{"query":"Grasp MultiObject","filters":{"category":null,"platform":null,"track":null,"safety":null,"include_blocked":false,"min_stars":0},"total":7,"skills":[{"rank":1,"match_type":"related","match_score":15,"raw_match_score":109.9,"semantic_relevance":30,"slug":"robotgradient-grasp-diffusion","name":"Grasp Diffusion","description":"Pytorch implementation of diffusion models on Lie Groups for 6D grasp pose generation https://sites.google.com/view/se3dif/home","tagline":"Pytorch implementation of diffusion models on Lie Groups for 6D grasp pose generation https://sites.google.com/view/se3dif/home","category":"robotics-iot","tags":["robotics","automation","robotics-iot","deep-learning","diffusion","diffusion-models","grasping","lie-groups","jupyter notebook","github"],"author":{"name":"robotgradient","verified":false,"url":"https://github.com/robotgradient"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"robotgradient/grasp_diffusion","creatorName":"robotgradient","creatorUrl":"https://github.com/robotgradient","sourceUrl":"https://github.com/robotgradient/grasp_diffusion","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/robotgradient-grasp-diffusion#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":352,"forks":38,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":36.53},"quality":{"score":46,"tier":"review","label":"Needs review","summary":"Inspect the repository carefully before adding it to an agent workflow.","signals":[{"label":"GitHub stars","value":"352","tone":"neutral"},{"label":"Freshness","value":"2y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":70,"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":"352 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"352 stars, 38 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":22,"weight":0.14,"status":"fail","detail":"2y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"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 robotgradient/grasp_diffusion"},{"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/robotgradient/grasp_diffusion"},{"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":"352 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"352 stars, 38 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"2y since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add robotgradient/grasp_diffusion"},{"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/robotgradient/grasp_diffusion"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Install command has no obvious high-risk pattern"],"warnings":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 352 stars, 38 forks; issue activity unavailable in current metadata","Recent maintenance: 2y since push"],"evidence":{"stars":"352 GitHub stars","repoActivity":"352 stars, 38 forks","lastPushed":"2y since push","license":"MIT","repository":"https://github.com/robotgradient/grasp_diffusion","install":"npx skills add robotgradient/grasp_diffusion","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 robotgradient/grasp_diffusion","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2y since push"]},"agentCompatibility":["Jupyter Notebook","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 352 stars, 38 forks; issue activity unavailable in current metadata","Recent maintenance: 2y since push"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["robotics-iot","robotics","automation","deep-learning","diffusion","diffusion-models"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 352 stars, 38 forks; issue activity unavailable in current metadata","Recent maintenance: 2y since push"]},"safety":{"score":50,"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","50/100 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","50/100 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","Jupyter Notebook"],"install":{"ready":true,"command":"npx skills add robotgradient/grasp_diffusion","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":352,"starsLabel":"352","forks":38,"license":"MIT","qualityScore":46,"trustScore":70,"auditScore":62},"maintenance":{"status":"stale","label":"2y since push","daysSincePush":780,"lastPushedAt":"2024-07-03T12:13:51+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","Stars/forks activity: 352 stars, 38 forks; issue activity unavailable in current metadata"]},"coverageTags":["Coding","GitHub automation","robotics-iot","robotics","automation","deep-learning","diffusion","diffusion-models"]},"audit":{"audit_score":62,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Stars/forks activity: 352 stars, 38 forks; issue activity unavailable in current metadata"]},"decision":{"readiness_score":36,"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":"robotgradient-grasp-diffusion","name":"Grasp Diffusion","description":"Pytorch implementation of diffusion models on Lie Groups for 6D grasp pose generation https://sites.google.com/view/se3dif/home","category":"robotics-iot","url":"https://www.openagentskill.com/skills/robotgradient-grasp-diffusion","repository":"https://github.com/robotgradient/grasp_diffusion","github_repo":"robotgradient/grasp_diffusion"},"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":["Jupyter Notebook","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add robotgradient/grasp_diffusion","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 robotgradient-grasp-diffusion"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Grasp Diffusion\" agent skill from https://github.com/robotgradient/grasp_diffusion. 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: Pytorch implementation of diffusion models on Lie Groups for 6D grasp pose generation https://sites.google.com/view/se3dif/home 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\":\"robotgradient-grasp-diffusion\",\"task\":\"Install Grasp Diffusion\",\"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 \"Grasp Diffusion\" as a Claude Code skill from https://github.com/robotgradient/grasp_diffusion. 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: Pytorch implementation of diffusion models on Lie Groups for 6D grasp pose generation https://sites.google.com/view/se3dif/home 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\":\"robotgradient-grasp-diffusion\",\"task\":\"Install Grasp Diffusion\",\"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 \"Grasp Diffusion\" from https://github.com/robotgradient/grasp_diffusion 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: Pytorch implementation of diffusion models on Lie Groups for 6D grasp pose generation https://sites.google.com/view/se3dif/home 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\":\"robotgradient-grasp-diffusion\",\"task\":\"Install Grasp Diffusion\",\"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/robotgradient-grasp-diffusion/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/robotgradient-grasp-diffusion"},"trust":{"score":70,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"352 GitHub stars","repoActivity":"352 stars, 38 forks","lastPushed":"2y since push","license":"MIT","repository":"https://github.com/robotgradient/grasp_diffusion","install":"npx skills add robotgradient/grasp_diffusion","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":["robotics-iot","robotics","automation","deep-learning","diffusion","diffusion-models"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 352 stars, 38 forks; issue activity unavailable in current metadata","Recent maintenance: 2y since push"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":62,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Stars/forks activity: 352 stars, 38 forks; issue activity unavailable in current metadata","Recent maintenance: 2y since push"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":46,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"2y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Documentation summary is thin","Repository appears stale","Quality score needs review","Stars/forks activity: 352 stars, 38 forks; issue activity unavailable in current metadata"],"agent_contract":{"task_input":"Use Grasp Diffusion 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: 70/100 Manual review","Audit: 62/100 Needs review","Safety: 50/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"robotgradient-grasp-diffusion (Grasp Diffusion)","install_command":"npx skills add robotgradient/grasp_diffusion","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":"robotgradient-grasp-diffusion","task":"Use Grasp Diffusion 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/robotgradient-grasp-diffusion","api":"https://www.openagentskill.com/api/agent/skills/robotgradient-grasp-diffusion","audit":"https://www.openagentskill.com/skills/robotgradient-grasp-diffusion/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=robotgradient-grasp-diffusion&task=Use%20Grasp%20Diffusion%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Grasp%20Diffusion%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Grasp%20Diffusion%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/robotgradient-grasp-diffusion/install","manifest":"https://www.openagentskill.com/api/registry/manifest/robotgradient-grasp-diffusion"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"robotgradient-grasp-diffusion","name":"Grasp Diffusion","description":"Pytorch implementation of diffusion models on Lie Groups for 6D grasp pose generation https://sites.google.com/view/se3dif/home","category":"robotics-iot","url":"https://www.openagentskill.com/skills/robotgradient-grasp-diffusion","repository":"https://github.com/robotgradient/grasp_diffusion","github_repo":"robotgradient/grasp_diffusion"},"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":["Jupyter Notebook","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add robotgradient/grasp_diffusion","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 robotgradient-grasp-diffusion"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Grasp Diffusion\" agent skill from https://github.com/robotgradient/grasp_diffusion. 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: Pytorch implementation of diffusion models on Lie Groups for 6D grasp pose generation https://sites.google.com/view/se3dif/home 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\":\"robotgradient-grasp-diffusion\",\"task\":\"Install Grasp Diffusion\",\"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 \"Grasp Diffusion\" as a Claude Code skill from https://github.com/robotgradient/grasp_diffusion. 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: Pytorch implementation of diffusion models on Lie Groups for 6D grasp pose generation https://sites.google.com/view/se3dif/home 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\":\"robotgradient-grasp-diffusion\",\"task\":\"Install Grasp Diffusion\",\"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 \"Grasp Diffusion\" from https://github.com/robotgradient/grasp_diffusion 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: Pytorch implementation of diffusion models on Lie Groups for 6D grasp pose generation https://sites.google.com/view/se3dif/home 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\":\"robotgradient-grasp-diffusion\",\"task\":\"Install Grasp Diffusion\",\"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/robotgradient-grasp-diffusion/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/robotgradient-grasp-diffusion"},"trust":{"score":70,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"352 GitHub stars","repoActivity":"352 stars, 38 forks","lastPushed":"2y since push","license":"MIT","repository":"https://github.com/robotgradient/grasp_diffusion","install":"npx skills add robotgradient/grasp_diffusion","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":["robotics-iot","robotics","automation","deep-learning","diffusion","diffusion-models"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 352 stars, 38 forks; issue activity unavailable in current metadata","Recent maintenance: 2y since push"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":62,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Stars/forks activity: 352 stars, 38 forks; issue activity unavailable in current metadata","Recent maintenance: 2y since push"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":46,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"2y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Documentation summary is thin","Repository appears stale","Quality score needs review","Stars/forks activity: 352 stars, 38 forks; issue activity unavailable in current metadata"],"agent_contract":{"task_input":"Use Grasp Diffusion 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: 70/100 Manual review","Audit: 62/100 Needs review","Safety: 50/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"robotgradient-grasp-diffusion (Grasp Diffusion)","install_command":"npx skills add robotgradient/grasp_diffusion","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":"robotgradient-grasp-diffusion","task":"Use Grasp Diffusion 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/robotgradient-grasp-diffusion","api":"https://www.openagentskill.com/api/agent/skills/robotgradient-grasp-diffusion","audit":"https://www.openagentskill.com/skills/robotgradient-grasp-diffusion/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=robotgradient-grasp-diffusion&task=Use%20Grasp%20Diffusion%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Grasp%20Diffusion%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Grasp%20Diffusion%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/robotgradient-grasp-diffusion/install","manifest":"https://www.openagentskill.com/api/registry/manifest/robotgradient-grasp-diffusion"}},"platforms":["Jupyter Notebook","Robotics"],"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 robotgradient/grasp_diffusion","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 robotgradient-grasp-diffusion","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 \"Grasp Diffusion\" agent skill from https://github.com/robotgradient/grasp_diffusion. 