{"query":"SAM DETR","filters":{"category":null,"platform":null,"track":null,"safety":null,"include_blocked":false,"min_stars":0},"total":10,"skills":[{"rank":1,"match_type":"exact","match_score":99,"raw_match_score":741.4,"semantic_relevance":100,"slug":"zhanggongjie-sam-detr","name":"SAM DETR","description":"[CVPR'2022] SAM-DETR & SAM-DETR++: Official PyTorch Implementation","tagline":"[CVPR'2022] SAM-DETR & SAM-DETR++: Official PyTorch Implementation","category":"ml-automation","tags":["machine-learning","automation","ml-media","computer-vision","cvpr","cvpr2022","deep-learning","detection","detr","object-detection"],"author":{"name":"ZhangGongjie","verified":false,"url":"https://github.com/ZhangGongjie"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"ZhangGongjie/SAM-DETR","creatorName":"ZhangGongjie","creatorUrl":"https://github.com/ZhangGongjie","sourceUrl":"https://github.com/ZhangGongjie/SAM-DETR","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/zhanggongjie-sam-detr#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":301,"forks":46,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":36.06},"quality":{"score":45,"tier":"review","label":"Needs review","summary":"Inspect the repository carefully before adding it to an agent workflow.","signals":[{"label":"GitHub stars","value":"301","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":"301 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"301 stars, 46 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 ZhangGongjie/SAM-DETR"},{"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/ZhangGongjie/SAM-DETR"},{"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":"301 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"301 stars, 46 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 ZhangGongjie/SAM-DETR"},{"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/ZhangGongjie/SAM-DETR"},{"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: 301 stars, 46 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":"301 GitHub stars","repoActivity":"301 stars, 46 forks","lastPushed":"4y since push","license":"MIT","repository":"https://github.com/ZhangGongjie/SAM-DETR","install":"npx skills add ZhangGongjie/SAM-DETR","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 ZhangGongjie/SAM-DETR","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","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 301 stars, 46 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":["ml-automation","machine-learning","automation","ml-media","computer-vision","cvpr"],"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: 301 stars, 46 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":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Multimodal media","description":"I need my agent to process images, video, or audio and extract useful information.","useCases":[{"slug":"multimodal-media","title":"Multimodal media"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"workflow-automation","title":"Workflow automation"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add ZhangGongjie/SAM-DETR","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":301,"starsLabel":"301","forks":46,"license":"MIT","qualityScore":45,"trustScore":68,"auditScore":60},"maintenance":{"status":"stale","label":"4y since push","daysSincePush":1459,"lastPushedAt":"2022-08-24T09:14:25+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: 301 stars, 46 forks; issue activity unavailable in current metadata"]},"coverageTags":["Design","Multimodal media","ml-automation","machine-learning","automation","ml-media","computer-vision","cvpr"]},"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: 301 stars, 46 forks; issue activity unavailable in current metadata"]},"decision":{"readiness_score":35,"readiness_label":"Needs manual review","headline":"Needs validation for Multimodal media","role":"Needs validation","primary_fit":"Multimodal media","best_for":["Multimodal media 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 Multimodal media task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"zhanggongjie-sam-detr","name":"SAM DETR","description":"[CVPR'2022] SAM-DETR & SAM-DETR++: Official PyTorch Implementation","category":"ml-automation","url":"https://www.openagentskill.com/skills/zhanggongjie-sam-detr","repository":"https://github.com/ZhangGongjie/SAM-DETR","github_repo":"ZhangGongjie/SAM-DETR"},"suited_tasks":["Multimodal media workflows","general agent builders","builders willing to evaluate younger projects","Read media metadata","Convert formats","Summarize visual or audio content","Navigate pages","Click and type safely"],"suited_agents":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add ZhangGongjie/SAM-DETR","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 zhanggongjie-sam-detr"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"SAM DETR\" agent skill from https://github.com/ZhangGongjie/SAM-DETR. 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: [CVPR'2022] SAM-DETR & SAM-DETR++: Official PyTorch Implementation 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\":\"zhanggongjie-sam-detr\",\"task\":\"Install SAM DETR\",\"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 \"SAM DETR\" as a Claude Code skill from https://github.com/ZhangGongjie/SAM-DETR. 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: [CVPR'2022] SAM-DETR & SAM-DETR++: Official PyTorch Implementation 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\":\"zhanggongjie-sam-detr\",\"task\":\"Install SAM DETR\",\"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 \"SAM DETR\" from https://github.com/ZhangGongjie/SAM-DETR 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: [CVPR'2022] SAM-DETR & SAM-DETR++: Official PyTorch Implementation 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\":\"zhanggongjie-sam-detr\",\"task\":\"Install SAM DETR\",\"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/zhanggongjie-sam-detr/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/zhanggongjie-sam-detr"},"trust":{"score":68,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"301 GitHub stars","repoActivity":"301 stars, 46 forks","lastPushed":"4y since push","license":"MIT","repository":"https://github.com/ZhangGongjie/SAM-DETR","install":"npx skills add ZhangGongjie/SAM-DETR","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["ml-automation","machine-learning","automation","ml-media","computer-vision","cvpr"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 301 stars, 46 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: 301 stars, 46 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":45,"label":"Needs review"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","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: 301 stars, 46 forks; issue activity unavailable in current metadata"],"agent_contract":{"task_input":"Use SAM DETR 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":"zhanggongjie-sam-detr (SAM DETR)","install_command":"npx skills add ZhangGongjie/SAM-DETR","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":"zhanggongjie-sam-detr","task":"Use SAM DETR 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/zhanggongjie-sam-detr","api":"https://www.openagentskill.com/api/agent/skills/zhanggongjie-sam-detr","audit":"https://www.openagentskill.com/skills/zhanggongjie-sam-detr/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=zhanggongjie-sam-detr&task=Use%20SAM%20DETR%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20SAM%20DETR%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20SAM%20DETR%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/zhanggongjie-sam-detr/install","manifest":"https://www.openagentskill.com/api/registry/manifest/zhanggongjie-sam-detr"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"zhanggongjie-sam-detr","name":"SAM DETR","description":"[CVPR'2022] SAM-DETR & SAM-DETR++: Official PyTorch Implementation","category":"ml-automation","url":"https://www.openagentskill.com/skills/zhanggongjie-sam-detr","repository":"https://github.com/ZhangGongjie/SAM-DETR","github_repo":"ZhangGongjie/SAM-DETR"},"suited_tasks":["Multimodal media workflows","general agent builders","builders willing to evaluate younger projects","Read media metadata","Convert formats","Summarize visual or audio content","Navigate pages","Click and type safely"],"suited_agents":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add ZhangGongjie/SAM-DETR","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 zhanggongjie-sam-detr"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"SAM DETR\" agent skill from https://github.com/ZhangGongjie/SAM-DETR. 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: [CVPR'2022] SAM-DETR & SAM-DETR++: Official PyTorch Implementation 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\":\"zhanggongjie-sam-detr\",\"task\":\"Install SAM DETR\",\"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 \"SAM DETR\" as a Claude Code skill from https://github.com/ZhangGongjie/SAM-DETR. 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: [CVPR'2022] SAM-DETR & SAM-DETR++: Official PyTorch Implementation 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\":\"zhanggongjie-sam-detr\",\"task\":\"Install SAM DETR\",\"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 \"SAM DETR\" from https://github.com/ZhangGongjie/SAM-DETR 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: [CVPR'2022] SAM-DETR & SAM-DETR++: Official PyTorch Implementation 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\":\"zhanggongjie-sam-detr\",\"task\":\"Install SAM DETR\",\"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/zhanggongjie-sam-detr/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/zhanggongjie-sam-detr"},"trust":{"score":68,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"301 GitHub stars","repoActivity":"301 stars, 46 forks","lastPushed":"4y since push","license":"MIT","repository":"https://github.com/ZhangGongjie/SAM-DETR","install":"npx skills add ZhangGongjie/SAM-DETR","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["ml-automation","machine-learning","automation","ml-media","computer-vision","cvpr"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 301 stars, 46 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: 301 stars, 46 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":45,"label":"Needs review"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","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: 301 stars, 46 forks; issue activity unavailable in current metadata"],"agent_contract":{"task_input":"Use SAM DETR 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":"zhanggongjie-sam-detr (SAM DETR)","install_command":"npx skills add ZhangGongjie/SAM-DETR","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":"zhanggongjie-sam-detr","task":"Use SAM DETR 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/zhanggongjie-sam-detr","api":"https://www.openagentskill.com/api/agent/skills/zhanggongjie-sam-detr","audit":"https://www.openagentskill.com/skills/zhanggongjie-sam-detr/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=zhanggongjie-sam-detr&task=Use%20SAM%20DETR%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20SAM%20DETR%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20SAM%20DETR%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/zhanggongjie-sam-detr/install","manifest":"https://www.openagentskill.com/api/registry/manifest/zhanggongjie-sam-detr"}},"platforms":["Python","Machine Learning"],"use_cases":[{"slug":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"}],"install":"npx skills add ZhangGongjie/SAM-DETR","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 zhanggongjie-sam-detr","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 \"SAM DETR\" agent skill from https://github.com/ZhangGongjie/SAM-DETR. 