GLM Skills","filters":{"category":null,"platform":null,"track":null,"safety":null,"include_blocked":false,"min_stars":0},"total":10,"skills":[{"rank":1,"match_type":"exact","match_score":99,"raw_match_score":680.4,"semantic_relevance":100,"slug":"zai-org-glm-skills","name":"GLM Skills","description":"Official skills for the GLM family of models.","tagline":"Official skills for the GLM family of models.","category":"document-processing","tags":["ocr","documents","extraction","glm","multimodal","skills","vision","python","github"],"author":{"name":"zai-org","verified":false,"url":"https://github.com/zai-org"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"zai-org/GLM-skills","creatorName":"zai-org","creatorUrl":"https://github.com/zai-org","sourceUrl":"https://github.com/zai-org/GLM-skills","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/zai-org-glm-skills#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":426,"forks":34,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":45.11},"quality":{"score":68,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"426","tone":"neutral"},{"label":"Freshness","value":"4mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":75,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"426 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"426 stars, 34 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":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":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 zai-org/GLM-skills"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/zai-org/GLM-skills"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"info","label":"GitHub adoption","detail":"426 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"426 stars, 34 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"4mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add zai-org/GLM-skills"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/zai-org/GLM-skills"},{"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","Documentation summary is thin","Stars/forks activity: 426 stars, 34 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"426 GitHub stars","repoActivity":"426 stars, 34 forks","lastPushed":"4mo since push","license":"Apache-2.0","repository":"https://github.com/zai-org/GLM-skills","install":"npx skills add zai-org/GLM-skills","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add zai-org/GLM-skills","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":["Python","OCR","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 426 stars, 34 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["document-processing","ocr","documents","extraction","glm","multimodal"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 426 stars, 34 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":61,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Documentation summary is thin","61/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Documentation summary is thin","61/100 agent safety score"]},"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"Document processing","description":"I need my agent to read PDFs, extract tables, and turn documents into structured data.","useCases":[{"slug":"document-processing","title":"Document processing"},{"slug":"github-automation","title":"GitHub automation"},{"slug":"multimodal-media","title":"Multimodal media"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","Python"],"install":{"ready":true,"command":"npx skills add zai-org/GLM-skills","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":426,"starsLabel":"426","forks":34,"license":"Apache-2.0","qualityScore":68,"trustScore":75,"auditScore":77},"maintenance":{"status":"active","label":"4mo since push","daysSincePush":129,"lastPushedAt":"2026-04-15T12:28:08+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 426 stars, 34 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Needs review"]},"coverageTags":["Research","Document processing","document-processing","ocr","documents","extraction","glm","multimodal"]},"audit":{"audit_score":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 426 stars, 34 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"decision":{"readiness_score":67,"readiness_label":"Prototype first","headline":"Fallback candidate for Document processing","role":"Fallback candidate","primary_fit":"Document processing","best_for":["Document processing 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 Document processing 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":"zai-org-glm-skills","name":"GLM Skills","description":"Official skills for the GLM family of models.","category":"document-processing","url":"https://www.openagentskill.com/skills/zai-org-glm-skills","repository":"https://github.com/zai-org/GLM-skills","github_repo":"zai-org/GLM-skills"},"suited_tasks":["Document processing workflows","Claude Code teams","builders willing to evaluate younger projects","Read uploaded files","Extract structured fields","Prepare clean context for downstream agents","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","OCR","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add zai-org/GLM-skills","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install zai-org-glm-skills"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"GLM Skills\" agent skill from https://github.com/zai-org/GLM-skills. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Official skills for the GLM family of models. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zai-org-glm-skills\",\"task\":\"Install GLM Skills\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"GLM Skills\" as a Claude Code skill from https://github.com/zai-org/GLM-skills. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Official skills for the GLM family of models. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zai-org-glm-skills\",\"task\":\"Install GLM Skills\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"GLM Skills\" from https://github.com/zai-org/GLM-skills into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Official skills for the GLM family of models. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zai-org-glm-skills\",\"task\":\"Install GLM Skills\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/zai-org-glm-skills/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/zai-org-glm-skills"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"426 GitHub stars","repoActivity":"426 stars, 34 forks","lastPushed":"4mo since push","license":"Apache-2.0","repository":"https://github.com/zai-org/GLM-skills","install":"npx skills add zai-org/GLM-skills","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["document-processing","ocr","documents","extraction","glm","multimodal"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 426 stars, 34 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 426 stars, 34 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":68,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"Document processing","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","Documentation summary is thin","Quality score needs review","Stars/forks activity: 426 stars, 34 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use GLM Skills in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 77/100 Needs review","Safety: 61/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"zai-org-glm-skills (GLM Skills)","install_command":"npx skills add zai-org/GLM-skills","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":"zai-org-glm-skills","task":"Use GLM Skills in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/zai-org-glm-skills","api":"https://www.openagentskill.com/api/agent/skills/zai-org-glm-skills","audit":"https://www.openagentskill.com/skills/zai-org-glm-skills/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=zai-org-glm-skills&task=Use%20GLM%20Skills%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20GLM%20Skills%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20GLM%20Skills%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/zai-org-glm-skills/install","manifest":"https://www.openagentskill.com/api/registry/manifest/zai-org-glm-skills"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"zai-org-glm-skills","name":"GLM Skills","description":"Official skills for the GLM family of models.","category":"document-processing","url":"https://www.openagentskill.com/skills/zai-org-glm-skills","repository":"https://github.com/zai-org/GLM-skills","github_repo":"zai-org/GLM-skills"},"suited_tasks":["Document processing workflows","Claude Code teams","builders willing to evaluate younger projects","Read uploaded files","Extract structured fields","Prepare clean context for downstream agents","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","OCR","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add zai-org/GLM-skills","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install zai-org-glm-skills"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"GLM Skills\" agent skill from https://github.com/zai-org/GLM-skills. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Official skills for the GLM family of models. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zai-org-glm-skills\",\"task\":\"Install GLM Skills\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"GLM Skills\" as a Claude Code skill from https://github.com/zai-org/GLM-skills. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Official skills for the GLM family of models. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zai-org-glm-skills\",\"task\":\"Install GLM Skills\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"GLM Skills\" from https://github.com/zai-org/GLM-skills into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Official skills for the GLM family of models. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zai-org-glm-skills\",\"task\":\"Install GLM Skills\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/zai-org-glm-skills/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/zai-org-glm-skills"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"426 GitHub stars","repoActivity":"426 stars, 34 forks","lastPushed":"4mo since push","license":"Apache-2.0","repository":"https://github.com/zai-org/GLM-skills","install":"npx skills add zai-org/GLM-skills","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["document-processing","ocr","documents","extraction","glm","multimodal"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 426 stars, 34 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 426 stars, 34 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":68,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"Document processing","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","Documentation summary is thin","Quality score needs review","Stars/forks activity: 426 stars, 34 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use GLM Skills in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 77/100 Needs review","Safety: 61/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"zai-org-glm-skills (GLM Skills)","install_command":"npx skills add zai-org/GLM-skills","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":"zai-org-glm-skills","task":"Use GLM Skills in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/zai-org-glm-skills","api":"https://www.openagentskill.com/api/agent/skills/zai-org-glm-skills","audit":"https://www.openagentskill.com/skills/zai-org-glm-skills/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=zai-org-glm-skills&task=Use%20GLM%20Skills%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20GLM%20Skills%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20GLM%20Skills%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/zai-org-glm-skills/install","manifest":"https://www.openagentskill.com/api/registry/manifest/zai-org-glm-skills"}},"platforms":["Python","OCR","Claude Code"],"use_cases":[{"slug":"document-processing","title":"Document processing","url":"https://www.openagentskill.com/use-cases/document-processing"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"},{"slug":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"}],"install":"npx skills add zai-org/GLM-skills","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install zai-org-glm-skills","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"GLM Skills\" agent skill from https://github.com/zai-org/GLM-skills. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Official skills for the GLM family of models. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zai-org-glm-skills\",\"task\":\"Install GLM Skills\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"GLM Skills\" as a Claude Code skill from https://github.com/zai-org/GLM-skills. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Official skills for the GLM family of models. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zai-org-glm-skills\",\"task\":\"Install GLM Skills\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"GLM Skills\" from https://github.com/zai-org/GLM-skills into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Official skills for the GLM family of models. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zai-org-glm-skills\",\"task\":\"Install GLM Skills\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/zai-org/GLM-skills","github_repo":"zai-org/GLM-skills","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"zai-org/glm-skills","recommendation_reasons":["Matches task terms: glm","Install handoff is available","Repository freshness signal is available","Registry match score 99"],"urls":{"web":"https://www.openagentskill.com/skills/zai-org-glm-skills","api":"https://www.openagentskill.com/api/agent/skills/zai-org-glm-skills","install_api":"https://www.openagentskill.com/api/skills/zai-org-glm-skills/install","audit":"https://www.openagentskill.com/skills/zai-org-glm-skills/audit","repository":"https://github.com/zai-org/GLM-skills"}},{"rank":2,"match_type":"near","match_score":19,"raw_match_score":128.7,"semantic_relevance":30,"slug":"zai-org-glm-ocr","name":"GLM OCR","description":"GLM-OCR: Accurate ×  Fast × Comprehensive","tagline":"GLM-OCR: Accurate ×  Fast × Comprehensive","category":"document-processing","tags":["ocr","documents","extraction","glm","image2text","python","github"],"author":{"name":"zai-org","verified":true,"url":"https://github.com/zai-org"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"zai-org/GLM-OCR","creatorName":"zai-org","creatorUrl":"https://github.com/zai-org","sourceUrl":"https://github.com/zai-org/GLM-OCR","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/zai-org-glm-ocr#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":7050,"forks":640,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":61.64},"quality":{"score":94,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"7.0K","tone":"positive"},{"label":"Freshness","value":"4mo 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":85,"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":94,"weight":0.13,"status":"pass","detail":"7.0K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"7.0K stars, 640 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":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":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 zai-org/GLM-OCR"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/zai-org/GLM-OCR"},{"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":"7.0K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"7.0K stars, 640 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"4mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add zai-org/GLM-OCR"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/zai-org/GLM-OCR"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"7.0K GitHub stars","repoActivity":"7.0K stars, 640 forks","lastPushed":"4mo since push","license":"Apache-2.0","repository":"https://github.com/zai-org/GLM-OCR","install":"npx skills add zai-org/GLM-OCR","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add zai-org/GLM-OCR","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":["Python","OCR","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["document-processing","ocr","documents","extraction","glm","image2text"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":71,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","71/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","71/100 agent safety score"]},"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"Document processing","description":"I need my agent to read PDFs, extract tables, and turn documents into structured data.","useCases":[{"slug":"document-processing","title":"Document processing"},{"slug":"github-automation","title":"GitHub automation"},{"slug":"multimodal-media","title":"Multimodal media"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add zai-org/GLM-OCR","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":7050,"starsLabel":"7.0K","forks":640,"license":"Apache-2.0","qualityScore":94,"trustScore":85,"auditScore":87},"maintenance":{"status":"active","label":"4mo since push","daysSincePush":123,"lastPushedAt":"2026-04-21T08:52:11+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"coverageTags":["Research","Document processing","document-processing","ocr","documents","extraction","glm","image2text"]},"audit":{"audit_score":87,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Document processing","role":"Primary pick","primary_fit":"Document processing","best_for":["Document processing workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Document processing 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":"zai-org-glm-ocr","name":"GLM OCR","description":"GLM-OCR: Accurate ×  Fast × Comprehensive","category":"document-processing","url":"https://www.openagentskill.com/skills/zai-org-glm-ocr","repository":"https://github.com/zai-org/GLM-OCR","github_repo":"zai-org/GLM-OCR"},"suited_tasks":["Document processing workflows","general agent builders","teams that value GitHub adoption signals","Read uploaded files","Extract structured fields","Prepare clean context for downstream agents","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","OCR","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add zai-org/GLM-OCR","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install zai-org-glm-ocr"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"GLM OCR\" agent skill from https://github.com/zai-org/GLM-OCR. 