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: Pytorch implementation of diffusion models on Lie Groups for 6D grasp pose generation https://sites.google.com/view/se3dif/home 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\":\"robotgradient-grasp-diffusion\",\"task\":\"Install Grasp Diffusion\",\"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 \"Grasp Diffusion\" as a Claude Code skill from https://github.com/robotgradient/grasp_diffusion. 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: Pytorch implementation of diffusion models on Lie Groups for 6D grasp pose generation https://sites.google.com/view/se3dif/home 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\":\"robotgradient-grasp-diffusion\",\"task\":\"Install Grasp Diffusion\",\"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 \"Grasp Diffusion\" from https://github.com/robotgradient/grasp_diffusion 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: Pytorch implementation of diffusion models on Lie Groups for 6D grasp pose generation https://sites.google.com/view/se3dif/home 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\":\"robotgradient-grasp-diffusion\",\"task\":\"Install Grasp Diffusion\",\"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/robotgradient/grasp_diffusion","github_repo":"robotgradient/grasp_diffusion","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"robotgradient/grasp_diffusion","recommendation_reasons":["Matches task terms: grasp","Install handoff is available","Repository freshness signal is available","Registry match score 15"],"urls":{"web":"https://www.openagentskill.com/skills/robotgradient-grasp-diffusion","api":"https://www.openagentskill.com/api/agent/skills/robotgradient-grasp-diffusion","install_api":"https://www.openagentskill.com/api/skills/robotgradient-grasp-diffusion/install","audit":"https://www.openagentskill.com/skills/robotgradient-grasp-diffusion/audit","repository":"https://github.com/robotgradient/grasp_diffusion"}},{"rank":2,"match_type":"related","match_score":8,"raw_match_score":56.1,"semantic_relevance":30,"slug":"atenpas-gpd","name":"Gpd","description":"Detect 6-DOF grasp poses in point clouds ","tagline":"Detect 6-DOF grasp poses in point clouds ","category":"robotics-iot","tags":["robotics","automation","robotics-iot","grasping","ros","c++","github"],"author":{"name":"atenpas","verified":false,"url":"https://github.com/atenpas"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"atenpas/gpd","creatorName":"atenpas","creatorUrl":"https://github.com/atenpas","sourceUrl":"https://github.com/atenpas/gpd","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/atenpas-gpd#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":748,"forks":247,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":38.82},"quality":{"score":49,"tier":"review","label":"Needs review","summary":"Inspect the repository carefully before adding it to an agent workflow.","signals":[{"label":"GitHub stars","value":"748","tone":"positive"},{"label":"Freshness","value":"5y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"BSD-2-Clause","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":71,"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":76,"weight":0.13,"status":"info","detail":"748 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":71,"weight":0.08,"status":"info","detail":"748 stars, 247 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":22,"weight":0.14,"status":"fail","detail":"5y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"BSD-2-Clause"},{"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 atenpas/gpd"},{"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/atenpas/gpd"},{"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":"748 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"748 stars, 247 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"5y since push"},{"status":"pass","label":"License clarity","detail":"BSD-2-Clause"},{"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 atenpas/gpd"},{"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/atenpas/gpd"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 5y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"748 GitHub stars","repoActivity":"748 stars, 247 forks","lastPushed":"5y since push","license":"BSD-2-Clause","repository":"https://github.com/atenpas/gpd","install":"npx skills add atenpas/gpd","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 atenpas/gpd","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","5y since push"]},"agentCompatibility":["C++","Robotics","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: 5y 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":["robotics-iot","robotics","automation","grasping","ros","c++"],"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: 5y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":51,"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","51/100 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","51/100 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","C++"],"install":{"ready":true,"command":"npx skills add atenpas/gpd","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":748,"starsLabel":"748","forks":247,"license":"BSD-2-Clause","qualityScore":49,"trustScore":71,"auditScore":63},"maintenance":{"status":"stale","label":"5y since push","daysSincePush":1664,"lastPushedAt":"2022-01-31T16:25:32+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: 5y since push"]},"coverageTags":["Coding","GitHub automation","robotics-iot","robotics","automation","grasping","ros","c++"]},"audit":{"audit_score":63,"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: 5y since push"]},"decision":{"readiness_score":51,"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","teams that value GitHub adoption signals"],"risks":["Repository looks stale","No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one 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":"atenpas-gpd","name":"Gpd","description":"Detect 6-DOF grasp poses in point clouds ","category":"robotics-iot","url":"https://www.openagentskill.com/skills/atenpas-gpd","repository":"https://github.com/atenpas/gpd","github_repo":"atenpas/gpd"},"suited_tasks":["GitHub automation workflows","general agent builders","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["C++","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add atenpas/gpd","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 atenpas-gpd"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Gpd\" agent skill from https://github.com/atenpas/gpd. 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: Detect 6-DOF grasp poses in point clouds 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\":\"atenpas-gpd\",\"task\":\"Install Gpd\",\"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 \"Gpd\" as a Claude Code skill from https://github.com/atenpas/gpd. 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: Detect 6-DOF grasp poses in point clouds 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\":\"atenpas-gpd\",\"task\":\"Install Gpd\",\"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 \"Gpd\" from https://github.com/atenpas/gpd 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: Detect 6-DOF grasp poses in point clouds 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\":\"atenpas-gpd\",\"task\":\"Install Gpd\",\"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/atenpas-gpd/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/atenpas-gpd"},"trust":{"score":71,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"748 GitHub stars","repoActivity":"748 stars, 247 forks","lastPushed":"5y since push","license":"BSD-2-Clause","repository":"https://github.com/atenpas/gpd","install":"npx skills add atenpas/gpd","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":["robotics-iot","robotics","automation","grasping","ros","c++"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 5y 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":63,"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: 5y 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":49,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"5y 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: 5y since push"],"agent_contract":{"task_input":"Use Gpd 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: 71/100 Manual review","Audit: 63/100 Needs review","Safety: 51/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"atenpas-gpd (Gpd)","install_command":"npx skills add atenpas/gpd","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":"atenpas-gpd","task":"Use Gpd 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/atenpas-gpd","api":"https://www.openagentskill.com/api/agent/skills/atenpas-gpd","audit":"https://www.openagentskill.com/skills/atenpas-gpd/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=atenpas-gpd&task=Use%20Gpd%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Gpd%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Gpd%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/atenpas-gpd/install","manifest":"https://www.openagentskill.com/api/registry/manifest/atenpas-gpd"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"atenpas-gpd","name":"Gpd","description":"Detect 6-DOF grasp poses in point clouds ","category":"robotics-iot","url":"https://www.openagentskill.com/skills/atenpas-gpd","repository":"https://github.com/atenpas/gpd","github_repo":"atenpas/gpd"},"suited_tasks":["GitHub automation workflows","general agent builders","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["C++","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add atenpas/gpd","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 atenpas-gpd"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Gpd\" agent skill from https://github.com/atenpas/gpd. 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: Detect 6-DOF grasp poses in point clouds 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\":\"atenpas-gpd\",\"task\":\"Install Gpd\",\"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 \"Gpd\" as a Claude Code skill from https://github.com/atenpas/gpd. 