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: [CVPR'2022] SAM-DETR & SAM-DETR++: Official PyTorch Implementation 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\":\"zhanggongjie-sam-detr\",\"task\":\"Install SAM DETR\",\"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 \"SAM DETR\" as a Claude Code skill from https://github.com/ZhangGongjie/SAM-DETR. 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: [CVPR'2022] SAM-DETR & SAM-DETR++: Official PyTorch Implementation 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\":\"zhanggongjie-sam-detr\",\"task\":\"Install SAM DETR\",\"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 \"SAM DETR\" from https://github.com/ZhangGongjie/SAM-DETR 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: [CVPR'2022] SAM-DETR & SAM-DETR++: Official PyTorch Implementation 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\":\"zhanggongjie-sam-detr\",\"task\":\"Install SAM DETR\",\"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/ZhangGongjie/SAM-DETR","github_repo":"ZhangGongjie/SAM-DETR","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"zhanggongjie/sam-detr","recommendation_reasons":["Matches task terms: sam, detr","Install handoff is available","Repository freshness signal is available","Registry match score 99"],"urls":{"web":"https://www.openagentskill.com/skills/zhanggongjie-sam-detr","api":"https://www.openagentskill.com/api/agent/skills/zhanggongjie-sam-detr","install_api":"https://www.openagentskill.com/api/skills/zhanggongjie-sam-detr/install","audit":"https://www.openagentskill.com/skills/zhanggongjie-sam-detr/audit","repository":"https://github.com/ZhangGongjie/SAM-DETR"}},{"rank":2,"match_type":"related","match_score":17,"raw_match_score":129.9,"semantic_relevance":30,"slug":"roboflow-rf-detr","name":"Rf Detr","description":"RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026] ","tagline":"RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026] ","category":"ml-automation","tags":["machine-learning","automation","ml-media","computer-vision","detr","instance-segmentation","object-detection","rf-detr","sota","python"],"author":{"name":"roboflow","verified":true,"url":"https://github.com/roboflow"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"roboflow/rf-detr","creatorName":"roboflow","creatorUrl":"https://github.com/roboflow","sourceUrl":"https://github.com/roboflow/rf-detr","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/roboflow-rf-detr#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":7779,"forks":994,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":65.94},"quality":{"score":98,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"7.8K","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":89,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"weight":0.13,"status":"pass","detail":"7.8K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"7.8K stars, 994 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add roboflow/rf-detr"},{"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/roboflow/rf-detr"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"7.8K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"7.8K stars, 994 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add roboflow/rf-detr"},{"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/roboflow/rf-detr"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin"],"evidence":{"stars":"7.8K GitHub stars","repoActivity":"7.8K stars, 994 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/roboflow/rf-detr","install":"npx skills add roboflow/rf-detr","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 roboflow/rf-detr","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["ml-automation","machine-learning","automation","ml-media","computer-vision","detr"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin"]},"safety":{"score":80,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","80/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","80/100 agent safety score"]},"supply_profile":{"track":{"slug":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Multimodal media","description":"I need my agent to process images, video, or audio and extract useful information.","useCases":[{"slug":"multimodal-media","title":"Multimodal media"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"workflow-automation","title":"Workflow automation"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add roboflow/rf-detr","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":7779,"starsLabel":"7.8K","forks":994,"license":"Apache-2.0","qualityScore":98,"trustScore":89,"auditScore":92},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":68,"lastPushedAt":"2026-06-15T22:52:27+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Design","Multimodal media","ml-automation","machine-learning","automation","ml-media","computer-vision","detr"]},"audit":{"audit_score":92,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Multimodal media","role":"Primary pick","primary_fit":"Multimodal media","best_for":["Multimodal media workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Multimodal media task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"roboflow-rf-detr","name":"Rf Detr","description":"RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026] ","category":"ml-automation","url":"https://www.openagentskill.com/skills/roboflow-rf-detr","repository":"https://github.com/roboflow/rf-detr","github_repo":"roboflow/rf-detr"},"suited_tasks":["Multimodal media workflows","general agent builders","teams that value GitHub adoption signals","Read media metadata","Convert formats","Summarize visual or audio content","Navigate pages","Click and type safely"],"suited_agents":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add roboflow/rf-detr","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 roboflow-rf-detr"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Rf Detr\" agent skill from https://github.com/roboflow/rf-detr. 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: RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026] 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\":\"roboflow-rf-detr\",\"task\":\"Install Rf Detr\",\"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 \"Rf Detr\" as a Claude Code skill from https://github.com/roboflow/rf-detr. 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: RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026] 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\":\"roboflow-rf-detr\",\"task\":\"Install Rf Detr\",\"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 \"Rf Detr\" from https://github.com/roboflow/rf-detr 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: RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026] 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\":\"roboflow-rf-detr\",\"task\":\"Install Rf Detr\",\"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/roboflow-rf-detr/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/roboflow-rf-detr"},"trust":{"score":89,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"7.8K GitHub stars","repoActivity":"7.8K stars, 994 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/roboflow/rf-detr","install":"npx skills add roboflow/rf-detr","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["ml-automation","machine-learning","automation","ml-media","computer-vision","detr"],"known_risks":["Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":92,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":98,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Rf Detr in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 89/100 Production candidate","Audit: 92/100 Safe to try","Safety: 80/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"roboflow-rf-detr (Rf Detr)","install_command":"npx skills add roboflow/rf-detr","risk_summary":"Safe to try; Reviewed; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"roboflow-rf-detr","task":"Use Rf Detr 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/roboflow-rf-detr","api":"https://www.openagentskill.com/api/agent/skills/roboflow-rf-detr","audit":"https://www.openagentskill.com/skills/roboflow-rf-detr/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=roboflow-rf-detr&task=Use%20Rf%20Detr%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Rf%20Detr%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Rf%20Detr%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/roboflow-rf-detr/install","manifest":"https://www.openagentskill.com/api/registry/manifest/roboflow-rf-detr"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"roboflow-rf-detr","name":"Rf Detr","description":"RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026] ","category":"ml-automation","url":"https://www.openagentskill.com/skills/roboflow-rf-detr","repository":"https://github.com/roboflow/rf-detr","github_repo":"roboflow/rf-detr"},"suited_tasks":["Multimodal media workflows","general agent builders","teams that value GitHub adoption signals","Read media metadata","Convert formats","Summarize visual or audio content","Navigate pages","Click and type safely"],"suited_agents":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add roboflow/rf-detr","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 roboflow-rf-detr"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Rf Detr\" agent skill from https://github.com/roboflow/rf-detr. 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: RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026] 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\":\"roboflow-rf-detr\",\"task\":\"Install Rf Detr\",\"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 \"Rf Detr\" as a Claude Code skill from https://github.com/roboflow/rf-detr. 