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: GLM-OCR: Accurate × Fast × Comprehensive After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zai-org-glm-ocr\",\"task\":\"Install GLM OCR\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"GLM OCR\" as a Claude Code skill from https://github.com/zai-org/GLM-OCR. 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: GLM-OCR: Accurate × Fast × Comprehensive After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zai-org-glm-ocr\",\"task\":\"Install GLM OCR\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"GLM OCR\" from https://github.com/zai-org/GLM-OCR 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: GLM-OCR: Accurate × Fast × Comprehensive After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zai-org-glm-ocr\",\"task\":\"Install GLM OCR\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/zai-org-glm-ocr/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/zai-org-glm-ocr"},"trust":{"score":85,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"7.0K GitHub stars","repoActivity":"7.0K stars, 640 forks","lastPushed":"4mo since push","license":"Apache-2.0","repository":"https://github.com/zai-org/GLM-OCR","install":"npx skills add zai-org/GLM-OCR","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["document-processing","ocr","documents","extraction","glm","image2text"],"known_risks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":87,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":94,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"Document processing","maintenance":"4mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use GLM OCR 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: 85/100 Strong shortlist","Audit: 87/100 Safe to try","Safety: 71/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"zai-org-glm-ocr (GLM OCR)","install_command":"npx skills add zai-org/GLM-OCR","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":"zai-org-glm-ocr","task":"Use GLM OCR 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/zai-org-glm-ocr","api":"https://www.openagentskill.com/api/agent/skills/zai-org-glm-ocr","audit":"https://www.openagentskill.com/skills/zai-org-glm-ocr/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=zai-org-glm-ocr&task=Use%20GLM%20OCR%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20GLM%20OCR%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20GLM%20OCR%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/zai-org-glm-ocr/install","manifest":"https://www.openagentskill.com/api/registry/manifest/zai-org-glm-ocr"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"zai-org-glm-ocr","name":"GLM OCR","description":"GLM-OCR: Accurate ×  Fast × Comprehensive","category":"document-processing","url":"https://www.openagentskill.com/skills/zai-org-glm-ocr","repository":"https://github.com/zai-org/GLM-OCR","github_repo":"zai-org/GLM-OCR"},"suited_tasks":["Document processing workflows","general agent builders","teams that value GitHub adoption signals","Read uploaded files","Extract structured fields","Prepare clean context for downstream agents","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","OCR","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add zai-org/GLM-OCR","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install zai-org-glm-ocr"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"GLM OCR\" agent skill from https://github.com/zai-org/GLM-OCR. 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: GLM-OCR: Accurate × Fast × Comprehensive After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zai-org-glm-ocr\",\"task\":\"Install GLM OCR\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"GLM OCR\" as a Claude Code skill from https://github.com/zai-org/GLM-OCR. 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: GLM-OCR: Accurate × Fast × Comprehensive After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zai-org-glm-ocr\",\"task\":\"Install GLM OCR\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"GLM OCR\" from https://github.com/zai-org/GLM-OCR 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: GLM-OCR: Accurate × Fast × Comprehensive After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zai-org-glm-ocr\",\"task\":\"Install GLM OCR\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/zai-org-glm-ocr/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/zai-org-glm-ocr"},"trust":{"score":85,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"7.0K GitHub stars","repoActivity":"7.0K stars, 640 forks","lastPushed":"4mo since push","license":"Apache-2.0","repository":"https://github.com/zai-org/GLM-OCR","install":"npx skills add zai-org/GLM-OCR","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["document-processing","ocr","documents","extraction","glm","image2text"],"known_risks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":87,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":94,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"Document processing","maintenance":"4mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use GLM OCR 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: 85/100 Strong shortlist","Audit: 87/100 Safe to try","Safety: 71/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"zai-org-glm-ocr (GLM OCR)","install_command":"npx skills add zai-org/GLM-OCR","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":"zai-org-glm-ocr","task":"Use GLM OCR 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/zai-org-glm-ocr","api":"https://www.openagentskill.com/api/agent/skills/zai-org-glm-ocr","audit":"https://www.openagentskill.com/skills/zai-org-glm-ocr/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=zai-org-glm-ocr&task=Use%20GLM%20OCR%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20GLM%20OCR%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20GLM%20OCR%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/zai-org-glm-ocr/install","manifest":"https://www.openagentskill.com/api/registry/manifest/zai-org-glm-ocr"}},"platforms":["Python","OCR"],"use_cases":[{"slug":"document-processing","title":"Document processing","url":"https://www.openagentskill.com/use-cases/document-processing"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"},{"slug":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"}],"install":"npx skills add zai-org/GLM-OCR","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install zai-org-glm-ocr","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"GLM OCR\" agent skill from https://github.com/zai-org/GLM-OCR. 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: GLM-OCR: Accurate × Fast × Comprehensive After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zai-org-glm-ocr\",\"task\":\"Install GLM OCR\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"GLM OCR\" as a Claude Code skill from https://github.com/zai-org/GLM-OCR. 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: GLM-OCR: Accurate × Fast × Comprehensive After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zai-org-glm-ocr\",\"task\":\"Install GLM OCR\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"GLM OCR\" from https://github.com/zai-org/GLM-OCR 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: GLM-OCR: Accurate × Fast × Comprehensive After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"zai-org-glm-ocr\",\"task\":\"Install GLM OCR\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/zai-org/GLM-OCR","github_repo":"zai-org/GLM-OCR","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"zai-org/glm-ocr","recommendation_reasons":["Matches task terms: glm","Useful GitHub adoption: 7,050 stars","Install handoff is available","Repository freshness signal is available","Registry match score 19"],"urls":{"web":"https://www.openagentskill.com/skills/zai-org-glm-ocr","api":"https://www.openagentskill.com/api/agent/skills/zai-org-glm-ocr","install_api":"https://www.openagentskill.com/api/skills/zai-org-glm-ocr/install","audit":"https://www.openagentskill.com/skills/zai-org-glm-ocr/audit","repository":"https://github.com/zai-org/GLM-OCR"}},{"rank":3,"match_type":"near","match_score":16,"raw_match_score":109.3,"semantic_relevance":30,"slug":"glm-tools-pyglmnet","name":"Pyglmnet","description":"Python implementation of elastic-net regularized generalized linear models","tagline":"Python implementation of elastic-net regularized generalized linear models","category":"ml-automation","tags":["machine-learning","automation","ml-media","data-science","elastic-net","glm","lasso","python","github"],"author":{"name":"glm-tools","verified":false,"url":"https://github.com/glm-tools"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"glm-tools/pyglmnet","creatorName":"glm-tools","creatorUrl":"https://github.com/glm-tools","sourceUrl":"https://github.com/glm-tools/pyglmnet","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/glm-tools-pyglmnet#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":288,"forks":85,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":35.93},"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":"288","tone":"neutral"},{"label":"Freshness","value":"3y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":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":"288 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":62,"weight":0.08,"status":"info","detail":"288 stars, 85 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":22,"weight":0.14,"status":"fail","detail":"3y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add glm-tools/pyglmnet"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/glm-tools/pyglmnet"},{"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":"288 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"288 stars, 85 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"3y since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add glm-tools/pyglmnet"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/glm-tools/pyglmnet"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Install command has no obvious high-risk pattern"],"warnings":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"288 GitHub stars","repoActivity":"288 stars, 85 forks","lastPushed":"3y since push","license":"MIT","repository":"https://github.com/glm-tools/pyglmnet","install":"npx skills add glm-tools/pyglmnet","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add glm-tools/pyglmnet","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","3y since push"]},"agentCompatibility":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["ml-automation","machine-learning","automation","ml-media","data-science","elastic-net"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":49,"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":["Documentation summary is thin","49/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"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":["Documentation summary is thin","49/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"GitHub automation","description":"I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.","useCases":[{"slug":"github-automation","title":"GitHub automation"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add glm-tools/pyglmnet","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":288,"starsLabel":"288","forks":85,"license":"MIT","qualityScore":45,"trustScore":69,"auditScore":61},"maintenance":{"status":"stale","label":"3y since push","daysSincePush":1101,"lastPushedAt":"2023-08-17T17:49:07+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 3y since push"]},"coverageTags":["Coding","GitHub automation","ml-automation","machine-learning","automation","ml-media","data-science","elastic-net"]},"audit":{"audit_score":61,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 3y since push"]},"decision":{"readiness_score":35,"readiness_label":"Needs manual review","headline":"Needs validation for GitHub automation","role":"Needs validation","primary_fit":"GitHub automation","best_for":["GitHub automation workflows","general agent builders","builders willing to evaluate younger projects"],"risks":["Repository looks stale","No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one GitHub automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"glm-tools-pyglmnet","name":"Pyglmnet","description":"Python implementation of elastic-net regularized generalized linear models","category":"ml-automation","url":"https://www.openagentskill.com/skills/glm-tools-pyglmnet","repository":"https://github.com/glm-tools/pyglmnet","github_repo":"glm-tools/pyglmnet"},"suited_tasks":["GitHub automation workflows","general agent builders","builders willing to evaluate younger projects","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add glm-tools/pyglmnet","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install glm-tools-pyglmnet"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Pyglmnet\" agent skill from https://github.com/glm-tools/pyglmnet. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Python implementation of elastic-net regularized generalized linear models After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"glm-tools-pyglmnet\",\"task\":\"Install Pyglmnet\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Pyglmnet\" as a Claude Code skill from https://github.com/glm-tools/pyglmnet. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Python implementation of elastic-net regularized generalized linear models After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"glm-tools-pyglmnet\",\"task\":\"Install Pyglmnet\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Pyglmnet\" from https://github.com/glm-tools/pyglmnet into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Python implementation of elastic-net regularized generalized linear models After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"glm-tools-pyglmnet\",\"task\":\"Install Pyglmnet\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/glm-tools-pyglmnet/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/glm-tools-pyglmnet"},"trust":{"score":69,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"288 GitHub stars","repoActivity":"288 stars, 85 forks","lastPushed":"3y since push","license":"MIT","repository":"https://github.com/glm-tools/pyglmnet","install":"npx skills add glm-tools/pyglmnet","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["ml-automation","machine-learning","automation","ml-media","data-science","elastic-net"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":61,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 3y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":45,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"3y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Documentation summary is thin","Repository appears stale","Quality score needs review","Recent maintenance: 3y since push"],"agent_contract":{"task_input":"Use Pyglmnet in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 69/100 Manual review","Audit: 61/100 Needs review","Safety: 49/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"glm-tools-pyglmnet (Pyglmnet)","install_command":"npx skills add glm-tools/pyglmnet","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":"glm-tools-pyglmnet","task":"Use Pyglmnet 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/glm-tools-pyglmnet","api":"https://www.openagentskill.com/api/agent/skills/glm-tools-pyglmnet","audit":"https://www.openagentskill.com/skills/glm-tools-pyglmnet/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=glm-tools-pyglmnet&task=Use%20Pyglmnet%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Pyglmnet%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Pyglmnet%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/glm-tools-pyglmnet/install","manifest":"https://www.openagentskill.com/api/registry/manifest/glm-tools-pyglmnet"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"glm-tools-pyglmnet","name":"Pyglmnet","description":"Python implementation of elastic-net regularized generalized linear models","category":"ml-automation","url":"https://www.openagentskill.com/skills/glm-tools-pyglmnet","repository":"https://github.com/glm-tools/pyglmnet","github_repo":"glm-tools/pyglmnet"},"suited_tasks":["GitHub automation workflows","general agent builders","builders willing to evaluate younger projects","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add glm-tools/pyglmnet","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install glm-tools-pyglmnet"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Pyglmnet\" agent skill from https://github.com/glm-tools/pyglmnet. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Python implementation of elastic-net regularized generalized linear models After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"glm-tools-pyglmnet\",\"task\":\"Install Pyglmnet\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Pyglmnet\" as a Claude Code skill from https://github.com/glm-tools/pyglmnet. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Python implementation of elastic-net regularized generalized linear models After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"glm-tools-pyglmnet\",\"task\":\"Install Pyglmnet\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Pyglmnet\" from https://github.com/glm-tools/pyglmnet into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Python implementation of elastic-net regularized generalized linear models After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"glm-tools-pyglmnet\",\"task\":\"Install Pyglmnet\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/glm-tools-pyglmnet/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/glm-tools-pyglmnet"},"trust":{"score":69,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"288 GitHub stars","repoActivity":"288 stars, 85 forks","lastPushed":"3y since push","license":"MIT","repository":"https://github.com/glm-tools/pyglmnet","install":"npx skills add glm-tools/pyglmnet","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["ml-automation","machine-learning","automation","ml-media","data-science","elastic-net"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":61,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 3y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":45,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"3y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Documentation summary is thin","Repository appears stale","Quality score needs review","Recent maintenance: 3y since push"],"agent_contract":{"task_input":"Use Pyglmnet in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 69/100 Manual review","Audit: 61/100 Needs review","Safety: 49/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"glm-tools-pyglmnet (Pyglmnet)","install_command":"npx skills add glm-tools/pyglmnet","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":"glm-tools-pyglmnet","task":"Use Pyglmnet 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/glm-tools-pyglmnet","api":"https://www.openagentskill.com/api/agent/skills/glm-tools-pyglmnet","audit":"https://www.openagentskill.com/skills/glm-tools-pyglmnet/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=glm-tools-pyglmnet&task=Use%20Pyglmnet%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Pyglmnet%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Pyglmnet%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/glm-tools-pyglmnet/install","manifest":"https://www.openagentskill.com/api/registry/manifest/glm-tools-pyglmnet"}},"platforms":["Python","Machine Learning"],"use_cases":[{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"install":"npx skills add glm-tools/pyglmnet","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install glm-tools-pyglmnet","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Pyglmnet\" agent skill from https://github.com/glm-tools/pyglmnet. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Python implementation of elastic-net regularized generalized linear models After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"glm-tools-pyglmnet\",\"task\":\"Install Pyglmnet\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Pyglmnet\" as a Claude Code skill from https://github.com/glm-tools/pyglmnet. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Python implementation of elastic-net regularized generalized linear models After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"glm-tools-pyglmnet\",\"task\":\"Install Pyglmnet\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Pyglmnet\" from https://github.com/glm-tools/pyglmnet into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Python implementation of elastic-net regularized generalized linear models After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"glm-tools-pyglmnet\",\"task\":\"Install Pyglmnet\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/glm-tools/pyglmnet","github_repo":"glm-tools/pyglmnet","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"glm-tools/pyglmnet","recommendation_reasons":["Matches task terms: glm","Install handoff is available","Repository freshness signal is available","Registry match score 16"],"urls":{"web":"https://www.openagentskill.com/skills/glm-tools-pyglmnet","api":"https://www.openagentskill.com/api/agent/skills/glm-tools-pyglmnet","install_api":"https://www.openagentskill.com/api/skills/glm-tools-pyglmnet/install","audit":"https://www.openagentskill.com/skills/glm-tools-pyglmnet/audit","repository":"https://github.com/glm-tools/pyglmnet"}},{"rank":4,"match_type":"related","match_score":11,"raw_match_score":78.8,"semantic_relevance":30,"slug":"huggingface-transformers","name":"Transformers","description":"🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. ","tagline":"🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. ","category":"ml-automation","tags":["machine-learning","automation","ml-media","audio","deep-learning","deepseek","gemma","glm","hacktoberfest","llm"],"author":{"name":"huggingface","verified":true,"url":"https://github.com/huggingface"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"huggingface/transformers","creatorName":"huggingface","creatorUrl":"https://github.com/huggingface","sourceUrl":"https://github.com/huggingface/transformers","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/huggingface-transformers#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":161622,"forks":33519,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":75.2},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"162K","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":90,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"162K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"162K stars, 34K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add huggingface/transformers"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/huggingface/transformers"},{"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":"162K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"162K stars, 34K 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 huggingface/transformers"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/huggingface/transformers"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin"],"evidence":{"stars":"162K GitHub stars","repoActivity":"162K stars, 34K forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/huggingface/transformers","install":"npx skills add huggingface/transformers","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add huggingface/transformers","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["ml-automation","machine-learning","automation","ml-media","audio","deep-learning"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin"]},"safety":{"score":81,"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","81/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","81/100 agent safety score"]},"supply_profile":{"track":{"slug":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Multimodal media","description":"I need my agent to process images, video, or audio and extract useful information.","useCases":[{"slug":"multimodal-media","title":"Multimodal media"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"workflow-automation","title":"Workflow automation"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add huggingface/transformers","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":161622,"starsLabel":"162K","forks":33519,"license":"Apache-2.0","qualityScore":100,"trustScore":90,"auditScore":93},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":67,"lastPushedAt":"2026-06-16T09:38:44+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Design","Multimodal media","ml-automation","machine-learning","automation","ml-media","audio","deep-learning"]},"audit":{"audit_score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Multimodal media","role":"Primary pick","primary_fit":"Multimodal media","best_for":["Multimodal media workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Multimodal media 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":"huggingface-transformers","name":"Transformers","description":"🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. ","category":"ml-automation","url":"https://www.openagentskill.com/skills/huggingface-transformers","repository":"https://github.com/huggingface/transformers","github_repo":"huggingface/transformers"},"suited_tasks":["Multimodal media workflows","general agent builders","teams that value GitHub adoption signals","Read media metadata","Convert formats","Summarize visual or audio content","Navigate pages","Click and type safely"],"suited_agents":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add huggingface/transformers","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install huggingface-transformers"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Transformers\" agent skill from https://github.com/huggingface/transformers. 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: 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"huggingface-transformers\",\"task\":\"Install Transformers\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Transformers\" as a Claude Code skill from https://github.com/huggingface/transformers. 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: 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"huggingface-transformers\",\"task\":\"Install Transformers\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Transformers\" from https://github.com/huggingface/transformers 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: 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"huggingface-transformers\",\"task\":\"Install Transformers\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/huggingface-transformers/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/huggingface-transformers"},"trust":{"score":90,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"162K GitHub stars","repoActivity":"162K stars, 34K forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/huggingface/transformers","install":"npx skills add huggingface/transformers","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["ml-automation","machine-learning","automation","ml-media","audio","deep-learning"],"known_risks":["Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Transformers in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 90/100 Production candidate","Audit: 93/100 Safe to try","Safety: 81/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"huggingface-transformers (Transformers)","install_command":"npx skills add huggingface/transformers","risk_summary":"Safe to try; Reviewed; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"huggingface-transformers","task":"Use Transformers 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/huggingface-transformers","api":"https://www.openagentskill.com/api/agent/skills/huggingface-transformers","audit":"https://www.openagentskill.com/skills/huggingface-transformers/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=huggingface-transformers&task=Use%20Transformers%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Transformers%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Transformers%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/huggingface-transformers/install","manifest":"https://www.openagentskill.com/api/registry/manifest/huggingface-transformers"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"huggingface-transformers","name":"Transformers","description":"🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. ","category":"ml-automation","url":"https://www.openagentskill.com/skills/huggingface-transformers","repository":"https://github.com/huggingface/transformers","github_repo":"huggingface/transformers"},"suited_tasks":["Multimodal media workflows","general agent builders","teams that value GitHub adoption signals","Read media metadata","Convert formats","Summarize visual or audio content","Navigate pages","Click and type safely"],"suited_agents":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add huggingface/transformers","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install huggingface-transformers"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Transformers\" agent skill from https://github.com/huggingface/transformers. 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: 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"huggingface-transformers\",\"task\":\"Install Transformers\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Transformers\" as a Claude Code skill from https://github.com/huggingface/transformers. 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: 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"huggingface-transformers\",\"task\":\"Install Transformers\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Transformers\" from https://github.com/huggingface/transformers 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: 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"huggingface-transformers\",\"task\":\"Install Transformers\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/huggingface-transformers/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/huggingface-transformers"},"trust":{"score":90,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"162K GitHub stars","repoActivity":"162K stars, 34K forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/huggingface/transformers","install":"npx skills add huggingface/transformers","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["ml-automation","machine-learning","automation","ml-media","audio","deep-learning"],"known_risks":["Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":93,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Transformers in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 90/100 Production candidate","Audit: 93/100 Safe to try","Safety: 81/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"huggingface-transformers (Transformers)","install_command":"npx skills add huggingface/transformers","risk_summary":"Safe to try; Reviewed; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"huggingface-transformers","task":"Use Transformers 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/huggingface-transformers","api":"https://www.openagentskill.com/api/agent/skills/huggingface-transformers","audit":"https://www.openagentskill.com/skills/huggingface-transformers/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=huggingface-transformers&task=Use%20Transformers%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Transformers%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Transformers%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/huggingface-transformers/install","manifest":"https://www.openagentskill.com/api/registry/manifest/huggingface-transformers"}},"platforms":["Python","Machine Learning"],"use_cases":[{"slug":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"}],"install":"npx skills add huggingface/transformers","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install huggingface-transformers","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Transformers\" agent skill from https://github.com/huggingface/transformers. 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: 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"huggingface-transformers\",\"task\":\"Install Transformers\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Transformers\" as a Claude Code skill from https://github.com/huggingface/transformers. 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: 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"huggingface-transformers\",\"task\":\"Install Transformers\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Transformers\" from https://github.com/huggingface/transformers 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: 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"huggingface-transformers\",\"task\":\"Install Transformers\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/huggingface/transformers","github_repo":"huggingface/transformers","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"huggingface/transformers","recommendation_reasons":["Matches task terms: glm","Strong GitHub adoption: 161,622 stars","Quality score 75/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/huggingface-transformers","api":"https://www.openagentskill.com/api/agent/skills/huggingface-transformers","install_api":"https://www.openagentskill.com/api/skills/huggingface-transformers/install","audit":"https://www.openagentskill.com/skills/huggingface-transformers/audit","repository":"https://github.com/huggingface/transformers"}},{"rank":5,"match_type":"related","match_score":8,"raw_match_score":57.6,"semantic_relevance":30,"slug":"vorojar-folio-ocr","name":"Folio OCR","description":"Open-source batch OCR workbench — a free, local alternative to ABBYY FineReader. Powered by Ollama + GLM-OCR + PP-DocLayoutV3, ~0.5s/page on RTX 4090. Three-panel editor, layout-aware, PDF/image batch processing, Markdown/Word export. 批量OCR工作台，纯本地运行，免费平替ABBYY，适合书籍文档数字化。","tagline":"Open-source batch OCR workbench — a free, local alternative to ABBYY FineReader. Powered by Ollama + GLM-OCR + PP-DocLayoutV3, ~0.5s/page on RTX 4090. Three-panel editor, layout-aware, PDF/image batch processing, Markdown/Word export. 