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: Detect 6-DOF grasp poses in point clouds 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\":\"atenpas-gpd\",\"task\":\"Install Gpd\",\"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 \"Gpd\" from https://github.com/atenpas/gpd 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: Detect 6-DOF grasp poses in point clouds 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\":\"atenpas-gpd\",\"task\":\"Install Gpd\",\"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/atenpas-gpd/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/atenpas-gpd"},"trust":{"score":71,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"748 GitHub stars","repoActivity":"748 stars, 247 forks","lastPushed":"5y since push","license":"BSD-2-Clause","repository":"https://github.com/atenpas/gpd","install":"npx skills add atenpas/gpd","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":["robotics-iot","robotics","automation","grasping","ros","c++"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 5y 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":63,"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: 5y 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":49,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"5y 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: 5y since push"],"agent_contract":{"task_input":"Use Gpd 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: 71/100 Manual review","Audit: 63/100 Needs review","Safety: 51/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"atenpas-gpd (Gpd)","install_command":"npx skills add atenpas/gpd","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":"atenpas-gpd","task":"Use Gpd 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/atenpas-gpd","api":"https://www.openagentskill.com/api/agent/skills/atenpas-gpd","audit":"https://www.openagentskill.com/skills/atenpas-gpd/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=atenpas-gpd&task=Use%20Gpd%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Gpd%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Gpd%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/atenpas-gpd/install","manifest":"https://www.openagentskill.com/api/registry/manifest/atenpas-gpd"}},"platforms":["C++","Robotics"],"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 atenpas/gpd","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 atenpas-gpd","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 \"Gpd\" agent skill from https://github.com/atenpas/gpd. 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: Detect 6-DOF grasp poses in point clouds 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\":\"atenpas-gpd\",\"task\":\"Install Gpd\",\"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 \"Gpd\" as a Claude Code skill from https://github.com/atenpas/gpd. 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: Detect 6-DOF grasp poses in point clouds 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\":\"atenpas-gpd\",\"task\":\"Install Gpd\",\"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 \"Gpd\" from https://github.com/atenpas/gpd 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: Detect 6-DOF grasp poses in point clouds 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\":\"atenpas-gpd\",\"task\":\"Install Gpd\",\"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/atenpas/gpd","github_repo":"atenpas/gpd","version":"1.0.0","license":"BSD-2-Clause","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"atenpas/gpd","recommendation_reasons":["Matches task terms: grasp","Useful GitHub adoption: 748 stars","Install handoff is available","Repository freshness signal is available","Registry match score 8"],"urls":{"web":"https://www.openagentskill.com/skills/atenpas-gpd","api":"https://www.openagentskill.com/api/agent/skills/atenpas-gpd","install_api":"https://www.openagentskill.com/api/skills/atenpas-gpd/install","audit":"https://www.openagentskill.com/skills/atenpas-gpd/audit","repository":"https://github.com/atenpas/gpd"}},{"rank":3,"match_type":"related","match_score":7,"raw_match_score":55.5,"semantic_relevance":30,"slug":"dougsm-ggcnn","name":"Ggcnn","description":"Generative Grasping CNN from \"Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach\" (RSS 2018)","tagline":"Generative Grasping CNN from \"Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach\" (RSS 2018)","category":"robotics-iot","tags":["robotics","automation","robotics-iot","deep-learning","grasping","python","github"],"author":{"name":"dougsm","verified":false,"url":"https://github.com/dougsm"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"dougsm/ggcnn","creatorName":"dougsm","creatorUrl":"https://github.com/dougsm","sourceUrl":"https://github.com/dougsm/ggcnn","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/dougsm-ggcnn#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":622,"forks":153,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":38.26},"quality":{"score":48,"tier":"review","label":"Needs review","summary":"Inspect the repository carefully before adding it to an agent workflow.","signals":[{"label":"GitHub stars","value":"622","tone":"positive"},{"label":"Freshness","value":"6y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"BSD-3-Clause","tone":"neutral"}],"warnings":["Repository looks stale"]},"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":76,"weight":0.13,"status":"info","detail":"622 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":71,"weight":0.08,"status":"info","detail":"622 stars, 153 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":22,"weight":0.14,"status":"fail","detail":"6y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"BSD-3-Clause"},{"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 dougsm/ggcnn"},{"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/dougsm/ggcnn"},{"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":"622 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"622 stars, 153 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"6y since push"},{"status":"pass","label":"License clarity","detail":"BSD-3-Clause"},{"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 dougsm/ggcnn"},{"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/dougsm/ggcnn"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 6y since push"],"evidence":{"stars":"622 GitHub stars","repoActivity":"622 stars, 153 forks","lastPushed":"6y since push","license":"BSD-3-Clause","repository":"https://github.com/dougsm/ggcnn","install":"npx skills add dougsm/ggcnn","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 dougsm/ggcnn","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","6y since push"]},"agentCompatibility":["Python","Robotics","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: 6y since push"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["robotics-iot","robotics","automation","deep-learning","grasping","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":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 6y since push"]},"safety":{"score":52,"level":"avoid_auto_install","label":"Avoid automatic install","safety_tier":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","summary":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","auto_install_policy":"review","reasons":["Repository appears stale","52/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Repository appears stale"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","reasons":["Repository appears stale","52/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"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":"local-desktop","title":"Local desktop"},{"slug":"coding-agents","title":"Coding agents"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add dougsm/ggcnn","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":622,"starsLabel":"622","forks":153,"license":"BSD-3-Clause","qualityScore":48,"trustScore":73,"auditScore":64},"maintenance":{"status":"stale","label":"6y since push","daysSincePush":2224,"lastPushedAt":"2020-07-21T00:34:15+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 6y since push"]},"coverageTags":["Coding","GitHub automation","robotics-iot","robotics","automation","deep-learning","grasping","python"]},"audit":{"audit_score":64,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 6y since push"]},"decision":{"readiness_score":50,"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","teams that value GitHub adoption signals"],"risks":["Repository looks stale","No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one 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":"dougsm-ggcnn","name":"Ggcnn","description":"Generative Grasping CNN from \"Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach\" (RSS 2018)","category":"robotics-iot","url":"https://www.openagentskill.com/skills/dougsm-ggcnn","repository":"https://github.com/dougsm/ggcnn","github_repo":"dougsm/ggcnn"},"suited_tasks":["GitHub automation workflows","general agent builders","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Navigate local resources","Run repeatable desktop actions"],"suited_agents":["Python","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add dougsm/ggcnn","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 dougsm-ggcnn"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Ggcnn\" agent skill from https://github.com/dougsm/ggcnn. 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: Generative Grasping CNN from \"Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach\" (RSS 2018) 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\":\"dougsm-ggcnn\",\"task\":\"Install Ggcnn\",\"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 \"Ggcnn\" as a Claude Code skill from https://github.com/dougsm/ggcnn. 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: Generative Grasping CNN from \"Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach\" (RSS 2018) 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\":\"dougsm-ggcnn\",\"task\":\"Install Ggcnn\",\"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 \"Ggcnn\" from https://github.com/dougsm/ggcnn 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: Generative Grasping CNN from \"Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach\" (RSS 2018) 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\":\"dougsm-ggcnn\",\"task\":\"Install Ggcnn\",\"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/dougsm-ggcnn/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/dougsm-ggcnn"},"trust":{"score":73,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"622 GitHub stars","repoActivity":"622 stars, 153 forks","lastPushed":"6y since push","license":"BSD-3-Clause","repository":"https://github.com/dougsm/ggcnn","install":"npx skills add dougsm/ggcnn","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":["robotics-iot","robotics","automation","deep-learning","grasping","python"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 6y since push"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":64,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 6y since push"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":48,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"6y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Repository appears stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 6y since push"],"agent_contract":{"task_input":"Use Ggcnn 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: 64/100 Needs review","Safety: 52/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"dougsm-ggcnn (Ggcnn)","install_command":"npx skills add dougsm/ggcnn","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":"dougsm-ggcnn","task":"Use Ggcnn 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/dougsm-ggcnn","api":"https://www.openagentskill.com/api/agent/skills/dougsm-ggcnn","audit":"https://www.openagentskill.com/skills/dougsm-ggcnn/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=dougsm-ggcnn&task=Use%20Ggcnn%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Ggcnn%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Ggcnn%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/dougsm-ggcnn/install","manifest":"https://www.openagentskill.com/api/registry/manifest/dougsm-ggcnn"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"dougsm-ggcnn","name":"Ggcnn","description":"Generative Grasping CNN from \"Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach\" (RSS 2018)","category":"robotics-iot","url":"https://www.openagentskill.com/skills/dougsm-ggcnn","repository":"https://github.com/dougsm/ggcnn","github_repo":"dougsm/ggcnn"},"suited_tasks":["GitHub automation workflows","general agent builders","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Navigate local resources","Run repeatable desktop actions"],"suited_agents":["Python","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add dougsm/ggcnn","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 dougsm-ggcnn"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Ggcnn\" agent skill from https://github.com/dougsm/ggcnn. 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: Generative Grasping CNN from \"Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach\" (RSS 2018) 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\":\"dougsm-ggcnn\",\"task\":\"Install Ggcnn\",\"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 \"Ggcnn\" as a Claude Code skill from https://github.com/dougsm/ggcnn. 