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: RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026] 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\":\"roboflow-rf-detr\",\"task\":\"Install Rf Detr\",\"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 \"Rf Detr\" from https://github.com/roboflow/rf-detr 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: RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026] 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\":\"roboflow-rf-detr\",\"task\":\"Install Rf Detr\",\"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/roboflow-rf-detr/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/roboflow-rf-detr"},"trust":{"score":89,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"7.8K GitHub stars","repoActivity":"7.8K stars, 994 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/roboflow/rf-detr","install":"npx skills add roboflow/rf-detr","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["ml-automation","machine-learning","automation","ml-media","computer-vision","detr"],"known_risks":["Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":92,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":98,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Rf Detr in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 89/100 Production candidate","Audit: 92/100 Safe to try","Safety: 80/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"roboflow-rf-detr (Rf Detr)","install_command":"npx skills add roboflow/rf-detr","risk_summary":"Safe to try; Reviewed; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"roboflow-rf-detr","task":"Use Rf Detr 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/roboflow-rf-detr","api":"https://www.openagentskill.com/api/agent/skills/roboflow-rf-detr","audit":"https://www.openagentskill.com/skills/roboflow-rf-detr/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=roboflow-rf-detr&task=Use%20Rf%20Detr%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Rf%20Detr%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Rf%20Detr%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/roboflow-rf-detr/install","manifest":"https://www.openagentskill.com/api/registry/manifest/roboflow-rf-detr"}},"platforms":["Python","Machine Learning"],"use_cases":[{"slug":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"slug":"design-creative","title":"Design and creative","url":"https://www.openagentskill.com/use-cases/design-creative"}],"install":"npx skills add roboflow/rf-detr","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 roboflow-rf-detr","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 \"Rf Detr\" agent skill from https://github.com/roboflow/rf-detr. 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: RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026] 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\":\"roboflow-rf-detr\",\"task\":\"Install Rf Detr\",\"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 \"Rf Detr\" as a Claude Code skill from https://github.com/roboflow/rf-detr. 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: RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026] 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\":\"roboflow-rf-detr\",\"task\":\"Install Rf Detr\",\"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 \"Rf Detr\" from https://github.com/roboflow/rf-detr 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: RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026] 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\":\"roboflow-rf-detr\",\"task\":\"Install Rf Detr\",\"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/roboflow/rf-detr","github_repo":"roboflow/rf-detr","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"roboflow/rf-detr","recommendation_reasons":["Matches task terms: detr","Useful GitHub adoption: 7,779 stars","Install handoff is available","Repository freshness signal is available","Registry match score 17"],"urls":{"web":"https://www.openagentskill.com/skills/roboflow-rf-detr","api":"https://www.openagentskill.com/api/agent/skills/roboflow-rf-detr","install_api":"https://www.openagentskill.com/api/skills/roboflow-rf-detr/install","audit":"https://www.openagentskill.com/skills/roboflow-rf-detr/audit","repository":"https://github.com/roboflow/rf-detr"}},{"rank":3,"match_type":"related","match_score":12,"raw_match_score":89.3,"semantic_relevance":30,"slug":"coolzhao-geo-sam","name":"Geo SAM","description":"A QGIS plugin tool using Segment Anything Model (SAM) to accelerate segmenting or delineating landforms in geospatial raster images.","tagline":"A QGIS plugin tool using Segment Anything Model (SAM) to accelerate segmenting or delineating landforms in geospatial raster images.","category":"geo-science","tags":["geospatial","analysis","geo-science","deep-learning","pytorch","qgis-plugin","satellite-images","segment-anything-model","segmentation","python"],"author":{"name":"coolzhao","verified":false,"url":"https://github.com/coolzhao"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"coolzhao/Geo-SAM","creatorName":"coolzhao","creatorUrl":"https://github.com/coolzhao","sourceUrl":"https://github.com/coolzhao/Geo-SAM","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/coolzhao-geo-sam#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":413,"forks":54,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":49.02},"quality":{"score":71,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"413","tone":"neutral"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":78,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"413 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":62,"weight":0.08,"status":"info","detail":"413 stars, 54 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add coolzhao/Geo-SAM"},{"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/coolzhao/Geo-SAM"},{"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":"413 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"413 stars, 54 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add coolzhao/Geo-SAM"},{"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/coolzhao/Geo-SAM"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin"],"evidence":{"stars":"413 GitHub stars","repoActivity":"413 stars, 54 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/coolzhao/Geo-SAM","install":"npx skills add coolzhao/Geo-SAM","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 coolzhao/Geo-SAM","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Python","Geospatial","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["geo-science","geospatial","analysis","deep-learning","pytorch","qgis-plugin"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Documentation summary is thin"]},"safety":{"score":69,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Quality score needs review","69/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Quality score needs review"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Quality score needs review","69/100 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":"research-agents","title":"Research agents"},{"slug":"github-automation","title":"GitHub automation"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add coolzhao/Geo-SAM","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":413,"starsLabel":"413","forks":54,"license":"MIT","qualityScore":71,"trustScore":78,"auditScore":81},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":62,"lastPushedAt":"2026-06-21T06:41:35+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Quality score needs review","Documentation summary is thin","Needs review"]},"coverageTags":["Coding","GitHub automation","geo-science","geospatial","analysis","deep-learning","pytorch","qgis-plugin"]},"audit":{"audit_score":81,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Documentation summary is thin"]},"decision":{"readiness_score":70,"readiness_label":"Prototype first","headline":"Fallback candidate for Browser automation","role":"Fallback candidate","primary_fit":"Browser automation","best_for":["Browser automation workflows","general agent builders","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one 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":"coolzhao-geo-sam","name":"Geo SAM","description":"A QGIS plugin tool using Segment Anything Model (SAM) to accelerate segmenting or delineating landforms in geospatial raster images.","category":"geo-science","url":"https://www.openagentskill.com/skills/coolzhao-geo-sam","repository":"https://github.com/coolzhao/Geo-SAM","github_repo":"coolzhao/Geo-SAM"},"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","Search sources","Extract claims"],"suited_agents":["Python","Geospatial","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add coolzhao/Geo-SAM","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 coolzhao-geo-sam"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Geo SAM\" agent skill from https://github.com/coolzhao/Geo-SAM. 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 QGIS plugin tool using Segment Anything Model (SAM) to accelerate segmenting or delineating landforms in geospatial raster 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\":\"coolzhao-geo-sam\",\"task\":\"Install Geo SAM\",\"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 \"Geo SAM\" as a Claude Code skill from https://github.com/coolzhao/Geo-SAM. 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 QGIS plugin tool using Segment Anything Model (SAM) to accelerate segmenting or delineating landforms in geospatial raster 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\":\"coolzhao-geo-sam\",\"task\":\"Install Geo SAM\",\"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 \"Geo SAM\" from https://github.com/coolzhao/Geo-SAM 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 QGIS plugin tool using Segment Anything Model (SAM) to accelerate segmenting or delineating landforms in geospatial raster 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\":\"coolzhao-geo-sam\",\"task\":\"Install Geo SAM\",\"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/coolzhao-geo-sam/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/coolzhao-geo-sam"},"trust":{"score":78,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"413 GitHub stars","repoActivity":"413 stars, 54 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/coolzhao/Geo-SAM","install":"npx skills add coolzhao/Geo-SAM","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":["geo-science","geospatial","analysis","deep-learning","pytorch","qgis-plugin"],"known_risks":["Quality score needs review","Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":81,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":71,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Quality score needs review","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use Geo SAM in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 78/100 Strong shortlist","Audit: 81/100 Needs review","Safety: 69/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"coolzhao-geo-sam (Geo SAM)","install_command":"npx skills add coolzhao/Geo-SAM","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"coolzhao-geo-sam","task":"Use Geo SAM 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/coolzhao-geo-sam","api":"https://www.openagentskill.com/api/agent/skills/coolzhao-geo-sam","audit":"https://www.openagentskill.com/skills/coolzhao-geo-sam/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=coolzhao-geo-sam&task=Use%20Geo%20SAM%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Geo%20SAM%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Geo%20SAM%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/coolzhao-geo-sam/install","manifest":"https://www.openagentskill.com/api/registry/manifest/coolzhao-geo-sam"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"coolzhao-geo-sam","name":"Geo SAM","description":"A QGIS plugin tool using Segment Anything Model (SAM) to accelerate segmenting or delineating landforms in geospatial raster images.","category":"geo-science","url":"https://www.openagentskill.com/skills/coolzhao-geo-sam","repository":"https://github.com/coolzhao/Geo-SAM","github_repo":"coolzhao/Geo-SAM"},"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","Search sources","Extract claims"],"suited_agents":["Python","Geospatial","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add coolzhao/Geo-SAM","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 coolzhao-geo-sam"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Geo SAM\" agent skill from https://github.com/coolzhao/Geo-SAM. 