批量OCR工作台，纯本地运行，免费平替ABBYY，适合书籍文档数字化。","category":"document-processing","tags":["ocr","documents","extraction","abbyy-alternative","batch-ocr","book-digitization","document-ocr","document-processing","glm-ocr","layout-detection"],"author":{"name":"vorojar","verified":false,"url":"https://github.com/vorojar"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"vorojar/Folio-OCR","creatorName":"vorojar","creatorUrl":"https://github.com/vorojar","sourceUrl":"https://github.com/vorojar/Folio-OCR","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/vorojar-folio-ocr#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":445,"forks":60,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":49.25},"quality":{"score":78,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"445","tone":"neutral"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":78,"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":"445 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":62,"weight":0.08,"status":"info","detail":"445 stars, 60 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add vorojar/Folio-OCR"},{"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/vorojar/Folio-OCR"},{"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":"445 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"445 stars, 60 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add vorojar/Folio-OCR"},{"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/vorojar/Folio-OCR"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin"],"evidence":{"stars":"445 GitHub stars","repoActivity":"445 stars, 60 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/vorojar/Folio-OCR","install":"npx skills add vorojar/Folio-OCR","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 vorojar/Folio-OCR","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","OCR","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["document-processing","ocr","documents","extraction","abbyy-alternative","batch-ocr"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Documentation summary is thin"]},"safety":{"score":67,"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","67/100 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 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","67/100 agent safety score"]},"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"Document processing","description":"I need my agent to read PDFs, extract tables, and turn documents into structured data.","useCases":[{"slug":"document-processing","title":"Document processing"},{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"multimodal-media","title":"Multimodal media"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add vorojar/Folio-OCR","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":445,"starsLabel":"445","forks":60,"license":"MIT","qualityScore":78,"trustScore":78,"auditScore":83},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":65,"lastPushedAt":"2026-06-18T09:42:19+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Quality score needs review","Documentation summary is thin"]},"coverageTags":["Research","Document processing","document-processing","ocr","documents","extraction","abbyy-alternative","batch-ocr"]},"audit":{"audit_score":83,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review","Documentation summary is thin"]},"decision":{"readiness_score":77,"readiness_label":"Strong shortlist","headline":"Companion skill for Document processing","role":"Companion skill","primary_fit":"Document processing","best_for":["Document processing workflows","general agent builders","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Document processing 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":"vorojar-folio-ocr","name":"Folio OCR","description":"Open-source batch OCR workbench — a free, local alternative to ABBYY FineReader. Powered by Ollama + GLM-OCR + PP-DocLayoutV3, ~0.5s/page on RTX 4090. Three-panel editor, layout-aware, PDF/image batch processing, Markdown/Word export. 批量OCR工作台，纯本地运行，免费平替ABBYY，适合书籍文档数字化。","category":"document-processing","url":"https://www.openagentskill.com/skills/vorojar-folio-ocr","repository":"https://github.com/vorojar/Folio-OCR","github_repo":"vorojar/Folio-OCR"},"suited_tasks":["Document processing workflows","general agent builders","builders willing to evaluate younger projects","Read uploaded files","Extract structured fields","Prepare clean context for downstream agents","Chunk documents","Create embeddings"],"suited_agents":["Python","OCR","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add vorojar/Folio-OCR","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install vorojar-folio-ocr"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Folio OCR\" agent skill from https://github.com/vorojar/Folio-OCR. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Open-source batch OCR workbench — a free, local alternative to ABBYY FineReader. Powered by Ollama + GLM-OCR + PP-DocLayoutV3, ~0.5s/page on RTX 4090. Three-panel editor, layout-aware, PDF/image batch processing, Markdown/Word export. 批量OCR工作台，纯本地运行，免费平替ABBYY，适合书籍文档数字化。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"vorojar-folio-ocr\",\"task\":\"Install Folio OCR\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Folio OCR\" as a Claude Code skill from https://github.com/vorojar/Folio-OCR. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Open-source batch OCR workbench — a free, local alternative to ABBYY FineReader. Powered by Ollama + GLM-OCR + PP-DocLayoutV3, ~0.5s/page on RTX 4090. Three-panel editor, layout-aware, PDF/image batch processing, Markdown/Word export. 批量OCR工作台，纯本地运行，免费平替ABBYY，适合书籍文档数字化。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"vorojar-folio-ocr\",\"task\":\"Install Folio OCR\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Folio OCR\" from https://github.com/vorojar/Folio-OCR into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Open-source batch OCR workbench — a free, local alternative to ABBYY FineReader. Powered by Ollama + GLM-OCR + PP-DocLayoutV3, ~0.5s/page on RTX 4090. Three-panel editor, layout-aware, PDF/image batch processing, Markdown/Word export. 批量OCR工作台，纯本地运行，免费平替ABBYY，适合书籍文档数字化。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"vorojar-folio-ocr\",\"task\":\"Install Folio OCR\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/vorojar-folio-ocr/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/vorojar-folio-ocr"},"trust":{"score":78,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"445 GitHub stars","repoActivity":"445 stars, 60 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/vorojar/Folio-OCR","install":"npx skills add vorojar/Folio-OCR","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":["document-processing","ocr","documents","extraction","abbyy-alternative","batch-ocr"],"known_risks":["Quality score needs review","Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":83,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review","Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":78,"label":"Strong"},"supply":{"track":"Research and knowledge work","scenario":"Document processing","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","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use Folio OCR in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 78/100 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":"vorojar-folio-ocr (Folio OCR)","install_command":"npx skills add vorojar/Folio-OCR","risk_summary":"Safe to try; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"vorojar-folio-ocr","task":"Use Folio OCR 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/vorojar-folio-ocr","api":"https://www.openagentskill.com/api/agent/skills/vorojar-folio-ocr","audit":"https://www.openagentskill.com/skills/vorojar-folio-ocr/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=vorojar-folio-ocr&task=Use%20Folio%20OCR%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Folio%20OCR%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Folio%20OCR%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/vorojar-folio-ocr/install","manifest":"https://www.openagentskill.com/api/registry/manifest/vorojar-folio-ocr"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"vorojar-folio-ocr","name":"Folio OCR","description":"Open-source batch OCR workbench — a free, local alternative to ABBYY FineReader. Powered by Ollama + GLM-OCR + PP-DocLayoutV3, ~0.5s/page on RTX 4090. Three-panel editor, layout-aware, PDF/image batch processing, Markdown/Word export. 批量OCR工作台，纯本地运行，免费平替ABBYY，适合书籍文档数字化。","category":"document-processing","url":"https://www.openagentskill.com/skills/vorojar-folio-ocr","repository":"https://github.com/vorojar/Folio-OCR","github_repo":"vorojar/Folio-OCR"},"suited_tasks":["Document processing workflows","general agent builders","builders willing to evaluate younger projects","Read uploaded files","Extract structured fields","Prepare clean context for downstream agents","Chunk documents","Create embeddings"],"suited_agents":["Python","OCR","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add vorojar/Folio-OCR","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install vorojar-folio-ocr"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Folio OCR\" agent skill from https://github.com/vorojar/Folio-OCR. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Open-source batch OCR workbench — a free, local alternative to ABBYY FineReader. Powered by Ollama + GLM-OCR + PP-DocLayoutV3, ~0.5s/page on RTX 4090. Three-panel editor, layout-aware, PDF/image batch processing, Markdown/Word export. 批量OCR工作台，纯本地运行，免费平替ABBYY，适合书籍文档数字化。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"vorojar-folio-ocr\",\"task\":\"Install Folio OCR\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Folio OCR\" as a Claude Code skill from https://github.com/vorojar/Folio-OCR. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Open-source batch OCR workbench — a free, local alternative to ABBYY FineReader. Powered by Ollama + GLM-OCR + PP-DocLayoutV3, ~0.5s/page on RTX 4090. Three-panel editor, layout-aware, PDF/image batch processing, Markdown/Word export. 批量OCR工作台，纯本地运行，免费平替ABBYY，适合书籍文档数字化。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"vorojar-folio-ocr\",\"task\":\"Install Folio OCR\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Folio OCR\" from https://github.com/vorojar/Folio-OCR into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Open-source batch OCR workbench — a free, local alternative to ABBYY FineReader. Powered by Ollama + GLM-OCR + PP-DocLayoutV3, ~0.5s/page on RTX 4090. Three-panel editor, layout-aware, PDF/image batch processing, Markdown/Word export. 批量OCR工作台，纯本地运行，免费平替ABBYY，适合书籍文档数字化。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"vorojar-folio-ocr\",\"task\":\"Install Folio OCR\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/vorojar-folio-ocr/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/vorojar-folio-ocr"},"trust":{"score":78,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"445 GitHub stars","repoActivity":"445 stars, 60 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/vorojar/Folio-OCR","install":"npx skills add vorojar/Folio-OCR","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":["document-processing","ocr","documents","extraction","abbyy-alternative","batch-ocr"],"known_risks":["Quality score needs review","Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":83,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review","Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":78,"label":"Strong"},"supply":{"track":"Research and knowledge work","scenario":"Document processing","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","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use Folio OCR in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 78/100 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":"vorojar-folio-ocr (Folio OCR)","install_command":"npx skills add vorojar/Folio-OCR","risk_summary":"Safe to try; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"vorojar-folio-ocr","task":"Use Folio OCR 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/vorojar-folio-ocr","api":"https://www.openagentskill.com/api/agent/skills/vorojar-folio-ocr","audit":"https://www.openagentskill.com/skills/vorojar-folio-ocr/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=vorojar-folio-ocr&task=Use%20Folio%20OCR%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Folio%20OCR%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Folio%20OCR%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/vorojar-folio-ocr/install","manifest":"https://www.openagentskill.com/api/registry/manifest/vorojar-folio-ocr"}},"platforms":["Python","OCR"],"use_cases":[{"slug":"document-processing","title":"Document processing","url":"https://www.openagentskill.com/use-cases/document-processing"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"},{"slug":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"}],"install":"npx skills add vorojar/Folio-OCR","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install vorojar-folio-ocr","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Folio OCR\" agent skill from https://github.com/vorojar/Folio-OCR. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Open-source batch OCR workbench — a free, local alternative to ABBYY FineReader. Powered by Ollama + GLM-OCR + PP-DocLayoutV3, ~0.5s/page on RTX 4090. Three-panel editor, layout-aware, PDF/image batch processing, Markdown/Word export. 批量OCR工作台，纯本地运行，免费平替ABBYY，适合书籍文档数字化。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"vorojar-folio-ocr\",\"task\":\"Install Folio OCR\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Folio OCR\" as a Claude Code skill from https://github.com/vorojar/Folio-OCR. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Open-source batch OCR workbench — a free, local alternative to ABBYY FineReader. Powered by Ollama + GLM-OCR + PP-DocLayoutV3, ~0.5s/page on RTX 4090. Three-panel editor, layout-aware, PDF/image batch processing, Markdown/Word export. 批量OCR工作台，纯本地运行，免费平替ABBYY，适合书籍文档数字化。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"vorojar-folio-ocr\",\"task\":\"Install Folio OCR\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Folio OCR\" from https://github.com/vorojar/Folio-OCR into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Open-source batch OCR workbench — a free, local alternative to ABBYY FineReader. Powered by Ollama + GLM-OCR + PP-DocLayoutV3, ~0.5s/page on RTX 4090. Three-panel editor, layout-aware, PDF/image batch processing, Markdown/Word export. 批量OCR工作台，纯本地运行，免费平替ABBYY，适合书籍文档数字化。 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"vorojar-folio-ocr\",\"task\":\"Install Folio OCR\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/vorojar/Folio-OCR","github_repo":"vorojar/Folio-OCR","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"vorojar/folio-ocr","recommendation_reasons":["Matches task terms: glm","Install handoff is available","Repository freshness signal is available","Registry match score 8"],"urls":{"web":"https://www.openagentskill.com/skills/vorojar-folio-ocr","api":"https://www.openagentskill.com/api/agent/skills/vorojar-folio-ocr","install_api":"https://www.openagentskill.com/api/skills/vorojar-folio-ocr/install","audit":"https://www.openagentskill.com/skills/vorojar-folio-ocr/audit","repository":"https://github.com/vorojar/Folio-OCR"}},{"rank":6,"match_type":"related","match_score":8,"raw_match_score":54.7,"semantic_relevance":30,"slug":"vobc-oh-my-coder","name":"Oh My Coder","description":"Multi-Agent AI Coding Assistant - 支持 DeepSeek / GLM / MiMo 等 12+ 国产大模型，多智能体协作编程","tagline":"Multi-Agent AI Coding Assistant - 支持 DeepSeek / GLM / MiMo 等 12+ 国产大模型，多智能体协作编程","category":"coding-agents","tags":["code-review","developer-tools","coding","ai-coding","chinese","cli","code-assistant","deepseek","developer-tool","glm"],"author":{"name":"VOBC","verified":false,"url":"https://github.com/VOBC"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"VOBC/oh-my-coder","creatorName":"VOBC","creatorUrl":"https://github.com/VOBC","sourceUrl":"https://github.com/VOBC/oh-my-coder","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/vobc-oh-my-coder#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":168,"forks":30,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":46.3},"quality":{"score":67,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"168","tone":"neutral"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":73,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"168 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"168 stars, 30 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"command execution surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add VOBC/oh-my-coder"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":76,"weight":0.07,"status":"info","detail":"shell or command execution"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/VOBC/oh-my-coder"},{"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":"168 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"168 stars, 30 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface"},{"status":"pass","label":"Install availability","detail":"npx skills add VOBC/oh-my-coder"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"shell or command execution"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/VOBC/oh-my-coder"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 168 stars, 30 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"168 GitHub stars","repoActivity":"168 stars, 30 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/VOBC/oh-my-coder","install":"npx skills add VOBC/oh-my-coder","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add VOBC/oh-my-coder","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","Code Review","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 168 stars, 30 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["coding-agents","code-review","developer-tools","coding","ai-coding","chinese"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 168 stars, 30 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":53,"level":"avoid_auto_install","label":"Avoid automatic install","safety_tier":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","summary":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","auto_install_policy":"review","reasons":["High-risk permission hints: Shell or command execution","53/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"shell","label":"Shell or command execution","reason":"Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.","severity":"high"},{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["High-risk permission hints: Shell or command execution","Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","reasons":["High-risk permission hints: Shell or command execution","53/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"github-automation","title":"GitHub automation"},{"slug":"web-scraping","title":"Web scraping"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add VOBC/oh-my-coder","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":168,"starsLabel":"168","forks":30,"license":"MIT","qualityScore":67,"trustScore":73,"auditScore":77},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":61,"lastPushedAt":"2026-06-22T14:31:13+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 168 stars, 30 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Needs review"]},"coverageTags":["Coding","Coding agents","coding-agents","code-review","developer-tools","ai-coding","chinese","cli"]},"audit":{"audit_score":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 168 stars, 30 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"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","general agent builders","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one 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":"vobc-oh-my-coder","name":"Oh My Coder","description":"Multi-Agent AI Coding Assistant - 支持 DeepSeek / GLM / MiMo 等 12+ 国产大模型，多智能体协作编程","category":"coding-agents","url":"https://www.openagentskill.com/skills/vobc-oh-my-coder","repository":"https://github.com/VOBC/oh-my-coder","github_repo":"VOBC/oh-my-coder"},"suited_tasks":["Coding agents workflows","general agent builders","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","Code Review","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add VOBC/oh-my-coder","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install vobc-oh-my-coder"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Oh My Coder\" agent skill from https://github.com/VOBC/oh-my-coder. 