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: Generative Grasping CNN from \"Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach\" (RSS 2018) 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\":\"dougsm-ggcnn\",\"task\":\"Install Ggcnn\",\"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 \"Ggcnn\" from https://github.com/dougsm/ggcnn 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: Generative Grasping CNN from \"Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach\" (RSS 2018) 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\":\"dougsm-ggcnn\",\"task\":\"Install Ggcnn\",\"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/dougsm-ggcnn/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/dougsm-ggcnn"},"trust":{"score":73,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"622 GitHub stars","repoActivity":"622 stars, 153 forks","lastPushed":"6y since push","license":"BSD-3-Clause","repository":"https://github.com/dougsm/ggcnn","install":"npx skills add dougsm/ggcnn","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":["robotics-iot","robotics","automation","deep-learning","grasping","python"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 6y since push"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":64,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 6y since push"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":48,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"6y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Repository appears stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 6y since push"],"agent_contract":{"task_input":"Use Ggcnn 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: 64/100 Needs review","Safety: 52/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"dougsm-ggcnn (Ggcnn)","install_command":"npx skills add dougsm/ggcnn","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":"dougsm-ggcnn","task":"Use Ggcnn 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/dougsm-ggcnn","api":"https://www.openagentskill.com/api/agent/skills/dougsm-ggcnn","audit":"https://www.openagentskill.com/skills/dougsm-ggcnn/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=dougsm-ggcnn&task=Use%20Ggcnn%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Ggcnn%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Ggcnn%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/dougsm-ggcnn/install","manifest":"https://www.openagentskill.com/api/registry/manifest/dougsm-ggcnn"}},"platforms":["Python","Robotics"],"use_cases":[{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"install":"npx skills add dougsm/ggcnn","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 dougsm-ggcnn","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 \"Ggcnn\" agent skill from https://github.com/dougsm/ggcnn. 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: Generative Grasping CNN from \"Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach\" (RSS 2018) 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\":\"dougsm-ggcnn\",\"task\":\"Install Ggcnn\",\"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 \"Ggcnn\" as a Claude Code skill from https://github.com/dougsm/ggcnn. 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: Generative Grasping CNN from \"Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach\" (RSS 2018) 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\":\"dougsm-ggcnn\",\"task\":\"Install Ggcnn\",\"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 \"Ggcnn\" from https://github.com/dougsm/ggcnn 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: Generative Grasping CNN from \"Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach\" (RSS 2018) 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\":\"dougsm-ggcnn\",\"task\":\"Install Ggcnn\",\"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/dougsm/ggcnn","github_repo":"dougsm/ggcnn","version":"1.0.0","license":"BSD-3-Clause","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"dougsm/ggcnn","recommendation_reasons":["Matches task terms: grasp","Useful GitHub adoption: 622 stars","Install handoff is available","Repository freshness signal is available","Registry match score 7"],"urls":{"web":"https://www.openagentskill.com/skills/dougsm-ggcnn","api":"https://www.openagentskill.com/api/agent/skills/dougsm-ggcnn","install_api":"https://www.openagentskill.com/api/skills/dougsm-ggcnn/install","audit":"https://www.openagentskill.com/skills/dougsm-ggcnn/audit","repository":"https://github.com/dougsm/ggcnn"}},{"rank":4,"match_type":"related","match_score":7,"raw_match_score":54.4,"semantic_relevance":30,"slug":"facebookresearch-contactpose","name":"ContactPose","description":"Large dataset of hand-object contact, hand- and object-pose, and 2.9 M RGB-D grasp images.","tagline":"Large dataset of hand-object contact, hand- and object-pose, and 2.9 M RGB-D grasp images.","category":"robotics-iot","tags":["robotics","automation","robotics-iot","computer-vision","contact","dataset","grasps","hand-object-interaction","mano","rgb"],"author":{"name":"facebookresearch","verified":false,"url":"https://github.com/facebookresearch"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"facebookresearch/ContactPose","creatorName":"facebookresearch","creatorUrl":"https://github.com/facebookresearch","sourceUrl":"https://github.com/facebookresearch/ContactPose","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/facebookresearch-contactpose#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":421,"forks":36,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":37.08},"quality":{"score":46,"tier":"review","label":"Needs review","summary":"Inspect the repository carefully before adding it to an agent workflow.","signals":[{"label":"GitHub stars","value":"421","tone":"neutral"},{"label":"Freshness","value":"1y 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":72,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"421 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"421 stars, 36 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":38,"weight":0.14,"status":"fail","detail":"1y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"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 facebookresearch/ContactPose"},{"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/facebookresearch/ContactPose"},{"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":"421 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"421 stars, 36 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"1y 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 facebookresearch/ContactPose"},{"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/facebookresearch/ContactPose"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Install command has no obvious high-risk pattern"],"warnings":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 421 stars, 36 forks; issue activity unavailable in current metadata","Recent maintenance: 1y since push"],"evidence":{"stars":"421 GitHub stars","repoActivity":"421 stars, 36 forks","lastPushed":"1y since push","license":"MIT","repository":"https://github.com/facebookresearch/ContactPose","install":"npx skills add facebookresearch/ContactPose","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 facebookresearch/ContactPose","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","1y since push"]},"agentCompatibility":["Jupyter Notebook","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 421 stars, 36 forks; issue activity unavailable in current metadata","Recent maintenance: 1y since push"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["robotics-iot","robotics","automation","computer-vision","contact","dataset"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 421 stars, 36 forks; issue activity unavailable in current metadata","Recent maintenance: 1y since push"]},"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":["Documentation summary is thin","53/100 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","53/100 agent safety score"]},"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"Research agents","description":"I need my agent to research a topic, compare sources, and produce a concise report.","useCases":[{"slug":"research-agents","title":"Research agents"},{"slug":"multimodal-media","title":"Multimodal media"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Jupyter Notebook"],"install":{"ready":true,"command":"npx skills add facebookresearch/ContactPose","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":421,"starsLabel":"421","forks":36,"license":"MIT","qualityScore":46,"trustScore":72,"auditScore":65},"maintenance":{"status":"stale","label":"1y since push","daysSincePush":473,"lastPushedAt":"2025-05-07T01:49:24+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","Stars/forks activity: 421 stars, 36 forks; issue activity unavailable in current metadata"]},"coverageTags":["Research","Research agents","robotics-iot","robotics","automation","computer-vision","contact","dataset"]},"audit":{"audit_score":65,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Stars/forks activity: 421 stars, 36 forks; issue activity unavailable in current metadata"]},"decision":{"readiness_score":36,"readiness_label":"Needs manual review","headline":"Needs validation for Research agents","role":"Needs validation","primary_fit":"Research agents","best_for":["Research agents workflows","general agent builders","builders willing to evaluate younger projects"],"risks":["Repository looks stale","No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Research agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"facebookresearch-contactpose","name":"ContactPose","description":"Large dataset of hand-object contact, hand- and object-pose, and 2.9 M RGB-D grasp images.","category":"robotics-iot","url":"https://www.openagentskill.com/skills/facebookresearch-contactpose","repository":"https://github.com/facebookresearch/ContactPose","github_repo":"facebookresearch/ContactPose"},"suited_tasks":["Research agents workflows","general agent builders","builders willing to evaluate younger projects","Search sources","Extract claims","Synthesize findings","Read media metadata","Convert formats"],"suited_agents":["Jupyter Notebook","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add facebookresearch/ContactPose","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 facebookresearch-contactpose"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"ContactPose\" agent skill from https://github.com/facebookresearch/ContactPose. 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: Large dataset of hand-object contact, hand- and object-pose, and 2.9 M RGB-D grasp images. 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\":\"facebookresearch-contactpose\",\"task\":\"Install ContactPose\",\"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 \"ContactPose\" as a Claude Code skill from https://github.com/facebookresearch/ContactPose. 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: Large dataset of hand-object contact, hand- and object-pose, and 2.9 M RGB-D grasp images. 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\":\"facebookresearch-contactpose\",\"task\":\"Install ContactPose\",\"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 \"ContactPose\" from https://github.com/facebookresearch/ContactPose 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: Large dataset of hand-object contact, hand- and object-pose, and 2.9 M RGB-D grasp images. 