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 QGIS plugin tool using Segment Anything Model (SAM) to accelerate segmenting or delineating landforms in geospatial raster 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\":\"coolzhao-geo-sam\",\"task\":\"Install Geo SAM\",\"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 \"Geo SAM\" as a Claude Code skill from https://github.com/coolzhao/Geo-SAM. 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 QGIS plugin tool using Segment Anything Model (SAM) to accelerate segmenting or delineating landforms in geospatial raster 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\":\"coolzhao-geo-sam\",\"task\":\"Install Geo SAM\",\"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 \"Geo SAM\" from https://github.com/coolzhao/Geo-SAM 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 QGIS plugin tool using Segment Anything Model (SAM) to accelerate segmenting or delineating landforms in geospatial raster 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\":\"coolzhao-geo-sam\",\"task\":\"Install Geo SAM\",\"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/coolzhao-geo-sam/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/coolzhao-geo-sam"},"trust":{"score":78,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"413 GitHub stars","repoActivity":"413 stars, 54 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/coolzhao/Geo-SAM","install":"npx skills add coolzhao/Geo-SAM","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":["geo-science","geospatial","analysis","deep-learning","pytorch","qgis-plugin"],"known_risks":["Quality score needs review","Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":81,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":71,"label":"Strong"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Quality score needs review","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use Geo SAM in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 78/100 Strong shortlist","Audit: 81/100 Needs review","Safety: 69/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"coolzhao-geo-sam (Geo SAM)","install_command":"npx skills add coolzhao/Geo-SAM","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"coolzhao-geo-sam","task":"Use Geo SAM 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/coolzhao-geo-sam","api":"https://www.openagentskill.com/api/agent/skills/coolzhao-geo-sam","audit":"https://www.openagentskill.com/skills/coolzhao-geo-sam/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=coolzhao-geo-sam&task=Use%20Geo%20SAM%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Geo%20SAM%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Geo%20SAM%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/coolzhao-geo-sam/install","manifest":"https://www.openagentskill.com/api/registry/manifest/coolzhao-geo-sam"}},"platforms":["Python","Geospatial"],"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"testing-qa","title":"Testing and QA","url":"https://www.openagentskill.com/use-cases/testing-qa"}],"install":"npx skills add coolzhao/Geo-SAM","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 coolzhao-geo-sam","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 \"Geo SAM\" agent skill from https://github.com/coolzhao/Geo-SAM. 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 QGIS plugin tool using Segment Anything Model (SAM) to accelerate segmenting or delineating landforms in geospatial raster 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\":\"coolzhao-geo-sam\",\"task\":\"Install Geo SAM\",\"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 \"Geo SAM\" as a Claude Code skill from https://github.com/coolzhao/Geo-SAM. 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 QGIS plugin tool using Segment Anything Model (SAM) to accelerate segmenting or delineating landforms in geospatial raster 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\":\"coolzhao-geo-sam\",\"task\":\"Install Geo SAM\",\"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 \"Geo SAM\" from https://github.com/coolzhao/Geo-SAM 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 QGIS plugin tool using Segment Anything Model (SAM) to accelerate segmenting or delineating landforms in geospatial raster 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\":\"coolzhao-geo-sam\",\"task\":\"Install Geo SAM\",\"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/coolzhao/Geo-SAM","github_repo":"coolzhao/Geo-SAM","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"coolzhao/geo-sam","recommendation_reasons":["Matches task terms: sam","Install handoff is available","Repository freshness signal is available","Registry match score 12"],"urls":{"web":"https://www.openagentskill.com/skills/coolzhao-geo-sam","api":"https://www.openagentskill.com/api/agent/skills/coolzhao-geo-sam","install_api":"https://www.openagentskill.com/api/skills/coolzhao-geo-sam/install","audit":"https://www.openagentskill.com/skills/coolzhao-geo-sam/audit","repository":"https://github.com/coolzhao/Geo-SAM"}},{"rank":4,"match_type":"related","match_score":12,"raw_match_score":86.5,"semantic_relevance":30,"slug":"zhanggongjie-meta-detr","name":"Meta DETR","description":"[T-PAMI  2022]  Meta-DETR for Few-Shot Object Detection: Official PyTorch Implementation","tagline":"[T-PAMI  2022]  Meta-DETR for Few-Shot Object Detection: Official PyTorch Implementation","category":"robotics-iot","tags":["computer-vision","automation","robotics-iot","few-shot-object-detection","meta-learning","object-detection","pytorch","python","github"],"author":{"name":"ZhangGongjie","verified":false,"url":"https://github.com/ZhangGongjie"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"ZhangGongjie/Meta-DETR","creatorName":"ZhangGongjie","creatorUrl":"https://github.com/ZhangGongjie","sourceUrl":"https://github.com/ZhangGongjie/Meta-DETR","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/zhanggongjie-meta-detr#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":436,"forks":79,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":37.18},"quality":{"score":47,"tier":"review","label":"Needs review","summary":"Inspect the repository carefully before adding it to an agent workflow.","signals":[{"label":"GitHub stars","value":"436","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":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":62,"weight":0.13,"status":"info","detail":"436 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":62,"weight":0.08,"status":"info","detail":"436 stars, 79 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 ZhangGongjie/Meta-DETR"},{"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/ZhangGongjie/Meta-DETR"},{"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":"436 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"436 stars, 79 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 ZhangGongjie/Meta-DETR"},{"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/ZhangGongjie/Meta-DETR"},{"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: 4y since push"],"evidence":{"stars":"436 GitHub stars","repoActivity":"436 stars, 79 forks","lastPushed":"4y since push","license":"MIT","repository":"https://github.com/ZhangGongjie/Meta-DETR","install":"npx skills add ZhangGongjie/Meta-DETR","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 ZhangGongjie/Meta-DETR","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","few-shot-object-detection","meta-learning","object-detection"],"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":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","Python"],"install":{"ready":true,"command":"npx skills add ZhangGongjie/Meta-DETR","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":436,"starsLabel":"436","forks":79,"license":"MIT","qualityScore":47,"trustScore":71,"auditScore":62},"maintenance":{"status":"stale","label":"4y since push","daysSincePush":1462,"lastPushedAt":"2022-08-21T08:09:08+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: 4y since push"]},"coverageTags":["Coding","GitHub automation","robotics-iot","computer-vision","automation","few-shot-object-detection","meta-learning","object-detection"]},"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","Recent maintenance: 4y since push"]},"decision":{"readiness_score":37,"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":"zhanggongjie-meta-detr","name":"Meta DETR","description":"[T-PAMI  2022]  Meta-DETR for Few-Shot Object Detection: Official PyTorch Implementation","category":"robotics-iot","url":"https://www.openagentskill.com/skills/zhanggongjie-meta-detr","repository":"https://github.com/ZhangGongjie/Meta-DETR","github_repo":"ZhangGongjie/Meta-DETR"},"suited_tasks":["GitHub automation workflows","general agent builders","builders willing to evaluate younger projects","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add ZhangGongjie/Meta-DETR","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 zhanggongjie-meta-detr"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Meta DETR\" agent skill from https://github.com/ZhangGongjie/Meta-DETR. 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: [T-PAMI 2022] Meta-DETR for Few-Shot Object Detection: Official PyTorch Implementation 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\":\"zhanggongjie-meta-detr\",\"task\":\"Install Meta DETR\",\"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 \"Meta DETR\" as a Claude Code skill from https://github.com/ZhangGongjie/Meta-DETR. 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: [T-PAMI 2022] Meta-DETR for Few-Shot Object Detection: Official PyTorch Implementation 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\":\"zhanggongjie-meta-detr\",\"task\":\"Install Meta DETR\",\"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 \"Meta DETR\" from https://github.com/ZhangGongjie/Meta-DETR 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: [T-PAMI 2022] Meta-DETR for Few-Shot Object Detection: Official PyTorch Implementation 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\":\"zhanggongjie-meta-detr\",\"task\":\"Install Meta DETR\",\"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/zhanggongjie-meta-detr/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/zhanggongjie-meta-detr"},"trust":{"score":71,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"436 GitHub stars","repoActivity":"436 stars, 79 forks","lastPushed":"4y since push","license":"MIT","repository":"https://github.com/ZhangGongjie/Meta-DETR","install":"npx skills add ZhangGongjie/Meta-DETR","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","few-shot-object-detection","meta-learning","object-detection"],"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":62,"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: 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":47,"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","Recent maintenance: 4y since push"],"agent_contract":{"task_input":"Use Meta DETR 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: 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":"zhanggongjie-meta-detr (Meta DETR)","install_command":"npx skills add ZhangGongjie/Meta-DETR","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":"zhanggongjie-meta-detr","task":"Use Meta DETR 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/zhanggongjie-meta-detr","api":"https://www.openagentskill.com/api/agent/skills/zhanggongjie-meta-detr","audit":"https://www.openagentskill.com/skills/zhanggongjie-meta-detr/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=zhanggongjie-meta-detr&task=Use%20Meta%20DETR%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Meta%20DETR%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Meta%20DETR%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/zhanggongjie-meta-detr/install","manifest":"https://www.openagentskill.com/api/registry/manifest/zhanggongjie-meta-detr"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"zhanggongjie-meta-detr","name":"Meta DETR","description":"[T-PAMI  2022]  Meta-DETR for Few-Shot Object Detection: Official PyTorch Implementation","category":"robotics-iot","url":"https://www.openagentskill.com/skills/zhanggongjie-meta-detr","repository":"https://github.com/ZhangGongjie/Meta-DETR","github_repo":"ZhangGongjie/Meta-DETR"},"suited_tasks":["GitHub automation workflows","general agent builders","builders willing to evaluate younger projects","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add ZhangGongjie/Meta-DETR","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 zhanggongjie-meta-detr"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Meta DETR\" agent skill from https://github.com/ZhangGongjie/Meta-DETR. 