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 AI Coding Assistant - 支持 DeepSeek / GLM / MiMo 等 12+ 国产大模型，多智能体协作编程 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"vobc-oh-my-coder\",\"task\":\"Install Oh My Coder\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Oh My Coder\" as a Claude Code skill from https://github.com/VOBC/oh-my-coder. 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 AI Coding Assistant - 支持 DeepSeek / GLM / MiMo 等 12+ 国产大模型，多智能体协作编程 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"vobc-oh-my-coder\",\"task\":\"Install Oh My Coder\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Oh My Coder\" from https://github.com/VOBC/oh-my-coder 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 AI Coding Assistant - 支持 DeepSeek / GLM / MiMo 等 12+ 国产大模型，多智能体协作编程 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"vobc-oh-my-coder\",\"task\":\"Install Oh My Coder\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/vobc-oh-my-coder/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/vobc-oh-my-coder"},"trust":{"score":73,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"168 GitHub stars","repoActivity":"168 stars, 30 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/VOBC/oh-my-coder","install":"npx skills add VOBC/oh-my-coder","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["coding-agents","code-review","developer-tools","coding","ai-coding","chinese"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 168 stars, 30 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 168 stars, 30 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":67,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution","Documentation summary is thin","Quality score needs review","Stars/forks activity: 168 stars, 30 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"agent_contract":{"task_input":"Use Oh My Coder in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 73/100 Strong shortlist","Audit: 77/100 Needs review","Safety: 53/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"vobc-oh-my-coder (Oh My Coder)","install_command":"npx skills add VOBC/oh-my-coder","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":"vobc-oh-my-coder","task":"Use Oh My Coder 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/vobc-oh-my-coder","api":"https://www.openagentskill.com/api/agent/skills/vobc-oh-my-coder","audit":"https://www.openagentskill.com/skills/vobc-oh-my-coder/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=vobc-oh-my-coder&task=Use%20Oh%20My%20Coder%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Oh%20My%20Coder%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Oh%20My%20Coder%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/vobc-oh-my-coder/install","manifest":"https://www.openagentskill.com/api/registry/manifest/vobc-oh-my-coder"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"vobc-oh-my-coder","name":"Oh My Coder","description":"Multi-Agent AI Coding Assistant - 支持 DeepSeek / GLM / MiMo 等 12+ 国产大模型，多智能体协作编程","category":"coding-agents","url":"https://www.openagentskill.com/skills/vobc-oh-my-coder","repository":"https://github.com/VOBC/oh-my-coder","github_repo":"VOBC/oh-my-coder"},"suited_tasks":["Coding agents workflows","general agent builders","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","Code Review","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add VOBC/oh-my-coder","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install vobc-oh-my-coder"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Oh My Coder\" agent skill from https://github.com/VOBC/oh-my-coder. 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 AI Coding Assistant - 支持 DeepSeek / GLM / MiMo 等 12+ 国产大模型，多智能体协作编程 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"vobc-oh-my-coder\",\"task\":\"Install Oh My Coder\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Oh My Coder\" as a Claude Code skill from https://github.com/VOBC/oh-my-coder. 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 AI Coding Assistant - 支持 DeepSeek / GLM / MiMo 等 12+ 国产大模型，多智能体协作编程 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"vobc-oh-my-coder\",\"task\":\"Install Oh My Coder\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Oh My Coder\" from https://github.com/VOBC/oh-my-coder 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 AI Coding Assistant - 支持 DeepSeek / GLM / MiMo 等 12+ 国产大模型，多智能体协作编程 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"vobc-oh-my-coder\",\"task\":\"Install Oh My Coder\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/vobc-oh-my-coder/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/vobc-oh-my-coder"},"trust":{"score":73,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"168 GitHub stars","repoActivity":"168 stars, 30 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/VOBC/oh-my-coder","install":"npx skills add VOBC/oh-my-coder","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["coding-agents","code-review","developer-tools","coding","ai-coding","chinese"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 168 stars, 30 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 168 stars, 30 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":67,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution","Documentation summary is thin","Quality score needs review","Stars/forks activity: 168 stars, 30 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"agent_contract":{"task_input":"Use Oh My Coder in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 73/100 Strong shortlist","Audit: 77/100 Needs review","Safety: 53/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"vobc-oh-my-coder (Oh My Coder)","install_command":"npx skills add VOBC/oh-my-coder","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":"vobc-oh-my-coder","task":"Use Oh My Coder 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/vobc-oh-my-coder","api":"https://www.openagentskill.com/api/agent/skills/vobc-oh-my-coder","audit":"https://www.openagentskill.com/skills/vobc-oh-my-coder/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=vobc-oh-my-coder&task=Use%20Oh%20My%20Coder%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Oh%20My%20Coder%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Oh%20My%20Coder%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/vobc-oh-my-coder/install","manifest":"https://www.openagentskill.com/api/registry/manifest/vobc-oh-my-coder"}},"platforms":["Python","Code Review"],"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"}],"install":"npx skills add VOBC/oh-my-coder","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install vobc-oh-my-coder","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Oh My Coder\" agent skill from https://github.com/VOBC/oh-my-coder. 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 AI Coding Assistant - 支持 DeepSeek / GLM / MiMo 等 12+ 国产大模型，多智能体协作编程 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"vobc-oh-my-coder\",\"task\":\"Install Oh My Coder\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Oh My Coder\" as a Claude Code skill from https://github.com/VOBC/oh-my-coder. 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 AI Coding Assistant - 支持 DeepSeek / GLM / MiMo 等 12+ 国产大模型，多智能体协作编程 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"vobc-oh-my-coder\",\"task\":\"Install Oh My Coder\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Oh My Coder\" from https://github.com/VOBC/oh-my-coder 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 AI Coding Assistant - 支持 DeepSeek / GLM / MiMo 等 12+ 国产大模型，多智能体协作编程 After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"vobc-oh-my-coder\",\"task\":\"Install Oh My Coder\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/VOBC/oh-my-coder","github_repo":"VOBC/oh-my-coder","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"vobc/oh-my-coder","recommendation_reasons":["Matches task terms: glm","Install handoff is available","Repository freshness signal is available","Registry match score 8"],"urls":{"web":"https://www.openagentskill.com/skills/vobc-oh-my-coder","api":"https://www.openagentskill.com/api/agent/skills/vobc-oh-my-coder","install_api":"https://www.openagentskill.com/api/skills/vobc-oh-my-coder/install","audit":"https://www.openagentskill.com/skills/vobc-oh-my-coder/audit","repository":"https://github.com/VOBC/oh-my-coder"}},{"rank":7,"match_type":"related","match_score":7,"raw_match_score":49.8,"semantic_relevance":30,"slug":"h2oai-h2o-3","name":"H2o 3","description":"H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.","tagline":"H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.","category":"ml-automation","tags":["machine-learning","automation","ml-media","automl","big-data","data-science","deep-learning","distributed","ensemble-learning","gbm"],"author":{"name":"h2oai","verified":true,"url":"https://github.com/h2oai"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"h2oai/h2o-3","creatorName":"h2oai","creatorUrl":"https://github.com/h2oai","sourceUrl":"https://github.com/h2oai/h2o-3","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/h2oai-h2o-3#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":7492,"forks":2030,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":65.82},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"7.5K","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":89,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"weight":0.13,"status":"pass","detail":"7.5K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":93,"weight":0.08,"status":"pass","detail":"7.5K stars, 2.0K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add h2oai/h2o-3"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/h2oai/h2o-3"},{"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":"7.5K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"7.5K stars, 2.0K 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 h2oai/h2o-3"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/h2oai/h2o-3"},{"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":"7.5K GitHub stars","repoActivity":"7.5K stars, 2.0K forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/h2oai/h2o-3","install":"npx skills add h2oai/h2o-3","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add h2oai/h2o-3","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Jupyter Notebook","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["No major trust warnings detected from available metadata"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["ml-automation","machine-learning","automation","ml-media","automl","big-data"],"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":88,"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","88/100 agent safety score"]},"auto_install_allowed":true,"human_review_required":false,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":[],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"verified","label":"Verified","badge":"VERIFIED","auto_install_policy":"allow","auto_install_allowed":true,"human_review_required":false,"blocked":false,"recommended_action":"Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.","reasons":["Verified listing","Safe-to-try audit","88/100 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":"browser-automation","title":"Browser automation"},{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"research-agents","title":"Research agents"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Jupyter Notebook"],"install":{"ready":true,"command":"npx skills add h2oai/h2o-3","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":7492,"starsLabel":"7.5K","forks":2030,"license":"Apache-2.0","qualityScore":100,"trustScore":89,"auditScore":92},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":67,"lastPushedAt":"2026-06-16T00:02:25+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","ml-automation","machine-learning","automation","ml-media","automl","big-data"]},"audit":{"audit_score":92,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":[]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Browser automation","role":"Primary pick","primary_fit":"Browser automation","best_for":["Browser automation workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Browser automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"h2oai-h2o-3","name":"H2o 3","description":"H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.","category":"ml-automation","url":"https://www.openagentskill.com/skills/h2oai-h2o-3","repository":"https://github.com/h2oai/h2o-3","github_repo":"h2oai/h2o-3"},"suited_tasks":["Browser automation workflows","general agent builders","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Chunk documents","Create embeddings"],"suited_agents":["Jupyter Notebook","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add h2oai/h2o-3","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install h2oai-h2o-3"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"H2o 3\" agent skill from https://github.com/h2oai/h2o-3. 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: H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"h2oai-h2o-3\",\"task\":\"Install H2o 3\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"H2o 3\" as a Claude Code skill from https://github.com/h2oai/h2o-3. 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: H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"h2oai-h2o-3\",\"task\":\"Install H2o 3\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"H2o 3\" from https://github.com/h2oai/h2o-3 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: H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"h2oai-h2o-3\",\"task\":\"Install H2o 3\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/h2oai-h2o-3/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/h2oai-h2o-3"},"trust":{"score":89,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"7.5K GitHub stars","repoActivity":"7.5K stars, 2.0K forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/h2oai/h2o-3","install":"npx skills add h2oai/h2o-3","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["ml-automation","machine-learning","automation","ml-media","automl","big-data"],"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":92,"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 H2o 3 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: 89/100 Production candidate","Audit: 92/100 Safe to try","Safety: 88/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"h2oai-h2o-3 (H2o 3)","install_command":"npx skills add h2oai/h2o-3","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":"h2oai-h2o-3","task":"Use H2o 3 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/h2oai-h2o-3","api":"https://www.openagentskill.com/api/agent/skills/h2oai-h2o-3","audit":"https://www.openagentskill.com/skills/h2oai-h2o-3/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=h2oai-h2o-3&task=Use%20H2o%203%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20H2o%203%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20H2o%203%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/h2oai-h2o-3/install","manifest":"https://www.openagentskill.com/api/registry/manifest/h2oai-h2o-3"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"h2oai-h2o-3","name":"H2o 3","description":"H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc.","category":"ml-automation","url":"https://www.openagentskill.com/skills/h2oai-h2o-3","repository":"https://github.com/h2oai/h2o-3","github_repo":"h2oai/h2o-3"},"suited_tasks":["Browser automation workflows","general agent builders","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Chunk documents","Create embeddings"],"suited_agents":["Jupyter Notebook","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add h2oai/h2o-3","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install h2oai-h2o-3"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"H2o 3\" agent skill from https://github.com/h2oai/h2o-3. 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: H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"h2oai-h2o-3\",\"task\":\"Install H2o 3\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"H2o 3\" as a Claude Code skill from https://github.com/h2oai/h2o-3. 