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\":\"facebookresearch-contactpose\",\"task\":\"Install ContactPose\",\"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/facebookresearch-contactpose/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/facebookresearch-contactpose"},"trust":{"score":72,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"421 GitHub stars","repoActivity":"421 stars, 36 forks","lastPushed":"1y since push","license":"MIT","repository":"https://github.com/facebookresearch/ContactPose","install":"npx skills add facebookresearch/ContactPose","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":["robotics-iot","robotics","automation","computer-vision","contact","dataset"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 421 stars, 36 forks; issue activity unavailable in current metadata","Recent maintenance: 1y since push"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":65,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Stars/forks activity: 421 stars, 36 forks; issue activity unavailable in current metadata","Recent maintenance: 1y since push"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":46,"label":"Needs review"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"1y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Documentation summary is thin","Repository appears stale","Quality score needs review","Stars/forks activity: 421 stars, 36 forks; issue activity unavailable in current metadata"],"agent_contract":{"task_input":"Use ContactPose in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 72/100 Strong shortlist","Audit: 65/100 Needs review","Safety: 53/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"facebookresearch-contactpose (ContactPose)","install_command":"npx skills add facebookresearch/ContactPose","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":"facebookresearch-contactpose","task":"Use ContactPose 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/facebookresearch-contactpose","api":"https://www.openagentskill.com/api/agent/skills/facebookresearch-contactpose","audit":"https://www.openagentskill.com/skills/facebookresearch-contactpose/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=facebookresearch-contactpose&task=Use%20ContactPose%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20ContactPose%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20ContactPose%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/facebookresearch-contactpose/install","manifest":"https://www.openagentskill.com/api/registry/manifest/facebookresearch-contactpose"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"facebookresearch-contactpose","name":"ContactPose","description":"Large dataset of hand-object contact, hand- and object-pose, and 2.9 M RGB-D grasp images.","category":"robotics-iot","url":"https://www.openagentskill.com/skills/facebookresearch-contactpose","repository":"https://github.com/facebookresearch/ContactPose","github_repo":"facebookresearch/ContactPose"},"suited_tasks":["Research agents workflows","general agent builders","builders willing to evaluate younger projects","Search sources","Extract claims","Synthesize findings","Read media metadata","Convert formats"],"suited_agents":["Jupyter Notebook","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add facebookresearch/ContactPose","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 facebookresearch-contactpose"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"ContactPose\" agent skill from https://github.com/facebookresearch/ContactPose. 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: Large dataset of hand-object contact, hand- and object-pose, and 2.9 M RGB-D grasp images. 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\":\"facebookresearch-contactpose\",\"task\":\"Install ContactPose\",\"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 \"ContactPose\" as a Claude Code skill from https://github.com/facebookresearch/ContactPose. 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: Large dataset of hand-object contact, hand- and object-pose, and 2.9 M RGB-D grasp images. 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\":\"facebookresearch-contactpose\",\"task\":\"Install ContactPose\",\"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 \"ContactPose\" from https://github.com/facebookresearch/ContactPose 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: Large dataset of hand-object contact, hand- and object-pose, and 2.9 M RGB-D grasp images. 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\":\"facebookresearch-contactpose\",\"task\":\"Install ContactPose\",\"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/facebookresearch-contactpose/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/facebookresearch-contactpose"},"trust":{"score":72,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"421 GitHub stars","repoActivity":"421 stars, 36 forks","lastPushed":"1y since push","license":"MIT","repository":"https://github.com/facebookresearch/ContactPose","install":"npx skills add facebookresearch/ContactPose","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":["robotics-iot","robotics","automation","computer-vision","contact","dataset"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 421 stars, 36 forks; issue activity unavailable in current metadata","Recent maintenance: 1y since push"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":65,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Stars/forks activity: 421 stars, 36 forks; issue activity unavailable in current metadata","Recent maintenance: 1y since push"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":46,"label":"Needs review"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"1y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Documentation summary is thin","Repository appears stale","Quality score needs review","Stars/forks activity: 421 stars, 36 forks; issue activity unavailable in current metadata"],"agent_contract":{"task_input":"Use ContactPose in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 72/100 Strong shortlist","Audit: 65/100 Needs review","Safety: 53/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"facebookresearch-contactpose (ContactPose)","install_command":"npx skills add facebookresearch/ContactPose","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":"facebookresearch-contactpose","task":"Use ContactPose 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/facebookresearch-contactpose","api":"https://www.openagentskill.com/api/agent/skills/facebookresearch-contactpose","audit":"https://www.openagentskill.com/skills/facebookresearch-contactpose/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=facebookresearch-contactpose&task=Use%20ContactPose%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20ContactPose%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20ContactPose%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/facebookresearch-contactpose/install","manifest":"https://www.openagentskill.com/api/registry/manifest/facebookresearch-contactpose"}},"platforms":["Jupyter Notebook","Robotics"],"use_cases":[{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"install":"npx skills add facebookresearch/ContactPose","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 facebookresearch-contactpose","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 \"ContactPose\" agent skill from https://github.com/facebookresearch/ContactPose. 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: Large dataset of hand-object contact, hand- and object-pose, and 2.9 M RGB-D grasp images. 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\":\"facebookresearch-contactpose\",\"task\":\"Install ContactPose\",\"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 \"ContactPose\" as a Claude Code skill from https://github.com/facebookresearch/ContactPose. 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: Large dataset of hand-object contact, hand- and object-pose, and 2.9 M RGB-D grasp images. 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\":\"facebookresearch-contactpose\",\"task\":\"Install ContactPose\",\"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 \"ContactPose\" from https://github.com/facebookresearch/ContactPose 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: Large dataset of hand-object contact, hand- and object-pose, and 2.9 M RGB-D grasp images. 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\":\"facebookresearch-contactpose\",\"task\":\"Install ContactPose\",\"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/facebookresearch/ContactPose","github_repo":"facebookresearch/ContactPose","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"facebookresearch/contactpose","recommendation_reasons":["Matches task terms: grasp","Install handoff is available","Repository freshness signal is available","Registry match score 7"],"urls":{"web":"https://www.openagentskill.com/skills/facebookresearch-contactpose","api":"https://www.openagentskill.com/api/agent/skills/facebookresearch-contactpose","install_api":"https://www.openagentskill.com/api/skills/facebookresearch-contactpose/install","audit":"https://www.openagentskill.com/skills/facebookresearch-contactpose/audit","repository":"https://github.com/facebookresearch/ContactPose"}},{"rank":5,"match_type":"related","match_score":7,"raw_match_score":51.1,"semantic_relevance":30,"slug":"liruiw-omg-planner","name":"OMG Planner","description":"An Optimization-based Motion and Grasp Planner","tagline":"An Optimization-based Motion and Grasp Planner","category":"robotics-iot","tags":["robotics","automation","robotics-iot","chomp","grasping","motion-planning","trajectory-optimization","c++","github"],"author":{"name":"liruiw","verified":false,"url":"https://github.com/liruiw"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"liruiw/OMG-Planner","creatorName":"liruiw","creatorUrl":"https://github.com/liruiw","sourceUrl":"https://github.com/liruiw/OMG-Planner","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/liruiw-omg-planner#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":138,"forks":29,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":33.7},"quality":{"score":42,"tier":"review","label":"Needs review","summary":"Inspect the repository carefully before adding it to an agent workflow.","signals":[{"label":"GitHub stars","value":"138","tone":"neutral"},{"label":"Freshness","value":"4y 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":68,"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":"138 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"138 stars, 29 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":22,"weight":0.14,"status":"fail","detail":"4y 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 liruiw/OMG-Planner"},{"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/liruiw/OMG-Planner"},{"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":"138 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"138 stars, 29 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"4y 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 liruiw/OMG-Planner"},{"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/liruiw/OMG-Planner"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Install command has no obvious high-risk pattern"],"warnings":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 138 stars, 29 forks; issue activity unavailable in current metadata","Recent maintenance: 4y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"138 GitHub stars","repoActivity":"138 stars, 29 forks","lastPushed":"4y since push","license":"MIT","repository":"https://github.com/liruiw/OMG-Planner","install":"npx skills add liruiw/OMG-Planner","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 liruiw/OMG-Planner","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","4y since push"]},"agentCompatibility":["C++","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 138 stars, 29 forks; issue activity unavailable in current metadata","Recent maintenance: 4y since push"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["robotics-iot","robotics","automation","chomp","grasping","motion-planning"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 138 stars, 29 forks; issue activity unavailable in current metadata","Recent maintenance: 4y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":48,"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","48/100 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","48/100 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":"browser-automation","title":"Browser automation"},{"slug":"github-automation","title":"GitHub automation"},{"slug":"coding-agents","title":"Coding agents"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","C++"],"install":{"ready":true,"command":"npx skills add liruiw/OMG-Planner","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":138,"starsLabel":"138","forks":29,"license":"MIT","qualityScore":42,"trustScore":68,"auditScore":60},"maintenance":{"status":"stale","label":"4y since push","daysSincePush":1365,"lastPushedAt":"2022-11-26T15:24:00+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","Stars/forks activity: 138 stars, 29 forks; issue activity unavailable in current metadata"]},"coverageTags":["Coding","GitHub automation","robotics-iot","robotics","automation","chomp","grasping","motion-planning"]},"audit":{"audit_score":60,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Stars/forks activity: 138 stars, 29 forks; issue activity unavailable in current metadata"]},"decision":{"readiness_score":32,"readiness_label":"Needs manual review","headline":"Needs validation for Browser automation","role":"Needs validation","primary_fit":"Browser automation","best_for":["Browser 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 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":"liruiw-omg-planner","name":"OMG Planner","description":"An Optimization-based Motion and Grasp Planner","category":"robotics-iot","url":"https://www.openagentskill.com/skills/liruiw-omg-planner","repository":"https://github.com/liruiw/OMG-Planner","github_repo":"liruiw/OMG-Planner"},"suited_tasks":["Browser automation workflows","general agent builders","builders willing to evaluate younger projects","Navigate pages","Click and type safely","Check visual and DOM state","Inspect repository metadata","Compare code changes"],"suited_agents":["C++","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add liruiw/OMG-Planner","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 liruiw-omg-planner"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"OMG Planner\" agent skill from https://github.com/liruiw/OMG-Planner. 