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: [T-PAMI 2022] Meta-DETR for Few-Shot Object Detection: Official PyTorch Implementation 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\":\"zhanggongjie-meta-detr\",\"task\":\"Install Meta DETR\",\"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 \"Meta DETR\" as a Claude Code skill from https://github.com/ZhangGongjie/Meta-DETR. 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: [T-PAMI 2022] Meta-DETR for Few-Shot Object Detection: Official PyTorch Implementation 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\":\"zhanggongjie-meta-detr\",\"task\":\"Install Meta DETR\",\"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 \"Meta DETR\" from https://github.com/ZhangGongjie/Meta-DETR 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: [T-PAMI 2022] Meta-DETR for Few-Shot Object Detection: Official PyTorch Implementation 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\":\"zhanggongjie-meta-detr\",\"task\":\"Install Meta DETR\",\"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/zhanggongjie-meta-detr/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/zhanggongjie-meta-detr"},"trust":{"score":71,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"436 GitHub stars","repoActivity":"436 stars, 79 forks","lastPushed":"4y since push","license":"MIT","repository":"https://github.com/ZhangGongjie/Meta-DETR","install":"npx skills add ZhangGongjie/Meta-DETR","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","few-shot-object-detection","meta-learning","object-detection"],"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":62,"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: 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":47,"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","Recent maintenance: 4y since push"],"agent_contract":{"task_input":"Use Meta DETR 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: 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":"zhanggongjie-meta-detr (Meta DETR)","install_command":"npx skills add ZhangGongjie/Meta-DETR","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":"zhanggongjie-meta-detr","task":"Use Meta DETR 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/zhanggongjie-meta-detr","api":"https://www.openagentskill.com/api/agent/skills/zhanggongjie-meta-detr","audit":"https://www.openagentskill.com/skills/zhanggongjie-meta-detr/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=zhanggongjie-meta-detr&task=Use%20Meta%20DETR%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Meta%20DETR%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Meta%20DETR%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/zhanggongjie-meta-detr/install","manifest":"https://www.openagentskill.com/api/registry/manifest/zhanggongjie-meta-detr"}},"platforms":["Python","Computer Vision"],"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 ZhangGongjie/Meta-DETR","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 zhanggongjie-meta-detr","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 \"Meta DETR\" agent skill from https://github.com/ZhangGongjie/Meta-DETR. 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: [T-PAMI 2022] Meta-DETR for Few-Shot Object Detection: Official PyTorch Implementation 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\":\"zhanggongjie-meta-detr\",\"task\":\"Install Meta DETR\",\"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 \"Meta DETR\" as a Claude Code skill from https://github.com/ZhangGongjie/Meta-DETR. 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: [T-PAMI 2022] Meta-DETR for Few-Shot Object Detection: Official PyTorch Implementation 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\":\"zhanggongjie-meta-detr\",\"task\":\"Install Meta DETR\",\"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 \"Meta DETR\" from https://github.com/ZhangGongjie/Meta-DETR 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: [T-PAMI 2022] Meta-DETR for Few-Shot Object Detection: Official PyTorch Implementation 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\":\"zhanggongjie-meta-detr\",\"task\":\"Install Meta DETR\",\"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/ZhangGongjie/Meta-DETR","github_repo":"ZhangGongjie/Meta-DETR","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"zhanggongjie/meta-detr","recommendation_reasons":["Matches task terms: detr","Install handoff is available","Repository freshness signal is available","Registry match score 12"],"urls":{"web":"https://www.openagentskill.com/skills/zhanggongjie-meta-detr","api":"https://www.openagentskill.com/api/agent/skills/zhanggongjie-meta-detr","install_api":"https://www.openagentskill.com/api/skills/zhanggongjie-meta-detr/install","audit":"https://www.openagentskill.com/skills/zhanggongjie-meta-detr/audit","repository":"https://github.com/ZhangGongjie/Meta-DETR"}},{"rank":5,"match_type":"related","match_score":11,"raw_match_score":84.9,"semantic_relevance":30,"slug":"wjun0830-qd-detr","name":"QD DETR","description":"Official pytorch repository for \"QD-DETR : Query-Dependent Video Representation for Moment Retrieval and Highlight Detection\" (CVPR 2023 Paper)","tagline":"Official pytorch repository for \"QD-DETR : Query-Dependent Video Representation for Moment Retrieval and Highlight Detection\" (CVPR 2023 Paper)","category":"robotics-iot","tags":["computer-vision","automation","robotics-iot","deep-learning","detection-transformer","moment-retrieval","multi-modal","text-video-retrieval","video-highlight-detection","video-retrieval"],"author":{"name":"wjun0830","verified":false,"url":"https://github.com/wjun0830"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"wjun0830/QD-DETR","creatorName":"wjun0830","creatorUrl":"https://github.com/wjun0830","sourceUrl":"https://github.com/wjun0830/QD-DETR","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/wjun0830-qd-detr#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":251,"forks":20,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":35.51},"quality":{"score":39,"tier":"review","label":"Needs review","summary":"Inspect the repository carefully before adding it to an agent workflow.","signals":[{"label":"GitHub stars","value":"251","tone":"neutral"},{"label":"Freshness","value":"1y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":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":"251 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"251 stars, 20 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":38,"weight":0.14,"status":"fail","detail":"1y since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":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 wjun0830/QD-DETR"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"weight":0.07,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/wjun0830/QD-DETR"},{"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":"251 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"251 stars, 20 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"1y since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add wjun0830/QD-DETR"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"filesystem or document access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/wjun0830/QD-DETR"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Install command has no obvious high-risk pattern"],"warnings":["License is unclear","Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 251 stars, 20 forks; issue activity unavailable in current metadata","Recent maintenance: 1y since push","License clarity: Unknown"],"evidence":{"stars":"251 GitHub stars","repoActivity":"251 stars, 20 forks","lastPushed":"1y since push","license":"Unknown","repository":"https://github.com/wjun0830/QD-DETR","install":"npx skills add wjun0830/QD-DETR","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add wjun0830/QD-DETR","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","No Agent Proven outcome evidence yet","1y since push"]},"agentCompatibility":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 251 stars, 20 forks; issue activity unavailable in current metadata"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["robotics-iot","computer-vision","automation","deep-learning","detection-transformer","moment-retrieval"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 251 stars, 20 forks; issue activity unavailable in current metadata","Recent maintenance: 1y since push","License clarity: Unknown"]},"safety":{"score":40,"level":"avoid_auto_install","label":"Avoid automatic install","safety_tier":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","summary":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","auto_install_policy":"review","reasons":["License is unclear","40/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"},{"id":"database","label":"Database access","reason":"Skill may inspect schemas, query databases, or work with persistent stores.","severity":"medium"}],"policy_warnings":["License is unclear"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","reasons":["License is unclear","40/100 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":"multimodal-media","title":"Multimodal media"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add wjun0830/QD-DETR","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":251,"starsLabel":"251","forks":20,"license":"Unknown","qualityScore":39,"trustScore":68,"auditScore":60},"maintenance":{"status":"stale","label":"1y since push","daysSincePush":376,"lastPushedAt":"2025-08-12T00:28:17+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["License is unclear","Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin"]},"coverageTags":["Coding","GitHub automation","robotics-iot","computer-vision","automation","deep-learning","detection-transformer","moment-retrieval"]},"audit":{"audit_score":60,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin"]},"decision":{"readiness_score":29,"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":"wjun0830-qd-detr","name":"QD DETR","description":"Official pytorch repository for \"QD-DETR : Query-Dependent Video Representation for Moment Retrieval and Highlight Detection\" (CVPR 2023 Paper)","category":"robotics-iot","url":"https://www.openagentskill.com/skills/wjun0830-qd-detr","repository":"https://github.com/wjun0830/QD-DETR","github_repo":"wjun0830/QD-DETR"},"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":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add wjun0830/QD-DETR","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 wjun0830-qd-detr"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"QD DETR\" agent skill from https://github.com/wjun0830/QD-DETR. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Official pytorch repository for \"QD-DETR : Query-Dependent Video Representation for Moment Retrieval and Highlight Detection\" (CVPR 2023 Paper) 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\":\"wjun0830-qd-detr\",\"task\":\"Install QD DETR\",\"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 \"QD DETR\" as a Claude Code skill from https://github.com/wjun0830/QD-DETR. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Official pytorch repository for \"QD-DETR : Query-Dependent Video Representation for Moment Retrieval and Highlight Detection\" (CVPR 2023 Paper) 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\":\"wjun0830-qd-detr\",\"task\":\"Install QD DETR\",\"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 \"QD DETR\" from https://github.com/wjun0830/QD-DETR into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Official pytorch repository for \"QD-DETR : Query-Dependent Video Representation for Moment Retrieval and Highlight Detection\" (CVPR 2023 Paper) 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\":\"wjun0830-qd-detr\",\"task\":\"Install QD DETR\",\"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/wjun0830-qd-detr/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/wjun0830-qd-detr"},"trust":{"score":68,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"251 GitHub stars","repoActivity":"251 stars, 20 forks","lastPushed":"1y since push","license":"Unknown","repository":"https://github.com/wjun0830/QD-DETR","install":"npx skills add wjun0830/QD-DETR","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["robotics-iot","computer-vision","automation","deep-learning","detection-transformer","moment-retrieval"],"known_risks":["License is unclear","Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 251 stars, 20 forks; issue activity unavailable in current metadata","Recent maintenance: 1y since push","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":60,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 251 stars, 20 forks; issue activity unavailable in current metadata","Recent maintenance: 1y since push","License clarity: Unknown"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":39,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"1y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","License is unclear","Repository appears stale","Quality score needs review","Documentation summary is thin"],"agent_contract":{"task_input":"Use QD DETR 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: 40/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"wjun0830-qd-detr (QD DETR)","install_command":"npx skills add wjun0830/QD-DETR","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":"wjun0830-qd-detr","task":"Use QD DETR 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/wjun0830-qd-detr","api":"https://www.openagentskill.com/api/agent/skills/wjun0830-qd-detr","audit":"https://www.openagentskill.com/skills/wjun0830-qd-detr/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=wjun0830-qd-detr&task=Use%20QD%20DETR%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20QD%20DETR%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20QD%20DETR%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/wjun0830-qd-detr/install","manifest":"https://www.openagentskill.com/api/registry/manifest/wjun0830-qd-detr"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"wjun0830-qd-detr","name":"QD DETR","description":"Official pytorch repository for \"QD-DETR : Query-Dependent Video Representation for Moment Retrieval and Highlight Detection\" (CVPR 2023 Paper)","category":"robotics-iot","url":"https://www.openagentskill.com/skills/wjun0830-qd-detr","repository":"https://github.com/wjun0830/QD-DETR","github_repo":"wjun0830/QD-DETR"},"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":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add wjun0830/QD-DETR","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 wjun0830-qd-detr"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"QD DETR\" agent skill from https://github.com/wjun0830/QD-DETR. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Official pytorch repository for \"QD-DETR : Query-Dependent Video Representation for Moment Retrieval and Highlight Detection\" (CVPR 2023 Paper) 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\":\"wjun0830-qd-detr\",\"task\":\"Install QD DETR\",\"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 \"QD DETR\" as a Claude Code skill from https://github.com/wjun0830/QD-DETR. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Official pytorch repository for \"QD-DETR : Query-Dependent Video Representation for Moment Retrieval and Highlight Detection\" (CVPR 2023 Paper) 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\":\"wjun0830-qd-detr\",\"task\":\"Install QD DETR\",\"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 \"QD DETR\" from https://github.com/wjun0830/QD-DETR into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Official pytorch repository for \"QD-DETR : Query-Dependent Video Representation for Moment Retrieval and Highlight Detection\" (CVPR 2023 Paper) 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\":\"wjun0830-qd-detr\",\"task\":\"Install QD DETR\",\"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/wjun0830-qd-detr/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/wjun0830-qd-detr"},"trust":{"score":68,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"251 GitHub stars","repoActivity":"251 stars, 20 forks","lastPushed":"1y since push","license":"Unknown","repository":"https://github.com/wjun0830/QD-DETR","install":"npx skills add wjun0830/QD-DETR","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["robotics-iot","computer-vision","automation","deep-learning","detection-transformer","moment-retrieval"],"known_risks":["License is unclear","Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 251 stars, 20 forks; issue activity unavailable in current metadata","Recent maintenance: 1y since push","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":60,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 251 stars, 20 forks; issue activity unavailable in current metadata","Recent maintenance: 1y since push","License clarity: Unknown"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":39,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"1y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","License is unclear","Repository appears stale","Quality score needs review","Documentation summary is thin"],"agent_contract":{"task_input":"Use QD DETR 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: 40/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"wjun0830-qd-detr (QD DETR)","install_command":"npx skills add wjun0830/QD-DETR","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":"wjun0830-qd-detr","task":"Use QD DETR 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/wjun0830-qd-detr","api":"https://www.openagentskill.com/api/agent/skills/wjun0830-qd-detr","audit":"https://www.openagentskill.com/skills/wjun0830-qd-detr/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=wjun0830-qd-detr&task=Use%20QD%20DETR%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20QD%20DETR%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20QD%20DETR%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/wjun0830-qd-detr/install","manifest":"https://www.openagentskill.com/api/registry/manifest/wjun0830-qd-detr"}},"platforms":["Python","Computer Vision"],"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":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"}],"install":"npx skills add wjun0830/QD-DETR","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 wjun0830-qd-detr","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 \"QD DETR\" agent skill from https://github.com/wjun0830/QD-DETR. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Official pytorch repository for \"QD-DETR : Query-Dependent Video Representation for Moment Retrieval and Highlight Detection\" (CVPR 2023 Paper) 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\":\"wjun0830-qd-detr\",\"task\":\"Install QD DETR\",\"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 \"QD DETR\" as a Claude Code skill from https://github.com/wjun0830/QD-DETR. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Official pytorch repository for \"QD-DETR : Query-Dependent Video Representation for Moment Retrieval and Highlight Detection\" (CVPR 2023 Paper) 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\":\"wjun0830-qd-detr\",\"task\":\"Install QD DETR\",\"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 \"QD DETR\" from https://github.com/wjun0830/QD-DETR into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Official pytorch repository for \"QD-DETR : Query-Dependent Video Representation for Moment Retrieval and Highlight Detection\" (CVPR 2023 Paper) 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\":\"wjun0830-qd-detr\",\"task\":\"Install QD DETR\",\"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/wjun0830/QD-DETR","github_repo":"wjun0830/QD-DETR","version":"1.0.0","license":"Unknown","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"wjun0830/qd-detr","recommendation_reasons":["Matches task terms: detr","Install handoff is available","Repository freshness signal is available","Registry match score 11"],"urls":{"web":"https://www.openagentskill.com/skills/wjun0830-qd-detr","api":"https://www.openagentskill.com/api/agent/skills/wjun0830-qd-detr","install_api":"https://www.openagentskill.com/api/skills/wjun0830-qd-detr/install","audit":"https://www.openagentskill.com/skills/wjun0830-qd-detr/audit","repository":"https://github.com/wjun0830/QD-DETR"}},{"rank":6,"match_type":"related","match_score":9,"raw_match_score":70.5,"semantic_relevance":30,"slug":"vietanhdev-anylabeling","name":"Anylabeling","description":"Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2/2.1+SAM3), MobileSAM!!","tagline":"Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2/2.1+SAM3), MobileSAM!!","category":"robotics-iot","tags":["computer-vision","automation","robotics-iot","auto-labeling","labeling","labeling-tool","mobilesam","onnx","sam2","segment-anything"],"author":{"name":"vietanhdev","verified":true,"url":"https://github.com/vietanhdev"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"vietanhdev/anylabeling","creatorName":"vietanhdev","creatorUrl":"https://github.com/vietanhdev","sourceUrl":"https://github.com/vietanhdev/anylabeling","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/vietanhdev-anylabeling#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":3391,"forks":345,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":59.41},"quality":{"score":91,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"3.4K","tone":"positive"},{"label":"Freshness","value":"4mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"GPL-3.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":86,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"3.4K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"3.4K stars, 345 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"4mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"GPL-3.