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: H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"h2oai-h2o-3\",\"task\":\"Install H2o 3\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"H2o 3\" from https://github.com/h2oai/h2o-3 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: H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"h2oai-h2o-3\",\"task\":\"Install H2o 3\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/h2oai-h2o-3/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/h2oai-h2o-3"},"trust":{"score":89,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"7.5K GitHub stars","repoActivity":"7.5K stars, 2.0K forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/h2oai/h2o-3","install":"npx skills add h2oai/h2o-3","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["ml-automation","machine-learning","automation","ml-media","automl","big-data"],"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":92,"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 H2o 3 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: 89/100 Production candidate","Audit: 92/100 Safe to try","Safety: 88/100 Safe to install with normal review","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"h2oai-h2o-3 (H2o 3)","install_command":"npx skills add h2oai/h2o-3","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":"h2oai-h2o-3","task":"Use H2o 3 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/h2oai-h2o-3","api":"https://www.openagentskill.com/api/agent/skills/h2oai-h2o-3","audit":"https://www.openagentskill.com/skills/h2oai-h2o-3/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=h2oai-h2o-3&task=Use%20H2o%203%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20H2o%203%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20H2o%203%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/h2oai-h2o-3/install","manifest":"https://www.openagentskill.com/api/registry/manifest/h2oai-h2o-3"}},"platforms":["Jupyter Notebook","Machine Learning"],"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"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 h2oai/h2o-3","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install h2oai-h2o-3","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"H2o 3\" agent skill from https://github.com/h2oai/h2o-3. 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: H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"h2oai-h2o-3\",\"task\":\"Install H2o 3\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"H2o 3\" as a Claude Code skill from https://github.com/h2oai/h2o-3. 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: H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"h2oai-h2o-3\",\"task\":\"Install H2o 3\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"H2o 3\" from https://github.com/h2oai/h2o-3 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: H2O is an Open Source, Distributed, Fast & Scalable Machine Learning Platform: Deep Learning, Gradient Boosting (GBM) & XGBoost, Random Forest, Generalized Linear Modeling (GLM with Elastic Net), K-Means, PCA, Generalized Additive Models (GAM), RuleFit, Support Vector Machine (SVM), Stacked Ensembles, Automatic Machine Learning (AutoML), etc. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"h2oai-h2o-3\",\"task\":\"Install H2o 3\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/h2oai/h2o-3","github_repo":"h2oai/h2o-3","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"h2oai/h2o-3","recommendation_reasons":["Matches task terms: glm","Useful GitHub adoption: 7,492 stars","Install handoff is available","Repository freshness signal is available","Registry match score 7"],"urls":{"web":"https://www.openagentskill.com/skills/h2oai-h2o-3","api":"https://www.openagentskill.com/api/agent/skills/h2oai-h2o-3","install_api":"https://www.openagentskill.com/api/skills/h2oai-h2o-3/install","audit":"https://www.openagentskill.com/skills/h2oai-h2o-3/audit","repository":"https://github.com/h2oai/h2o-3"}},{"rank":8,"match_type":"related","match_score":5,"raw_match_score":36,"semantic_relevance":30,"slug":"orkas-ai-orkas","name":"Orkas","description":"Open-source multi-agent AI desktop client — build and command your AI agent team through conversation. A commander LLM dispatches sub-agents in parallel or in series; agents self-evolve via reflection and skill crystallization. Local-first, BYO LLM keys (Claude · OpenAI · Gemini · DeepSeek · Kimi · GLM · Qwen). macOS / Windows / Linux.","tagline":"Open-source multi-agent AI desktop client — build and command your AI agent team through conversation. A commander LLM dispatches sub-agents in parallel or in series; agents self-evolve via reflection and skill crystallization. Local-first, BYO LLM keys (Claude · OpenAI · Gemini · DeepSeek · Kimi · GLM · Qwen). macOS / Windows / Linux.","category":"agent-frameworks","tags":["agents","ai-agents","agent-collaboration","agent-orchestration","agent-team","agentic-ai","ai-assistant","ai-team","ai-workflow","autonomous-agents"],"author":{"name":"Orkas-AI","verified":false,"url":"https://github.com/Orkas-AI"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"Orkas-AI/Orkas","creatorName":"Orkas-AI","creatorUrl":"https://github.com/Orkas-AI","sourceUrl":"https://github.com/Orkas-AI/Orkas","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/orkas-ai-orkas#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":806,"forks":35,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":54.05},"quality":{"score":86,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"806","tone":"positive"},{"label":"Freshness","value":"24d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":80,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":76,"weight":0.13,"status":"info","detail":"806 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":65,"weight":0.08,"status":"info","detail":"806 stars, 35 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":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add Orkas-AI/Orkas"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":76,"weight":0.07,"status":"info","detail":"shell or command execution"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/Orkas-AI/Orkas"},{"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":"806 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"806 stars, 35 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"24d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add Orkas-AI/Orkas"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"shell or command execution"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/Orkas-AI/Orkas"},{"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":"806 GitHub stars","repoActivity":"806 stars, 35 forks","lastPushed":"24d since push","license":"MIT","repository":"https://github.com/Orkas-AI/Orkas","install":"npx skills add Orkas-AI/Orkas","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add Orkas-AI/Orkas","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","24d since push"]},"agentCompatibility":["TypeScript","AI Agents","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":["agent-frameworks","agents","ai-agents","agent-collaboration","agent-orchestration","agent-team"],"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":63,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["High-risk permission hints: Shell or command execution","63/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"shell","label":"Shell or command execution","reason":"Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.","severity":"high"},{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["High-risk permission hints: Shell or command execution","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":["High-risk permission hints: Shell or command execution","63/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Local desktop","description":"I need my agent to operate local files and desktop apps in a repeatable workflow.","useCases":[{"slug":"local-desktop","title":"Local desktop"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"research-agents","title":"Research agents"}]},"applicableAgents":["Claude Code","OpenAI Agents","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add Orkas-AI/Orkas","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":806,"starsLabel":"806","forks":35,"license":"MIT","qualityScore":86,"trustScore":80,"auditScore":87},"maintenance":{"status":"fresh","label":"24d since push","daysSincePush":24,"lastPushedAt":"2026-07-29T11:53:19+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Quality score needs review"]},"coverageTags":["Coding","Local desktop","agent-frameworks","agents","ai-agents","agent-collaboration","agent-orchestration","agent-team"]},"audit":{"audit_score":87,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review"]},"decision":{"readiness_score":97,"readiness_label":"Production-ready","headline":"Primary pick for Local desktop","role":"Primary pick","primary_fit":"Local desktop","best_for":["Local desktop 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 Local desktop 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":"orkas-ai-orkas","name":"Orkas","description":"Open-source multi-agent AI desktop client — build and command your AI agent team through conversation. A commander LLM dispatches sub-agents in parallel or in series; agents self-evolve via reflection and skill crystallization. Local-first, BYO LLM keys (Claude · OpenAI · Gemini · DeepSeek · Kimi · GLM · Qwen). macOS / Windows / Linux.","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/orkas-ai-orkas","repository":"https://github.com/Orkas-AI/Orkas","github_repo":"Orkas-AI/Orkas"},"suited_tasks":["Local desktop workflows","Claude Code teams","teams that value GitHub adoption signals","Navigate local resources","Run repeatable desktop actions","Verify file outputs","Navigate pages","Click and type safely"],"suited_agents":["TypeScript","AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add Orkas-AI/Orkas","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install orkas-ai-orkas"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Orkas\" agent skill from https://github.com/Orkas-AI/Orkas. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Open-source multi-agent AI desktop client — build and command your AI agent team through conversation. A commander LLM dispatches sub-agents in parallel or in series; agents self-evolve via reflection and skill crystallization. Local-first, BYO LLM keys (Claude · OpenAI · Gemini · DeepSeek · Kimi · GLM · Qwen). macOS / Windows / Linux. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"orkas-ai-orkas\",\"task\":\"Install Orkas\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Orkas\" as a Claude Code skill from https://github.com/Orkas-AI/Orkas. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Open-source multi-agent AI desktop client — build and command your AI agent team through conversation. A commander LLM dispatches sub-agents in parallel or in series; agents self-evolve via reflection and skill crystallization. Local-first, BYO LLM keys (Claude · OpenAI · Gemini · DeepSeek · Kimi · GLM · Qwen). macOS / Windows / Linux. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"orkas-ai-orkas\",\"task\":\"Install Orkas\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Orkas\" from https://github.com/Orkas-AI/Orkas into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Open-source multi-agent AI desktop client — build and command your AI agent team through conversation. A commander LLM dispatches sub-agents in parallel or in series; agents self-evolve via reflection and skill crystallization. Local-first, BYO LLM keys (Claude · OpenAI · Gemini · DeepSeek · Kimi · GLM · Qwen). macOS / Windows / Linux. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"orkas-ai-orkas\",\"task\":\"Install Orkas\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/orkas-ai-orkas/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/orkas-ai-orkas"},"trust":{"score":80,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"806 GitHub stars","repoActivity":"806 stars, 35 forks","lastPushed":"24d since push","license":"MIT","repository":"https://github.com/Orkas-AI/Orkas","install":"npx skills add Orkas-AI/Orkas","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["agent-frameworks","agents","ai-agents","agent-collaboration","agent-orchestration","agent-team"],"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":87,"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":86,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Local desktop","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","High-risk permission hints: Shell or command execution","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 Orkas in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 80/100 Strong shortlist","Audit: 87/100 Safe to try","Safety: 63/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"orkas-ai-orkas (Orkas)","install_command":"npx skills add Orkas-AI/Orkas","risk_summary":"Safe to try; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"orkas-ai-orkas","task":"Use Orkas 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/orkas-ai-orkas","api":"https://www.openagentskill.com/api/agent/skills/orkas-ai-orkas","audit":"https://www.openagentskill.com/skills/orkas-ai-orkas/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=orkas-ai-orkas&task=Use%20Orkas%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Orkas%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Orkas%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/orkas-ai-orkas/install","manifest":"https://www.openagentskill.com/api/registry/manifest/orkas-ai-orkas"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"orkas-ai-orkas","name":"Orkas","description":"Open-source multi-agent AI desktop client — build and command your AI agent team through conversation. A commander LLM dispatches sub-agents in parallel or in series; agents self-evolve via reflection and skill crystallization. Local-first, BYO LLM keys (Claude · OpenAI · Gemini · DeepSeek · Kimi · GLM · Qwen). macOS / Windows / Linux.","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/orkas-ai-orkas","repository":"https://github.com/Orkas-AI/Orkas","github_repo":"Orkas-AI/Orkas"},"suited_tasks":["Local desktop workflows","Claude Code teams","teams that value GitHub adoption signals","Navigate local resources","Run repeatable desktop actions","Verify file outputs","Navigate pages","Click and type safely"],"suited_agents":["TypeScript","AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add Orkas-AI/Orkas","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install orkas-ai-orkas"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Orkas\" agent skill from https://github.com/Orkas-AI/Orkas. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Open-source multi-agent AI desktop client — build and command your AI agent team through conversation. A commander LLM dispatches sub-agents in parallel or in series; agents self-evolve via reflection and skill crystallization. Local-first, BYO LLM keys (Claude · OpenAI · Gemini · DeepSeek · Kimi · GLM · Qwen). macOS / Windows / Linux. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"orkas-ai-orkas\",\"task\":\"Install Orkas\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Orkas\" as a Claude Code skill from https://github.com/Orkas-AI/Orkas. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Open-source multi-agent AI desktop client — build and command your AI agent team through conversation. A commander LLM dispatches sub-agents in parallel or in series; agents self-evolve via reflection and skill crystallization. Local-first, BYO LLM keys (Claude · OpenAI · Gemini · DeepSeek · Kimi · GLM · Qwen). macOS / Windows / Linux. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"orkas-ai-orkas\",\"task\":\"Install Orkas\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Orkas\" from https://github.com/Orkas-AI/Orkas into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Open-source multi-agent AI desktop client — build and command your AI agent team through conversation. A commander LLM dispatches sub-agents in parallel or in series; agents self-evolve via reflection and skill crystallization. Local-first, BYO LLM keys (Claude · OpenAI · Gemini · DeepSeek · Kimi · GLM · Qwen). macOS / Windows / Linux. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"orkas-ai-orkas\",\"task\":\"Install Orkas\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/orkas-ai-orkas/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/orkas-ai-orkas"},"trust":{"score":80,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"806 GitHub stars","repoActivity":"806 stars, 35 forks","lastPushed":"24d since push","license":"MIT","repository":"https://github.com/Orkas-AI/Orkas","install":"npx skills add Orkas-AI/Orkas","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["agent-frameworks","agents","ai-agents","agent-collaboration","agent-orchestration","agent-team"],"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":87,"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":86,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Local desktop","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","High-risk permission hints: Shell or command execution","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 Orkas in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 80/100 Strong shortlist","Audit: 87/100 Safe to try","Safety: 63/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"orkas-ai-orkas (Orkas)","install_command":"npx skills add Orkas-AI/Orkas","risk_summary":"Safe to try; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"orkas-ai-orkas","task":"Use Orkas 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/orkas-ai-orkas","api":"https://www.openagentskill.com/api/agent/skills/orkas-ai-orkas","audit":"https://www.openagentskill.com/skills/orkas-ai-orkas/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=orkas-ai-orkas&task=Use%20Orkas%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Orkas%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Orkas%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/orkas-ai-orkas/install","manifest":"https://www.openagentskill.com/api/registry/manifest/orkas-ai-orkas"}},"platforms":["TypeScript","AI Agents","Claude Code","OpenAI Agents"],"use_cases":[{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"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 Orkas-AI/Orkas","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install orkas-ai-orkas","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Orkas\" agent skill from https://github.com/Orkas-AI/Orkas. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Open-source multi-agent AI desktop client — build and command your AI agent team through conversation. A commander LLM dispatches sub-agents in parallel or in series; agents self-evolve via reflection and skill crystallization. Local-first, BYO LLM keys (Claude · OpenAI · Gemini · DeepSeek · Kimi · GLM · Qwen). macOS / Windows / Linux. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"orkas-ai-orkas\",\"task\":\"Install Orkas\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Orkas\" as a Claude Code skill from https://github.com/Orkas-AI/Orkas. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Open-source multi-agent AI desktop client — build and command your AI agent team through conversation. A commander LLM dispatches sub-agents in parallel or in series; agents self-evolve via reflection and skill crystallization. Local-first, BYO LLM keys (Claude · OpenAI · Gemini · DeepSeek · Kimi · GLM · Qwen). macOS / Windows / Linux. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"orkas-ai-orkas\",\"task\":\"Install Orkas\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Orkas\" from https://github.com/Orkas-AI/Orkas into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Open-source multi-agent AI desktop client — build and command your AI agent team through conversation. A commander LLM dispatches sub-agents in parallel or in series; agents self-evolve via reflection and skill crystallization. Local-first, BYO LLM keys (Claude · OpenAI · Gemini · DeepSeek · Kimi · GLM · Qwen). macOS / Windows / Linux. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"orkas-ai-orkas\",\"task\":\"Install Orkas\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/Orkas-AI/Orkas","github_repo":"Orkas-AI/Orkas","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"orkas-ai/orkas","recommendation_reasons":["Matches task terms: glm","Useful GitHub adoption: 806 stars","Install handoff is available","Repository freshness signal is available","Registry match score 5"],"urls":{"web":"https://www.openagentskill.com/skills/orkas-ai-orkas","api":"https://www.openagentskill.com/api/agent/skills/orkas-ai-orkas","install_api":"https://www.openagentskill.com/api/skills/orkas-ai-orkas/install","audit":"https://www.openagentskill.com/skills/orkas-ai-orkas/audit","repository":"https://github.com/Orkas-AI/Orkas"}},{"rank":9,"match_type":"related","match_score":4,"raw_match_score":30.6,"semantic_relevance":30,"slug":"deepelementlab-clawcode","name":"Clawcode","description":"ClawCode is claude code inspired implementation in python and Rust focused on agents and experience-based evolution, and is an Open-source coding-agent CLI for Anthropic, OpenAI, Gemini, DeepSeek, GLM, Kimit, Ollama, Codex, GitHub Models, and 200+ models via OpenAI-compatible APIs.","tagline":"ClawCode is claude code inspired implementation in python and Rust focused on agents and experience-based evolution, and is an Open-source coding-agent CLI for Anthropic, OpenAI, Gemini, DeepSeek, GLM, Kimit, Ollama, Codex, GitHub Models, and 200+ models via OpenAI-compatible APIs.","category":"agent-frameworks","tags":["multi-agent","orchestration","ai-agents","automation","clawcode","coding-assistant","llm","python3","reinforcement-learning","rust-library"],"author":{"name":"deepelementlab","verified":false,"url":"https://github.com/deepelementlab"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"deepelementlab/clawcode","creatorName":"deepelementlab","creatorUrl":"https://github.com/deepelementlab","sourceUrl":"https://github.com/deepelementlab/clawcode","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/deepelementlab-clawcode#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":162,"forks":49,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":46.19},"quality":{"score":73,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"162","tone":"neutral"},{"label":"Freshness","value":"3mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"GPL-3.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":73,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"162 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"162 stars, 49 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"3mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"GPL-3.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"command execution surface"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add deepelementlab/clawcode"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":76,"weight":0.07,"status":"info","detail":"shell or command execution"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/deepelementlab/clawcode"},{"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":"162 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"162 stars, 49 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"3mo since push"},{"status":"pass","label":"License clarity","detail":"GPL-3.0"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"info","label":"Dependency/runtime risk","detail":"command execution surface"},{"status":"pass","label":"Install availability","detail":"npx skills add deepelementlab/clawcode"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"shell or command execution"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/deepelementlab/clawcode"},{"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","Documentation summary is thin","Stars/forks activity: 162 stars, 49 forks; issue activity unavailable in current metadata"],"evidence":{"stars":"162 GitHub stars","repoActivity":"162 stars, 49 forks","lastPushed":"3mo since push","license":"GPL-3.0","repository":"https://github.com/deepelementlab/clawcode","install":"npx skills add deepelementlab/clawcode","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add deepelementlab/clawcode","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","Multi-Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 162 stars, 49 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":["agent-frameworks","multi-agent","orchestration","ai-agents","automation","clawcode"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 162 stars, 49 forks; issue activity unavailable in current metadata"]},"safety":{"score":54,"level":"avoid_auto_install","label":"Avoid automatic install","safety_tier":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","summary":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","auto_install_policy":"review","reasons":["High-risk permission hints: Shell or command execution","54/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"shell","label":"Shell or command execution","reason":"Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.","severity":"high"},{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["High-risk permission hints: Shell or command execution","Quality score needs review"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","reasons":["High-risk permission hints: Shell or command execution","54/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"github-automation","title":"GitHub automation"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["Claude Code","OpenAI Agents","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add deepelementlab/clawcode","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":162,"starsLabel":"162","forks":49,"license":"GPL-3.0","qualityScore":73,"trustScore":73,"auditScore":78},"maintenance":{"status":"active","label":"3mo since push","daysSincePush":93,"lastPushedAt":"2026-05-21T09:49:11+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 162 stars, 49 forks; issue activity unavailable in current metadata","Needs review"]},"coverageTags":["Coding","Coding agents","agent-frameworks","multi-agent","orchestration","ai-agents","automation","clawcode"]},"audit":{"audit_score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 162 stars, 49 forks; issue activity unavailable in current metadata"]},"decision":{"readiness_score":72,"readiness_label":"Strong shortlist","headline":"Companion skill for Coding agents","role":"Companion skill","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":"deepelementlab-clawcode","name":"Clawcode","description":"ClawCode is claude code inspired implementation in python and Rust focused on agents and experience-based evolution, and is an Open-source coding-agent CLI for Anthropic, OpenAI, Gemini, DeepSeek, GLM, Kimit, Ollama, Codex, GitHub Models, and 200+ models via OpenAI-compatible APIs.","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/deepelementlab-clawcode","repository":"https://github.com/deepelementlab/clawcode","github_repo":"deepelementlab/clawcode"},"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","Multi-Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add deepelementlab/clawcode","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install deepelementlab-clawcode"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Clawcode\" agent skill from https://github.com/deepelementlab/clawcode. 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: ClawCode is claude code inspired implementation in python and Rust focused on agents and experience-based evolution, and is an Open-source coding-agent CLI for Anthropic, OpenAI, Gemini, DeepSeek, GLM, Kimit, Ollama, Codex, GitHub Models, and 200+ models via OpenAI-compatible APIs. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"deepelementlab-clawcode\",\"task\":\"Install Clawcode\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Clawcode\" as a Claude Code skill from https://github.com/deepelementlab/clawcode. 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: ClawCode is claude code inspired implementation in python and Rust focused on agents and experience-based evolution, and is an Open-source coding-agent CLI for Anthropic, OpenAI, Gemini, DeepSeek, GLM, Kimit, Ollama, Codex, GitHub Models, and 200+ models via OpenAI-compatible APIs. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"deepelementlab-clawcode\",\"task\":\"Install Clawcode\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Clawcode\" from https://github.com/deepelementlab/clawcode 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: ClawCode is claude code inspired implementation in python and Rust focused on agents and experience-based evolution, and is an Open-source coding-agent CLI for Anthropic, OpenAI, Gemini, DeepSeek, GLM, Kimit, Ollama, Codex, GitHub Models, and 200+ models via OpenAI-compatible APIs. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"deepelementlab-clawcode\",\"task\":\"Install Clawcode\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/deepelementlab-clawcode/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/deepelementlab-clawcode"},"trust":{"score":73,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"162 GitHub stars","repoActivity":"162 stars, 49 forks","lastPushed":"3mo since push","license":"GPL-3.0","repository":"https://github.com/deepelementlab/clawcode","install":"npx skills add deepelementlab/clawcode","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["agent-frameworks","multi-agent","orchestration","ai-agents","automation","clawcode"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 162 stars, 49 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","Documentation summary is thin","Stars/forks activity: 162 stars, 49 forks; issue activity unavailable in current metadata"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":73,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"3mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution","Quality score needs review","Documentation summary is thin","Stars/forks activity: 162 stars, 49 forks; issue activity unavailable in current metadata","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use Clawcode in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 73/100 Strong shortlist","Audit: 78/100 Needs review","Safety: 54/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"deepelementlab-clawcode (Clawcode)","install_command":"npx skills add deepelementlab/clawcode","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":"deepelementlab-clawcode","task":"Use Clawcode 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/deepelementlab-clawcode","api":"https://www.openagentskill.com/api/agent/skills/deepelementlab-clawcode","audit":"https://www.openagentskill.com/skills/deepelementlab-clawcode/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=deepelementlab-clawcode&task=Use%20Clawcode%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Clawcode%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Clawcode%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/deepelementlab-clawcode/install","manifest":"https://www.openagentskill.com/api/registry/manifest/deepelementlab-clawcode"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"deepelementlab-clawcode","name":"Clawcode","description":"ClawCode is claude code inspired implementation in python and Rust focused on agents and experience-based evolution, and is an Open-source coding-agent CLI for Anthropic, OpenAI, Gemini, DeepSeek, GLM, Kimit, Ollama, Codex, GitHub Models, and 200+ models via OpenAI-compatible APIs.","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/deepelementlab-clawcode","repository":"https://github.com/deepelementlab/clawcode","github_repo":"deepelementlab/clawcode"},"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","Multi-Agent","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add deepelementlab/clawcode","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install deepelementlab-clawcode"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Clawcode\" agent skill from https://github.com/deepelementlab/clawcode. 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: ClawCode is claude code inspired implementation in python and Rust focused on agents and experience-based evolution, and is an Open-source coding-agent CLI for Anthropic, OpenAI, Gemini, DeepSeek, GLM, Kimit, Ollama, Codex, GitHub Models, and 200+ models via OpenAI-compatible APIs. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"deepelementlab-clawcode\",\"task\":\"Install Clawcode\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Clawcode\" as a Claude Code skill from https://github.com/deepelementlab/clawcode. 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: ClawCode is claude code inspired implementation in python and Rust focused on agents and experience-based evolution, and is an Open-source coding-agent CLI for Anthropic, OpenAI, Gemini, DeepSeek, GLM, Kimit, Ollama, Codex, GitHub Models, and 200+ models via OpenAI-compatible APIs. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"deepelementlab-clawcode\",\"task\":\"Install Clawcode\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Clawcode\" from https://github.com/deepelementlab/clawcode 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: ClawCode is claude code inspired implementation in python and Rust focused on agents and experience-based evolution, and is an Open-source coding-agent CLI for Anthropic, OpenAI, Gemini, DeepSeek, GLM, Kimit, Ollama, Codex, GitHub Models, and 200+ models via OpenAI-compatible APIs. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"deepelementlab-clawcode\",\"task\":\"Install Clawcode\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/deepelementlab-clawcode/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/deepelementlab-clawcode"},"trust":{"score":73,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"162 GitHub stars","repoActivity":"162 stars, 49 forks","lastPushed":"3mo since push","license":"GPL-3.0","repository":"https://github.com/deepelementlab/clawcode","install":"npx skills add deepelementlab/clawcode","installSafety":"standard package or runtime install path","permissionSurface":"shell or command execution","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["agent-frameworks","multi-agent","orchestration","ai-agents","automation","clawcode"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 162 stars, 49 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","Documentation summary is thin","Stars/forks activity: 162 stars, 49 forks; issue activity unavailable in current metadata"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":73,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"3mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","High-risk permission hints: Shell or command execution","Quality score needs review","Documentation summary is thin","Stars/forks activity: 162 stars, 49 forks; issue activity unavailable in current metadata","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use Clawcode in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 73/100 Strong shortlist","Audit: 78/100 Needs review","Safety: 54/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"deepelementlab-clawcode (Clawcode)","install_command":"npx skills add deepelementlab/clawcode","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":"deepelementlab-clawcode","task":"Use Clawcode 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/deepelementlab-clawcode","api":"https://www.openagentskill.com/api/agent/skills/deepelementlab-clawcode","audit":"https://www.openagentskill.com/skills/deepelementlab-clawcode/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=deepelementlab-clawcode&task=Use%20Clawcode%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Clawcode%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Clawcode%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/deepelementlab-clawcode/install","manifest":"https://www.openagentskill.com/api/registry/manifest/deepelementlab-clawcode"}},"platforms":["Python","Multi-Agent","Claude Code","OpenAI Agents"],"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"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 deepelementlab/clawcode","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install deepelementlab-clawcode","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Clawcode\" agent skill from https://github.com/deepelementlab/clawcode. 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: ClawCode is claude code inspired implementation in python and Rust focused on agents and experience-based evolution, and is an Open-source coding-agent CLI for Anthropic, OpenAI, Gemini, DeepSeek, GLM, Kimit, Ollama, Codex, GitHub Models, and 200+ models via OpenAI-compatible APIs. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"deepelementlab-clawcode\",\"task\":\"Install Clawcode\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Clawcode\" as a Claude Code skill from https://github.com/deepelementlab/clawcode. 