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: An Optimization-based Motion and Grasp Planner 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\":\"liruiw-omg-planner\",\"task\":\"Install OMG Planner\",\"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 \"OMG Planner\" as a Claude Code skill from https://github.com/liruiw/OMG-Planner. 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: An Optimization-based Motion and Grasp Planner 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\":\"liruiw-omg-planner\",\"task\":\"Install OMG Planner\",\"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 \"OMG Planner\" from https://github.com/liruiw/OMG-Planner 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: An Optimization-based Motion and Grasp Planner 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\":\"liruiw-omg-planner\",\"task\":\"Install OMG Planner\",\"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/liruiw-omg-planner/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/liruiw-omg-planner"},"trust":{"score":68,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"138 GitHub stars","repoActivity":"138 stars, 29 forks","lastPushed":"4y since push","license":"MIT","repository":"https://github.com/liruiw/OMG-Planner","install":"npx skills add liruiw/OMG-Planner","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":["robotics-iot","robotics","automation","chomp","grasping","motion-planning"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 138 stars, 29 forks; issue activity unavailable in current metadata","Recent maintenance: 4y 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":60,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Stars/forks activity: 138 stars, 29 forks; issue activity unavailable in current metadata","Recent maintenance: 4y 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":42,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"4y 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","Stars/forks activity: 138 stars, 29 forks; issue activity unavailable in current metadata"],"agent_contract":{"task_input":"Use OMG Planner 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: 68/100 Manual review","Audit: 60/100 Needs review","Safety: 48/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"liruiw-omg-planner (OMG Planner)","install_command":"npx skills add liruiw/OMG-Planner","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":"liruiw-omg-planner","task":"Use OMG Planner 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/liruiw-omg-planner","api":"https://www.openagentskill.com/api/agent/skills/liruiw-omg-planner","audit":"https://www.openagentskill.com/skills/liruiw-omg-planner/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=liruiw-omg-planner&task=Use%20OMG%20Planner%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20OMG%20Planner%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20OMG%20Planner%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/liruiw-omg-planner/install","manifest":"https://www.openagentskill.com/api/registry/manifest/liruiw-omg-planner"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"liruiw-omg-planner","name":"OMG Planner","description":"An Optimization-based Motion and Grasp Planner","category":"robotics-iot","url":"https://www.openagentskill.com/skills/liruiw-omg-planner","repository":"https://github.com/liruiw/OMG-Planner","github_repo":"liruiw/OMG-Planner"},"suited_tasks":["Browser automation workflows","general agent builders","builders willing to evaluate younger projects","Navigate pages","Click and type safely","Check visual and DOM state","Inspect repository metadata","Compare code changes"],"suited_agents":["C++","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add liruiw/OMG-Planner","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 liruiw-omg-planner"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"OMG Planner\" agent skill from https://github.com/liruiw/OMG-Planner. 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: An Optimization-based Motion and Grasp Planner 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\":\"liruiw-omg-planner\",\"task\":\"Install OMG Planner\",\"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 \"OMG Planner\" as a Claude Code skill from https://github.com/liruiw/OMG-Planner. 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: An Optimization-based Motion and Grasp Planner 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\":\"liruiw-omg-planner\",\"task\":\"Install OMG Planner\",\"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 \"OMG Planner\" from https://github.com/liruiw/OMG-Planner 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: An Optimization-based Motion and Grasp Planner 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\":\"liruiw-omg-planner\",\"task\":\"Install OMG Planner\",\"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/liruiw-omg-planner/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/liruiw-omg-planner"},"trust":{"score":68,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"138 GitHub stars","repoActivity":"138 stars, 29 forks","lastPushed":"4y since push","license":"MIT","repository":"https://github.com/liruiw/OMG-Planner","install":"npx skills add liruiw/OMG-Planner","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":["robotics-iot","robotics","automation","chomp","grasping","motion-planning"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 138 stars, 29 forks; issue activity unavailable in current metadata","Recent maintenance: 4y 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":60,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Stars/forks activity: 138 stars, 29 forks; issue activity unavailable in current metadata","Recent maintenance: 4y 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":42,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"4y 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","Stars/forks activity: 138 stars, 29 forks; issue activity unavailable in current metadata"],"agent_contract":{"task_input":"Use OMG Planner 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: 68/100 Manual review","Audit: 60/100 Needs review","Safety: 48/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"liruiw-omg-planner (OMG Planner)","install_command":"npx skills add liruiw/OMG-Planner","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":"liruiw-omg-planner","task":"Use OMG Planner 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/liruiw-omg-planner","api":"https://www.openagentskill.com/api/agent/skills/liruiw-omg-planner","audit":"https://www.openagentskill.com/skills/liruiw-omg-planner/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=liruiw-omg-planner&task=Use%20OMG%20Planner%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20OMG%20Planner%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20OMG%20Planner%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/liruiw-omg-planner/install","manifest":"https://www.openagentskill.com/api/registry/manifest/liruiw-omg-planner"}},"platforms":["C++","Robotics"],"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"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":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"install":"npx skills add liruiw/OMG-Planner","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 liruiw-omg-planner","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 \"OMG Planner\" agent skill from https://github.com/liruiw/OMG-Planner. 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: An Optimization-based Motion and Grasp Planner 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\":\"liruiw-omg-planner\",\"task\":\"Install OMG Planner\",\"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 \"OMG Planner\" as a Claude Code skill from https://github.com/liruiw/OMG-Planner. 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: An Optimization-based Motion and Grasp Planner 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\":\"liruiw-omg-planner\",\"task\":\"Install OMG Planner\",\"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 \"OMG Planner\" from https://github.com/liruiw/OMG-Planner 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: An Optimization-based Motion and Grasp Planner 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\":\"liruiw-omg-planner\",\"task\":\"Install OMG Planner\",\"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/liruiw/OMG-Planner","github_repo":"liruiw/OMG-Planner","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"liruiw/omg-planner","recommendation_reasons":["Matches task terms: grasp","Install handoff is available","Repository freshness signal is available","Registry match score 7"],"urls":{"web":"https://www.openagentskill.com/skills/liruiw-omg-planner","api":"https://www.openagentskill.com/api/agent/skills/liruiw-omg-planner","install_api":"https://www.openagentskill.com/api/skills/liruiw-omg-planner/install","audit":"https://www.openagentskill.com/skills/liruiw-omg-planner/audit","repository":"https://github.com/liruiw/OMG-Planner"}},{"rank":6,"match_type":"related","match_score":7,"raw_match_score":50.7,"semantic_relevance":30,"slug":"atenpas-gpg","name":"Gpg","description":"Generate grasp pose candidates in point clouds","tagline":"Generate grasp pose candidates in point clouds","category":"robotics-iot","tags":["robotics","automation","robotics-iot","grasping","ros","c++","github"],"author":{"name":"atenpas","verified":false,"url":"https://github.com/atenpas"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"atenpas/gpg","creatorName":"atenpas","creatorUrl":"https://github.com/atenpas","sourceUrl":"https://github.com/atenpas/gpg","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/atenpas-gpg#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":119,"forks":62,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":33.25},"quality":{"score":41,"tier":"review","label":"Needs review","summary":"Inspect the repository carefully before adding it to an agent workflow.","signals":[{"label":"GitHub stars","value":"119","tone":"neutral"},{"label":"Freshness","value":"8y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"BSD-2-Clause","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":"119 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":62,"weight":0.08,"status":"info","detail":"119 stars, 62 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":22,"weight":0.14,"status":"fail","detail":"8y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"BSD-2-Clause"},{"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 atenpas/gpg"},{"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/atenpas/gpg"},{"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":"119 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"119 stars, 62 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"8y since push"},{"status":"pass","label":"License clarity","detail":"BSD-2-Clause"},{"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 atenpas/gpg"},{"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/atenpas/gpg"},{"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: 8y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"119 GitHub stars","repoActivity":"119 stars, 62 forks","lastPushed":"8y since push","license":"BSD-2-Clause","repository":"https://github.com/atenpas/gpg","install":"npx skills add atenpas/gpg","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 atenpas/gpg","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","8y since push"]},"agentCompatibility":["C++","Robotics","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: 8y 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":["robotics-iot","robotics","automation","grasping","ros","c++"],"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: 8y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":48,"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","48/100 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","48/100 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","C++"],"install":{"ready":true,"command":"npx skills add atenpas/gpg","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":119,"starsLabel":"119","forks":62,"license":"BSD-2-Clause","qualityScore":41,"trustScore":69,"auditScore":60},"maintenance":{"status":"stale","label":"8y since push","daysSincePush":2774,"lastPushedAt":"2019-01-18T02:57:53+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: 8y since push"]},"coverageTags":["Coding","GitHub automation","robotics-iot","robotics","automation","grasping","ros","c++"]},"audit":{"audit_score":60,"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: 8y since push"]},"decision":{"readiness_score":31,"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":"atenpas-gpg","name":"Gpg","description":"Generate grasp pose candidates in point clouds","category":"robotics-iot","url":"https://www.openagentskill.com/skills/atenpas-gpg","repository":"https://github.com/atenpas/gpg","github_repo":"atenpas/gpg"},"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":["C++","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add atenpas/gpg","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 atenpas-gpg"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Gpg\" agent skill from https://github.com/atenpas/gpg. 