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add vietanhdev/anylabeling"},{"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/vietanhdev/anylabeling"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"3.4K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"3.4K stars, 345 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"4mo since push"},{"status":"pass","label":"License clarity","detail":"GPL-3.0"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add vietanhdev/anylabeling"},{"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/vietanhdev/anylabeling"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin"],"evidence":{"stars":"3.4K GitHub stars","repoActivity":"3.4K stars, 345 forks","lastPushed":"4mo since push","license":"GPL-3.0","repository":"https://github.com/vietanhdev/anylabeling","install":"npx skills add vietanhdev/anylabeling","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 vietanhdev/anylabeling","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","4mo since push"]},"agentCompatibility":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["robotics-iot","computer-vision","automation","auto-labeling","labeling","labeling-tool"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin"]},"safety":{"score":75,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","75/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","75/100 agent safety score"]},"supply_profile":{"track":{"slug":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Multimodal media","description":"I need my agent to process images, video, or audio and extract useful information.","useCases":[{"slug":"browser-automation","title":"Browser automation"},{"slug":"workflow-automation","title":"Workflow automation"},{"slug":"multimodal-media","title":"Multimodal media"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add vietanhdev/anylabeling","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":3391,"starsLabel":"3.4K","forks":345,"license":"GPL-3.0","qualityScore":91,"trustScore":86,"auditScore":87},"maintenance":{"status":"active","label":"4mo since push","daysSincePush":120,"lastPushedAt":"2026-04-25T04:46:10+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Design","Multimodal media","robotics-iot","computer-vision","automation","auto-labeling","labeling","labeling-tool"]},"audit":{"audit_score":87,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Browser automation","role":"Primary pick","primary_fit":"Browser automation","best_for":["Browser automation workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Browser automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"vietanhdev-anylabeling","name":"Anylabeling","description":"Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2/2.1+SAM3), MobileSAM!!","category":"robotics-iot","url":"https://www.openagentskill.com/skills/vietanhdev-anylabeling","repository":"https://github.com/vietanhdev/anylabeling","github_repo":"vietanhdev/anylabeling"},"suited_tasks":["Browser automation workflows","general agent builders","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Move data between tools","Transform files"],"suited_agents":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add vietanhdev/anylabeling","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 vietanhdev-anylabeling"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Anylabeling\" agent skill from https://github.com/vietanhdev/anylabeling. 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: Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2/2.1+SAM3), MobileSAM!! 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\":\"vietanhdev-anylabeling\",\"task\":\"Install Anylabeling\",\"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 \"Anylabeling\" as a Claude Code skill from https://github.com/vietanhdev/anylabeling. 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: Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2/2.1+SAM3), MobileSAM!! 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\":\"vietanhdev-anylabeling\",\"task\":\"Install Anylabeling\",\"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 \"Anylabeling\" from https://github.com/vietanhdev/anylabeling 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: Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2/2.1+SAM3), MobileSAM!! 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\":\"vietanhdev-anylabeling\",\"task\":\"Install Anylabeling\",\"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/vietanhdev-anylabeling/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/vietanhdev-anylabeling"},"trust":{"score":86,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"3.4K GitHub stars","repoActivity":"3.4K stars, 345 forks","lastPushed":"4mo since push","license":"GPL-3.0","repository":"https://github.com/vietanhdev/anylabeling","install":"npx skills add vietanhdev/anylabeling","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["robotics-iot","computer-vision","automation","auto-labeling","labeling","labeling-tool"],"known_risks":["Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":87,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":91,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"4mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Anylabeling in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 86/100 Production candidate","Audit: 87/100 Safe to try","Safety: 75/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"vietanhdev-anylabeling (Anylabeling)","install_command":"npx skills add vietanhdev/anylabeling","risk_summary":"Safe to try; Reviewed; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"vietanhdev-anylabeling","task":"Use Anylabeling 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/vietanhdev-anylabeling","api":"https://www.openagentskill.com/api/agent/skills/vietanhdev-anylabeling","audit":"https://www.openagentskill.com/skills/vietanhdev-anylabeling/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=vietanhdev-anylabeling&task=Use%20Anylabeling%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Anylabeling%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Anylabeling%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/vietanhdev-anylabeling/install","manifest":"https://www.openagentskill.com/api/registry/manifest/vietanhdev-anylabeling"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"vietanhdev-anylabeling","name":"Anylabeling","description":"Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2/2.1+SAM3), MobileSAM!!","category":"robotics-iot","url":"https://www.openagentskill.com/skills/vietanhdev-anylabeling","repository":"https://github.com/vietanhdev/anylabeling","github_repo":"vietanhdev/anylabeling"},"suited_tasks":["Browser automation workflows","general agent builders","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Move data between tools","Transform files"],"suited_agents":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add vietanhdev/anylabeling","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 vietanhdev-anylabeling"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Anylabeling\" agent skill from https://github.com/vietanhdev/anylabeling. 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: Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2/2.1+SAM3), MobileSAM!! 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\":\"vietanhdev-anylabeling\",\"task\":\"Install Anylabeling\",\"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 \"Anylabeling\" as a Claude Code skill from https://github.com/vietanhdev/anylabeling. 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: Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2/2.1+SAM3), MobileSAM!! 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\":\"vietanhdev-anylabeling\",\"task\":\"Install Anylabeling\",\"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 \"Anylabeling\" from https://github.com/vietanhdev/anylabeling 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: Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2/2.1+SAM3), MobileSAM!! 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\":\"vietanhdev-anylabeling\",\"task\":\"Install Anylabeling\",\"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/vietanhdev-anylabeling/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/vietanhdev-anylabeling"},"trust":{"score":86,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"3.4K GitHub stars","repoActivity":"3.4K stars, 345 forks","lastPushed":"4mo since push","license":"GPL-3.0","repository":"https://github.com/vietanhdev/anylabeling","install":"npx skills add vietanhdev/anylabeling","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["robotics-iot","computer-vision","automation","auto-labeling","labeling","labeling-tool"],"known_risks":["Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":87,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":91,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"4mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Anylabeling in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 86/100 Production candidate","Audit: 87/100 Safe to try","Safety: 75/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"vietanhdev-anylabeling (Anylabeling)","install_command":"npx skills add vietanhdev/anylabeling","risk_summary":"Safe to try; Reviewed; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"vietanhdev-anylabeling","task":"Use Anylabeling 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/vietanhdev-anylabeling","api":"https://www.openagentskill.com/api/agent/skills/vietanhdev-anylabeling","audit":"https://www.openagentskill.com/skills/vietanhdev-anylabeling/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=vietanhdev-anylabeling&task=Use%20Anylabeling%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Anylabeling%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Anylabeling%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/vietanhdev-anylabeling/install","manifest":"https://www.openagentskill.com/api/registry/manifest/vietanhdev-anylabeling"}},"platforms":["Python","Computer Vision"],"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"slug":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"},{"slug":"customer-support","title":"Customer support","url":"https://www.openagentskill.com/use-cases/customer-support"}],"install":"npx skills add vietanhdev/anylabeling","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 vietanhdev-anylabeling","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 \"Anylabeling\" agent skill from https://github.com/vietanhdev/anylabeling. 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: Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2/2.1+SAM3), MobileSAM!! 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\":\"vietanhdev-anylabeling\",\"task\":\"Install Anylabeling\",\"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 \"Anylabeling\" as a Claude Code skill from https://github.com/vietanhdev/anylabeling. 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: Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2/2.1+SAM3), MobileSAM!! 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\":\"vietanhdev-anylabeling\",\"task\":\"Install Anylabeling\",\"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 \"Anylabeling\" from https://github.com/vietanhdev/anylabeling 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: Effortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2/2.1+SAM3), MobileSAM!! 