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: ClawCode is claude code inspired implementation in python and Rust focused on agents and experience-based evolution, and is an Open-source coding-agent CLI for Anthropic, OpenAI, Gemini, DeepSeek, GLM, Kimit, Ollama, Codex, GitHub Models, and 200+ models via OpenAI-compatible APIs. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"deepelementlab-clawcode\",\"task\":\"Install Clawcode\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Clawcode\" from https://github.com/deepelementlab/clawcode 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: ClawCode is claude code inspired implementation in python and Rust focused on agents and experience-based evolution, and is an Open-source coding-agent CLI for Anthropic, OpenAI, Gemini, DeepSeek, GLM, Kimit, Ollama, Codex, GitHub Models, and 200+ models via OpenAI-compatible APIs. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"deepelementlab-clawcode\",\"task\":\"Install Clawcode\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/deepelementlab/clawcode","github_repo":"deepelementlab/clawcode","version":"1.0.0","license":"GPL-3.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"deepelementlab/clawcode","recommendation_reasons":["Matches task terms: glm","Install handoff is available","Repository freshness signal is available","Registry match score 4"],"urls":{"web":"https://www.openagentskill.com/skills/deepelementlab-clawcode","api":"https://www.openagentskill.com/api/agent/skills/deepelementlab-clawcode","install_api":"https://www.openagentskill.com/api/skills/deepelementlab-clawcode/install","audit":"https://www.openagentskill.com/skills/deepelementlab-clawcode/audit","repository":"https://github.com/deepelementlab/clawcode"}},{"rank":10,"match_type":"related","match_score":4,"raw_match_score":29.2,"semantic_relevance":30,"slug":"shinpr-sub-agents-skills","name":"Sub Agents Skills","description":"A cross-LLM Agent Skill that routes tasks to multiple coding backends like Codex, Claude Code, Gemini, and others from compatible agent runtimes.","tagline":"Cross-LLM sub-agent orchestration as an Agent Skills. Route tasks to Codex, Claude Code, Grok, GLM, Kimi, Cursor, Gemini, or OpenCode from any compatible tool.","category":"coding-agents","tags":["sub-agents","orchestration","multi-agent","agent-skills","coding-agents"],"author":{"name":"shinpr","verified":false,"url":"https://github.com/shinpr"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"OpenAgentSkill auto-indexer","sourceDetail":"shinpr/sub-agents-skills","creatorName":"shinpr","creatorUrl":"https://github.com/shinpr","sourceUrl":"https://github.com/shinpr/sub-agents-skills","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/shinpr-sub-agents-skills#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":76,"forks":10,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":46.91},"quality":{"score":70,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"76","tone":"neutral"},{"label":"Freshness","value":"15d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":77,"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":48,"weight":0.13,"status":"warn","detail":"76 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":48,"weight":0.08,"status":"warn","detail":"76 stars, 10 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"15d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add shinpr/sub-agents-skills"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/shinpr/sub-agents-skills"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"warn","label":"GitHub adoption","detail":"76 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"76 stars, 10 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"15d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add shinpr/sub-agents-skills"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/shinpr/sub-agents-skills"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin","GitHub adoption: 76 GitHub stars","Stars/forks activity: 76 stars, 10 forks; issue activity unavailable in current metadata"],"evidence":{"stars":"76 GitHub stars","repoActivity":"76 stars, 10 forks","lastPushed":"15d since push","license":"MIT","repository":"https://github.com/shinpr/sub-agents-skills","install":"npx skills add shinpr/sub-agents-skills","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add shinpr/sub-agents-skills","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","15d since push"]},"agentCompatibility":["Python","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","GitHub adoption: 76 GitHub stars","Stars/forks activity: 76 stars, 10 forks; issue activity unavailable in current metadata"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["coding-agents","sub-agents","orchestration","multi-agent","agent-skills","Python"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Documentation summary is thin","GitHub adoption: 76 GitHub stars","Stars/forks activity: 76 stars, 10 forks; issue activity unavailable in current metadata"]},"safety":{"score":70,"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","70/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["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","70/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"workflow-automation","title":"Workflow automation"},{"slug":"web-scraping","title":"Web scraping"}]},"applicableAgents":["Claude Code","OpenAI Agents","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add shinpr/sub-agents-skills","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":76,"starsLabel":"76","forks":10,"license":"MIT","qualityScore":70,"trustScore":77,"auditScore":82},"maintenance":{"status":"fresh","label":"15d since push","daysSincePush":15,"lastPushedAt":"2026-08-07T13:33:40+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Quality score needs review","Documentation summary is thin","GitHub adoption: 76 GitHub stars","Stars/forks activity: 76 stars, 10 forks; issue activity unavailable in current metadata","Needs review"]},"coverageTags":["Coding","Coding agents","coding-agents","sub-agents","orchestration","multi-agent","agent-skills","Python"]},"audit":{"audit_score":82,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Documentation summary is thin","GitHub adoption: 76 GitHub stars","Stars/forks activity: 76 stars, 10 forks; issue activity unavailable in current metadata"]},"decision":{"readiness_score":69,"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":"shinpr-sub-agents-skills","name":"Sub Agents Skills","description":"A cross-LLM Agent Skill that routes tasks to multiple coding backends like Codex, Claude Code, Gemini, and others from compatible agent runtimes.","category":"coding-agents","url":"https://www.openagentskill.com/skills/shinpr-sub-agents-skills","repository":"https://github.com/shinpr/sub-agents-skills","github_repo":"shinpr/sub-agents-skills"},"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Move data between tools","Transform files"],"suited_agents":["Python","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add shinpr/sub-agents-skills","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install shinpr-sub-agents-skills"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Sub Agents Skills\" agent skill from https://github.com/shinpr/sub-agents-skills. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A cross-LLM Agent Skill that routes tasks to multiple coding backends like Codex, Claude Code, Gemini, and others from compatible agent runtimes. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"shinpr-sub-agents-skills\",\"task\":\"Install Sub Agents Skills\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Sub Agents Skills\" as a Claude Code skill from https://github.com/shinpr/sub-agents-skills. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A cross-LLM Agent Skill that routes tasks to multiple coding backends like Codex, Claude Code, Gemini, and others from compatible agent runtimes. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"shinpr-sub-agents-skills\",\"task\":\"Install Sub Agents Skills\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Sub Agents Skills\" from https://github.com/shinpr/sub-agents-skills into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A cross-LLM Agent Skill that routes tasks to multiple coding backends like Codex, Claude Code, Gemini, and others from compatible agent runtimes. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"shinpr-sub-agents-skills\",\"task\":\"Install Sub Agents Skills\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/shinpr-sub-agents-skills/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/shinpr-sub-agents-skills"},"trust":{"score":77,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"76 GitHub stars","repoActivity":"76 stars, 10 forks","lastPushed":"15d since push","license":"MIT","repository":"https://github.com/shinpr/sub-agents-skills","install":"npx skills add shinpr/sub-agents-skills","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["coding-agents","sub-agents","orchestration","multi-agent","agent-skills","Python"],"known_risks":["Quality score needs review","Documentation summary is thin","GitHub adoption: 76 GitHub stars","Stars/forks activity: 76 stars, 10 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":82,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Documentation summary is thin","GitHub adoption: 76 GitHub stars","Stars/forks activity: 76 stars, 10 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":70,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"15d 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","Documentation summary is thin","GitHub adoption: 76 GitHub stars","Stars/forks activity: 76 stars, 10 forks; issue activity unavailable in current metadata","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use Sub Agents Skills in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 77/100 Strong shortlist","Audit: 82/100 Needs review","Safety: 70/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"shinpr-sub-agents-skills (Sub Agents Skills)","install_command":"npx skills add shinpr/sub-agents-skills","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":"shinpr-sub-agents-skills","task":"Use Sub Agents Skills in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/shinpr-sub-agents-skills","api":"https://www.openagentskill.com/api/agent/skills/shinpr-sub-agents-skills","audit":"https://www.openagentskill.com/skills/shinpr-sub-agents-skills/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=shinpr-sub-agents-skills&task=Use%20Sub%20Agents%20Skills%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Sub%20Agents%20Skills%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Sub%20Agents%20Skills%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/shinpr-sub-agents-skills/install","manifest":"https://www.openagentskill.com/api/registry/manifest/shinpr-sub-agents-skills"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"shinpr-sub-agents-skills","name":"Sub Agents Skills","description":"A cross-LLM Agent Skill that routes tasks to multiple coding backends like Codex, Claude Code, Gemini, and others from compatible agent runtimes.","category":"coding-agents","url":"https://www.openagentskill.com/skills/shinpr-sub-agents-skills","repository":"https://github.com/shinpr/sub-agents-skills","github_repo":"shinpr/sub-agents-skills"},"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Move data between tools","Transform files"],"suited_agents":["Python","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add shinpr/sub-agents-skills","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install shinpr-sub-agents-skills"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Sub Agents Skills\" agent skill from https://github.com/shinpr/sub-agents-skills. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A cross-LLM Agent Skill that routes tasks to multiple coding backends like Codex, Claude Code, Gemini, and others from compatible agent runtimes. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"shinpr-sub-agents-skills\",\"task\":\"Install Sub Agents Skills\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Sub Agents Skills\" as a Claude Code skill from https://github.com/shinpr/sub-agents-skills. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A cross-LLM Agent Skill that routes tasks to multiple coding backends like Codex, Claude Code, Gemini, and others from compatible agent runtimes. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"shinpr-sub-agents-skills\",\"task\":\"Install Sub Agents Skills\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Sub Agents Skills\" from https://github.com/shinpr/sub-agents-skills into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A cross-LLM Agent Skill that routes tasks to multiple coding backends like Codex, Claude Code, Gemini, and others from compatible agent runtimes. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"shinpr-sub-agents-skills\",\"task\":\"Install Sub Agents Skills\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/shinpr-sub-agents-skills/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/shinpr-sub-agents-skills"},"trust":{"score":77,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"76 GitHub stars","repoActivity":"76 stars, 10 forks","lastPushed":"15d since push","license":"MIT","repository":"https://github.com/shinpr/sub-agents-skills","install":"npx skills add shinpr/sub-agents-skills","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["coding-agents","sub-agents","orchestration","multi-agent","agent-skills","Python"],"known_risks":["Quality score needs review","Documentation summary is thin","GitHub adoption: 76 GitHub stars","Stars/forks activity: 76 stars, 10 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":82,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Documentation summary is thin","GitHub adoption: 76 GitHub stars","Stars/forks activity: 76 stars, 10 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":70,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"15d 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","Documentation summary is thin","GitHub adoption: 76 GitHub stars","Stars/forks activity: 76 stars, 10 forks; issue activity unavailable in current metadata","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use Sub Agents Skills in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 77/100 Strong shortlist","Audit: 82/100 Needs review","Safety: 70/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"shinpr-sub-agents-skills (Sub Agents Skills)","install_command":"npx skills add shinpr/sub-agents-skills","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":"shinpr-sub-agents-skills","task":"Use Sub Agents Skills in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/shinpr-sub-agents-skills","api":"https://www.openagentskill.com/api/agent/skills/shinpr-sub-agents-skills","audit":"https://www.openagentskill.com/skills/shinpr-sub-agents-skills/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=shinpr-sub-agents-skills&task=Use%20Sub%20Agents%20Skills%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Sub%20Agents%20Skills%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Sub%20Agents%20Skills%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/shinpr-sub-agents-skills/install","manifest":"https://www.openagentskill.com/api/registry/manifest/shinpr-sub-agents-skills"}},"platforms":["Python","Claude Code","OpenAI Agents"],"use_cases":[{"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"},{"slug":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"}],"install":"npx skills add shinpr/sub-agents-skills","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install shinpr-sub-agents-skills","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Sub Agents Skills\" agent skill from https://github.com/shinpr/sub-agents-skills. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A cross-LLM Agent Skill that routes tasks to multiple coding backends like Codex, Claude Code, Gemini, and others from compatible agent runtimes. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"shinpr-sub-agents-skills\",\"task\":\"Install Sub Agents Skills\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Sub Agents Skills\" as a Claude Code skill from https://github.com/shinpr/sub-agents-skills. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A cross-LLM Agent Skill that routes tasks to multiple coding backends like Codex, Claude Code, Gemini, and others from compatible agent runtimes. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"shinpr-sub-agents-skills\",\"task\":\"Install Sub Agents Skills\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Sub Agents Skills\" from https://github.com/shinpr/sub-agents-skills into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A cross-LLM Agent Skill that routes tasks to multiple coding backends like Codex, Claude Code, Gemini, and others from compatible agent runtimes. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"shinpr-sub-agents-skills\",\"task\":\"Install Sub Agents Skills\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/shinpr/sub-agents-skills","github_repo":"shinpr/sub-agents-skills","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"shinpr/sub-agents-skills","recommendation_reasons":["Matches task terms: glm","Install handoff is available","Repository freshness signal is available","Registry match score 4"],"urls":{"web":"https://www.openagentskill.com/skills/shinpr-sub-agents-skills","api":"https://www.openagentskill.com/api/agent/skills/shinpr-sub-agents-skills","install_api":"https://www.openagentskill.com/api/skills/shinpr-sub-agents-skills/install","audit":"https://www.openagentskill.com/skills/shinpr-sub-agents-skills/audit","repository":"https://github.com/shinpr/sub-agents-skills"}}],"meta":{"endpoint":"/api/skills/search","canonical_agent_endpoint":"/api/agent/resolve","lookup_intent":false,"exact_match_found":true,"match_counts":{"exact":1,"near":2,"related":7},"no_match_message":null,"safety_policy":"Blocked candidates are excluded by default. Pass include_blocked=true only for manual audit workflows.","agent_friendly":true,"api_version":"1.0","generated_at":"2026-08-22T21:02:29.800Z"}}