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: Generate grasp pose candidates in point clouds 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\":\"atenpas-gpg\",\"task\":\"Install Gpg\",\"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 \"Gpg\" as a Claude Code skill from https://github.com/atenpas/gpg. 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: Generate grasp pose candidates in point clouds 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\":\"atenpas-gpg\",\"task\":\"Install Gpg\",\"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 \"Gpg\" from https://github.com/atenpas/gpg 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: Generate grasp pose candidates in point clouds 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\":\"atenpas-gpg\",\"task\":\"Install Gpg\",\"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/atenpas-gpg/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/atenpas-gpg"},"trust":{"score":69,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"119 GitHub stars","repoActivity":"119 stars, 62 forks","lastPushed":"8y since push","license":"BSD-2-Clause","repository":"https://github.com/atenpas/gpg","install":"npx skills add atenpas/gpg","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":["robotics-iot","robotics","automation","grasping","ros","c++"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 8y 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":60,"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: 8y 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":41,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"8y 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: 8y since push"],"agent_contract":{"task_input":"Use Gpg 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: 60/100 Needs review","Safety: 48/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"atenpas-gpg (Gpg)","install_command":"npx skills add atenpas/gpg","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":"atenpas-gpg","task":"Use Gpg 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/atenpas-gpg","api":"https://www.openagentskill.com/api/agent/skills/atenpas-gpg","audit":"https://www.openagentskill.com/skills/atenpas-gpg/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=atenpas-gpg&task=Use%20Gpg%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Gpg%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Gpg%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/atenpas-gpg/install","manifest":"https://www.openagentskill.com/api/registry/manifest/atenpas-gpg"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"atenpas-gpg","name":"Gpg","description":"Generate grasp pose candidates in point clouds","category":"robotics-iot","url":"https://www.openagentskill.com/skills/atenpas-gpg","repository":"https://github.com/atenpas/gpg","github_repo":"atenpas/gpg"},"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":["C++","Robotics","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add atenpas/gpg","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 atenpas-gpg"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Gpg\" agent skill from https://github.com/atenpas/gpg. 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: Generate grasp pose candidates in point clouds 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\":\"atenpas-gpg\",\"task\":\"Install Gpg\",\"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 \"Gpg\" as a Claude Code skill from https://github.com/atenpas/gpg. 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: Generate grasp pose candidates in point clouds 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\":\"atenpas-gpg\",\"task\":\"Install Gpg\",\"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 \"Gpg\" from https://github.com/atenpas/gpg 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: Generate grasp pose candidates in point clouds 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\":\"atenpas-gpg\",\"task\":\"Install Gpg\",\"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/atenpas-gpg/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/atenpas-gpg"},"trust":{"score":69,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"119 GitHub stars","repoActivity":"119 stars, 62 forks","lastPushed":"8y since push","license":"BSD-2-Clause","repository":"https://github.com/atenpas/gpg","install":"npx skills add atenpas/gpg","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":["robotics-iot","robotics","automation","grasping","ros","c++"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 8y 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":60,"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: 8y 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":41,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"8y 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: 8y since push"],"agent_contract":{"task_input":"Use Gpg 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: 60/100 Needs review","Safety: 48/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"atenpas-gpg (Gpg)","install_command":"npx skills add atenpas/gpg","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":"atenpas-gpg","task":"Use Gpg 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/atenpas-gpg","api":"https://www.openagentskill.com/api/agent/skills/atenpas-gpg","audit":"https://www.openagentskill.com/skills/atenpas-gpg/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=atenpas-gpg&task=Use%20Gpg%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Gpg%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Gpg%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/atenpas-gpg/install","manifest":"https://www.openagentskill.com/api/registry/manifest/atenpas-gpg"}},"platforms":["C++","Robotics"],"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 atenpas/gpg","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 atenpas-gpg","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 \"Gpg\" agent skill from https://github.com/atenpas/gpg. 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: Generate grasp pose candidates in point clouds 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\":\"atenpas-gpg\",\"task\":\"Install Gpg\",\"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 \"Gpg\" as a Claude Code skill from https://github.com/atenpas/gpg. 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: Generate grasp pose candidates in point clouds 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\":\"atenpas-gpg\",\"task\":\"Install Gpg\",\"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 \"Gpg\" from https://github.com/atenpas/gpg 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: Generate grasp pose candidates in point clouds 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\":\"atenpas-gpg\",\"task\":\"Install Gpg\",\"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/atenpas/gpg","github_repo":"atenpas/gpg","version":"1.0.0","license":"BSD-2-Clause","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"atenpas/gpg","recommendation_reasons":["Matches task terms: grasp","Install handoff is available","Repository freshness signal is available","Registry match score 7"],"urls":{"web":"https://www.openagentskill.com/skills/atenpas-gpg","api":"https://www.openagentskill.com/api/agent/skills/atenpas-gpg","install_api":"https://www.openagentskill.com/api/skills/atenpas-gpg/install","audit":"https://www.openagentskill.com/skills/atenpas-gpg/audit","repository":"https://github.com/atenpas/gpg"}},{"rank":7,"match_type":"related","match_score":4,"raw_match_score":31.8,"semantic_relevance":30,"slug":"pauldanielml-mujoco-rl-ur5","name":"MuJoCo RL UR5","description":"A MuJoCo/Gym environment for robot control using Reinforcement Learning. The task of agents in this environment is pixel-wise prediction of grasp success chances.","tagline":"A MuJoCo/Gym environment for robot control using Reinforcement Learning. The task of agents in this environment is pixel-wise prediction of grasp success chances.","category":"robotics-iot","tags":["computer-vision","automation","robotics-iot","gym-environment","mujoco","pick-and-place","reinforcement-learning","robotics","python","github"],"author":{"name":"PaulDanielML","verified":false,"url":"https://github.com/PaulDanielML"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"PaulDanielML/MuJoCo_RL_UR5","creatorName":"PaulDanielML","creatorUrl":"https://github.com/PaulDanielML","sourceUrl":"https://github.com/PaulDanielML/MuJoCo_RL_UR5","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/pauldanielml-mujoco-rl-ur5#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":679,"forks":68,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":38.53},"quality":{"score":49,"tier":"review","label":"Needs review","summary":"Inspect the repository carefully before adding it to an agent workflow.","signals":[{"label":"GitHub stars","value":"679","tone":"positive"},{"label":"Freshness","value":"4y 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":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":76,"weight":0.13,"status":"info","detail":"679 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":71,"weight":0.08,"status":"info","detail":"679 stars, 68 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":22,"weight":0.14,"status":"fail","detail":"4y 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 PaulDanielML/MuJoCo_RL_UR5"},{"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/PaulDanielML/MuJoCo_RL_UR5"},{"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":"679 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"679 stars, 68 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"4y 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 PaulDanielML/MuJoCo_RL_UR5"},{"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/PaulDanielML/MuJoCo_RL_UR5"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 4y since push"],"evidence":{"stars":"679 GitHub stars","repoActivity":"679 stars, 68 forks","lastPushed":"4y since push","license":"MIT","repository":"https://github.com/PaulDanielML/MuJoCo_RL_UR5","install":"npx skills add PaulDanielML/MuJoCo_RL_UR5","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 PaulDanielML/MuJoCo_RL_UR5","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","4y since push"]},"agentCompatibility":["Python","Computer Vision","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: 4y since push"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["robotics-iot","computer-vision","automation","gym-environment","mujoco","pick-and-place"],"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: 4y since push"]},"safety":{"score":52,"level":"avoid_auto_install","label":"Avoid automatic install","safety_tier":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","summary":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","auto_install_policy":"review","reasons":["Repository appears stale","52/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Repository appears stale"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","reasons":["Repository appears stale","52/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"GitHub automation","description":"I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.","useCases":[{"slug":"workflow-automation","title":"Workflow automation"},{"slug":"github-automation","title":"GitHub automation"},{"slug":"coding-agents","title":"Coding agents"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add PaulDanielML/MuJoCo_RL_UR5","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":679,"starsLabel":"679","forks":68,"license":"MIT","qualityScore":49,"trustScore":73,"auditScore":64},"maintenance":{"status":"stale","label":"4y since push","daysSincePush":1370,"lastPushedAt":"2022-11-21T12:11:32+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 4y since push"]},"coverageTags":["Coding","GitHub automation","robotics-iot","computer-vision","automation","gym-environment","mujoco","pick-and-place"]},"audit":{"audit_score":64,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 4y since push"]},"decision":{"readiness_score":51,"readiness_label":"Needs manual review","headline":"Needs validation for Workflow automation","role":"Needs validation","primary_fit":"Workflow automation","best_for":["Workflow automation workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["Repository looks stale","No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Workflow 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":"pauldanielml-mujoco-rl-ur5","name":"MuJoCo RL UR5","description":"A MuJoCo/Gym environment for robot control using Reinforcement Learning. The task of agents in this environment is pixel-wise prediction of grasp success chances.","category":"robotics-iot","url":"https://www.openagentskill.com/skills/pauldanielml-mujoco-rl-ur5","repository":"https://github.com/PaulDanielML/MuJoCo_RL_UR5","github_repo":"PaulDanielML/MuJoCo_RL_UR5"},"suited_tasks":["Workflow automation workflows","general agent builders","teams that value GitHub adoption signals","Move data between tools","Transform files","Trigger repeatable actions","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add PaulDanielML/MuJoCo_RL_UR5","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 pauldanielml-mujoco-rl-ur5"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"MuJoCo RL UR5\" agent skill from https://github.com/PaulDanielML/MuJoCo_RL_UR5. 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 MuJoCo/Gym environment for robot control using Reinforcement Learning. The task of agents in this environment is pixel-wise prediction of grasp success chances. 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\":\"pauldanielml-mujoco-rl-ur5\",\"task\":\"Install MuJoCo RL UR5\",\"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 \"MuJoCo RL UR5\" as a Claude Code skill from https://github.com/PaulDanielML/MuJoCo_RL_UR5. 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 MuJoCo/Gym environment for robot control using Reinforcement Learning. The task of agents in this environment is pixel-wise prediction of grasp success chances. 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\":\"pauldanielml-mujoco-rl-ur5\",\"task\":\"Install MuJoCo RL UR5\",\"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 \"MuJoCo RL UR5\" from https://github.com/PaulDanielML/MuJoCo_RL_UR5 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 MuJoCo/Gym environment for robot control using Reinforcement Learning. The task of agents in this environment is pixel-wise prediction of grasp success chances. 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\":\"pauldanielml-mujoco-rl-ur5\",\"task\":\"Install MuJoCo RL UR5\",\"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/pauldanielml-mujoco-rl-ur5/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/pauldanielml-mujoco-rl-ur5"},"trust":{"score":73,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"679 GitHub stars","repoActivity":"679 stars, 68 forks","lastPushed":"4y since push","license":"MIT","repository":"https://github.com/PaulDanielML/MuJoCo_RL_UR5","install":"npx skills add PaulDanielML/MuJoCo_RL_UR5","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":["robotics-iot","computer-vision","automation","gym-environment","mujoco","pick-and-place"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 4y since push"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":64,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 4y since push"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":49,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"4y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Repository appears stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 4y since push"],"agent_contract":{"task_input":"Use MuJoCo RL UR5 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: 64/100 Needs review","Safety: 52/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"pauldanielml-mujoco-rl-ur5 (MuJoCo RL UR5)","install_command":"npx skills add PaulDanielML/MuJoCo_RL_UR5","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":"pauldanielml-mujoco-rl-ur5","task":"Use MuJoCo RL UR5 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/pauldanielml-mujoco-rl-ur5","api":"https://www.openagentskill.com/api/agent/skills/pauldanielml-mujoco-rl-ur5","audit":"https://www.openagentskill.com/skills/pauldanielml-mujoco-rl-ur5/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=pauldanielml-mujoco-rl-ur5&task=Use%20MuJoCo%20RL%20UR5%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20MuJoCo%20RL%20UR5%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20MuJoCo%20RL%20UR5%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/pauldanielml-mujoco-rl-ur5/install","manifest":"https://www.openagentskill.com/api/registry/manifest/pauldanielml-mujoco-rl-ur5"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"pauldanielml-mujoco-rl-ur5","name":"MuJoCo RL UR5","description":"A MuJoCo/Gym environment for robot control using Reinforcement Learning. The task of agents in this environment is pixel-wise prediction of grasp success chances.","category":"robotics-iot","url":"https://www.openagentskill.com/skills/pauldanielml-mujoco-rl-ur5","repository":"https://github.com/PaulDanielML/MuJoCo_RL_UR5","github_repo":"PaulDanielML/MuJoCo_RL_UR5"},"suited_tasks":["Workflow automation workflows","general agent builders","teams that value GitHub adoption signals","Move data between tools","Transform files","Trigger repeatable actions","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add PaulDanielML/MuJoCo_RL_UR5","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 pauldanielml-mujoco-rl-ur5"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"MuJoCo RL UR5\" agent skill from https://github.com/PaulDanielML/MuJoCo_RL_UR5. 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 MuJoCo/Gym environment for robot control using Reinforcement Learning. The task of agents in this environment is pixel-wise prediction of grasp success chances. 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\":\"pauldanielml-mujoco-rl-ur5\",\"task\":\"Install MuJoCo RL UR5\",\"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 \"MuJoCo RL UR5\" as a Claude Code skill from https://github.com/PaulDanielML/MuJoCo_RL_UR5. 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 MuJoCo/Gym environment for robot control using Reinforcement Learning. The task of agents in this environment is pixel-wise prediction of grasp success chances. 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\":\"pauldanielml-mujoco-rl-ur5\",\"task\":\"Install MuJoCo RL UR5\",\"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 \"MuJoCo RL UR5\" from https://github.com/PaulDanielML/MuJoCo_RL_UR5 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 MuJoCo/Gym environment for robot control using Reinforcement Learning. The task of agents in this environment is pixel-wise prediction of grasp success chances. 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\":\"pauldanielml-mujoco-rl-ur5\",\"task\":\"Install MuJoCo RL UR5\",\"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/pauldanielml-mujoco-rl-ur5/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/pauldanielml-mujoco-rl-ur5"},"trust":{"score":73,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"679 GitHub stars","repoActivity":"679 stars, 68 forks","lastPushed":"4y since push","license":"MIT","repository":"https://github.com/PaulDanielML/MuJoCo_RL_UR5","install":"npx skills add PaulDanielML/MuJoCo_RL_UR5","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":["robotics-iot","computer-vision","automation","gym-environment","mujoco","pick-and-place"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 4y since push"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":64,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 4y since push"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":49,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"4y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Repository appears stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 4y since push"],"agent_contract":{"task_input":"Use MuJoCo RL UR5 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: 64/100 Needs review","Safety: 52/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"pauldanielml-mujoco-rl-ur5 (MuJoCo RL UR5)","install_command":"npx skills add PaulDanielML/MuJoCo_RL_UR5","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":"pauldanielml-mujoco-rl-ur5","task":"Use MuJoCo RL UR5 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/pauldanielml-mujoco-rl-ur5","api":"https://www.openagentskill.com/api/agent/skills/pauldanielml-mujoco-rl-ur5","audit":"https://www.openagentskill.com/skills/pauldanielml-mujoco-rl-ur5/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=pauldanielml-mujoco-rl-ur5&task=Use%20MuJoCo%20RL%20UR5%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20MuJoCo%20RL%20UR5%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20MuJoCo%20RL%20UR5%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/pauldanielml-mujoco-rl-ur5/install","manifest":"https://www.openagentskill.com/api/registry/manifest/pauldanielml-mujoco-rl-ur5"}},"platforms":["Python","Computer Vision"],"use_cases":[{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"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"}],"install":"npx skills add PaulDanielML/MuJoCo_RL_UR5","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 pauldanielml-mujoco-rl-ur5","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 \"MuJoCo RL UR5\" agent skill from https://github.com/PaulDanielML/MuJoCo_RL_UR5. 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 MuJoCo/Gym environment for robot control using Reinforcement Learning. The task of agents in this environment is pixel-wise prediction of grasp success chances. 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\":\"pauldanielml-mujoco-rl-ur5\",\"task\":\"Install MuJoCo RL UR5\",\"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 \"MuJoCo RL UR5\" as a Claude Code skill from https://github.com/PaulDanielML/MuJoCo_RL_UR5. 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 MuJoCo/Gym environment for robot control using Reinforcement Learning. The task of agents in this environment is pixel-wise prediction of grasp success chances. 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\":\"pauldanielml-mujoco-rl-ur5\",\"task\":\"Install MuJoCo RL UR5\",\"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 \"MuJoCo RL UR5\" from https://github.com/PaulDanielML/MuJoCo_RL_UR5 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 MuJoCo/Gym environment for robot control using Reinforcement Learning. The task of agents in this environment is pixel-wise prediction of grasp success chances. 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\":\"pauldanielml-mujoco-rl-ur5\",\"task\":\"Install MuJoCo RL UR5\",\"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/PaulDanielML/MuJoCo_RL_UR5","github_repo":"PaulDanielML/MuJoCo_RL_UR5","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"pauldanielml/mujoco_rl_ur5","recommendation_reasons":["Matches task terms: grasp","Useful GitHub adoption: 679 stars","Install handoff is available","Repository freshness signal is available","Registry match score 4"],"urls":{"web":"https://www.openagentskill.com/skills/pauldanielml-mujoco-rl-ur5","api":"https://www.openagentskill.com/api/agent/skills/pauldanielml-mujoco-rl-ur5","install_api":"https://www.openagentskill.com/api/skills/pauldanielml-mujoco-rl-ur5/install","audit":"https://www.openagentskill.com/skills/pauldanielml-mujoco-rl-ur5/audit","repository":"https://github.com/PaulDanielML/MuJoCo_RL_UR5"}}],"meta":{"endpoint":"/api/skills/search","canonical_agent_endpoint":"/api/agent/resolve","lookup_intent":false,"exact_match_found":false,"match_counts":{"exact":0,"near":0,"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":"2026-08-23T12:06:56.949Z"}}