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\":\"vietanhdev-anylabeling\",\"task\":\"Install Anylabeling\",\"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/vietanhdev/anylabeling","github_repo":"vietanhdev/anylabeling","version":"1.0.0","license":"GPL-3.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"vietanhdev/anylabeling","recommendation_reasons":["Matches task terms: sam","Useful GitHub adoption: 3,391 stars","Install handoff is available","Repository freshness signal is available","Registry match score 9"],"urls":{"web":"https://www.openagentskill.com/skills/vietanhdev-anylabeling","api":"https://www.openagentskill.com/api/agent/skills/vietanhdev-anylabeling","install_api":"https://www.openagentskill.com/api/skills/vietanhdev-anylabeling/install","audit":"https://www.openagentskill.com/skills/vietanhdev-anylabeling/audit","repository":"https://github.com/vietanhdev/anylabeling"}},{"rank":7,"match_type":"related","match_score":9,"raw_match_score":68.1,"semantic_relevance":30,"slug":"yatenglg-isat-with-segment-anything","name":"ISAT With Segment Anything","description":"Labeling tool with SAM(segment anything model),supports SAM, SAM2, SAM3, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具","tagline":"Labeling tool with SAM(segment anything model),supports SAM, SAM2, SAM3, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具","category":"robotics-iot","tags":["computer-vision","automation","robotics-iot","annotation-tool","labeling","labeling-tool","sam","sam2","sam3","segment-anything"],"author":{"name":"yatengLG","verified":true,"url":"https://github.com/yatengLG"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"yatengLG/ISAT_with_segment_anything","creatorName":"yatengLG","creatorUrl":"https://github.com/yatengLG","sourceUrl":"https://github.com/yatengLG/ISAT_with_segment_anything","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/yatenglg-isat-with-segment-anything#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":2130,"forks":207,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":54},"quality":{"score":76,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"2.1K","tone":"positive"},{"label":"Freshness","value":"7mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":81,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"2.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":77,"weight":0.08,"status":"info","detail":"2.1K stars, 207 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":62,"weight":0.14,"status":"info","detail":"7mo since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"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 yatengLG/ISAT_with_segment_anything"},{"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/yatengLG/ISAT_with_segment_anything"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"2.1K GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"2.1K stars, 207 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"7mo since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add yatengLG/ISAT_with_segment_anything"},{"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/yatengLG/ISAT_with_segment_anything"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"],"evidence":{"stars":"2.1K GitHub stars","repoActivity":"2.1K stars, 207 forks","lastPushed":"7mo since push","license":"Unknown","repository":"https://github.com/yatengLG/ISAT_with_segment_anything","install":"npx skills add yatengLG/ISAT_with_segment_anything","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 yatengLG/ISAT_with_segment_anything","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","No Agent Proven outcome evidence yet","7mo since push"]},"agentCompatibility":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["robotics-iot","computer-vision","automation","annotation-tool","labeling","labeling-tool"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"]},"safety":{"score":66,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["License is unclear","66/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["License is unclear"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["License is unclear","66/100 agent safety score"]},"supply_profile":{"track":{"slug":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Multimodal media","description":"I need my agent to process images, video, or audio and extract useful information.","useCases":[{"slug":"browser-automation","title":"Browser automation"},{"slug":"workflow-automation","title":"Workflow automation"},{"slug":"multimodal-media","title":"Multimodal media"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add yatengLG/ISAT_with_segment_anything","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":2130,"starsLabel":"2.1K","forks":207,"license":"Unknown","qualityScore":76,"trustScore":81,"auditScore":78},"maintenance":{"status":"stable","label":"7mo since push","daysSincePush":204,"lastPushedAt":"2026-01-30T08:10:13+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["License is unclear","Documentation summary is thin","Quality score needs review","License clarity: Unknown","Needs review"]},"coverageTags":["Design","Multimodal media","robotics-iot","computer-vision","automation","annotation-tool","labeling","labeling-tool"]},"audit":{"audit_score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","Quality score needs review","License clarity: Unknown"]},"decision":{"readiness_score":78,"readiness_label":"Strong shortlist","headline":"Companion skill for Browser automation","role":"Companion skill","primary_fit":"Browser automation","best_for":["Browser automation workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Browser automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"yatenglg-isat-with-segment-anything","name":"ISAT With Segment Anything","description":"Labeling tool with SAM(segment anything model),supports SAM, SAM2, SAM3, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具","category":"robotics-iot","url":"https://www.openagentskill.com/skills/yatenglg-isat-with-segment-anything","repository":"https://github.com/yatengLG/ISAT_with_segment_anything","github_repo":"yatengLG/ISAT_with_segment_anything"},"suited_tasks":["Browser automation workflows","general agent builders","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Move data between tools","Transform files"],"suited_agents":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add yatengLG/ISAT_with_segment_anything","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 yatenglg-isat-with-segment-anything"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"ISAT With Segment Anything\" agent skill from https://github.com/yatengLG/ISAT_with_segment_anything. 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: Labeling tool with SAM(segment anything model),supports SAM, SAM2, SAM3, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具 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\":\"yatenglg-isat-with-segment-anything\",\"task\":\"Install ISAT With Segment Anything\",\"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 \"ISAT With Segment Anything\" as a Claude Code skill from https://github.com/yatengLG/ISAT_with_segment_anything. 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: Labeling tool with SAM(segment anything model),supports SAM, SAM2, SAM3, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具 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\":\"yatenglg-isat-with-segment-anything\",\"task\":\"Install ISAT With Segment Anything\",\"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 \"ISAT With Segment Anything\" from https://github.com/yatengLG/ISAT_with_segment_anything 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: Labeling tool with SAM(segment anything model),supports SAM, SAM2, SAM3, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具 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\":\"yatenglg-isat-with-segment-anything\",\"task\":\"Install ISAT With Segment Anything\",\"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/yatenglg-isat-with-segment-anything/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/yatenglg-isat-with-segment-anything"},"trust":{"score":81,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"2.1K GitHub stars","repoActivity":"2.1K stars, 207 forks","lastPushed":"7mo since push","license":"Unknown","repository":"https://github.com/yatengLG/ISAT_with_segment_anything","install":"npx skills add yatengLG/ISAT_with_segment_anything","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","annotation-tool","labeling","labeling-tool"],"known_risks":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","Quality score needs review","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":76,"label":"Strong"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"7mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","Quality score needs review","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use ISAT With Segment Anything in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 81/100 Strong shortlist","Audit: 78/100 Needs review","Safety: 66/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"yatenglg-isat-with-segment-anything (ISAT With Segment Anything)","install_command":"npx skills add yatengLG/ISAT_with_segment_anything","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"yatenglg-isat-with-segment-anything","task":"Use ISAT With Segment Anything 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/yatenglg-isat-with-segment-anything","api":"https://www.openagentskill.com/api/agent/skills/yatenglg-isat-with-segment-anything","audit":"https://www.openagentskill.com/skills/yatenglg-isat-with-segment-anything/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=yatenglg-isat-with-segment-anything&task=Use%20ISAT%20With%20Segment%20Anything%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20ISAT%20With%20Segment%20Anything%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20ISAT%20With%20Segment%20Anything%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/yatenglg-isat-with-segment-anything/install","manifest":"https://www.openagentskill.com/api/registry/manifest/yatenglg-isat-with-segment-anything"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"yatenglg-isat-with-segment-anything","name":"ISAT With Segment Anything","description":"Labeling tool with SAM(segment anything model),supports SAM, SAM2, SAM3, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具","category":"robotics-iot","url":"https://www.openagentskill.com/skills/yatenglg-isat-with-segment-anything","repository":"https://github.com/yatengLG/ISAT_with_segment_anything","github_repo":"yatengLG/ISAT_with_segment_anything"},"suited_tasks":["Browser automation workflows","general agent builders","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Move data between tools","Transform files"],"suited_agents":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add yatengLG/ISAT_with_segment_anything","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 yatenglg-isat-with-segment-anything"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"ISAT With Segment Anything\" agent skill from https://github.com/yatengLG/ISAT_with_segment_anything. 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: Labeling tool with SAM(segment anything model),supports SAM, SAM2, SAM3, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具 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\":\"yatenglg-isat-with-segment-anything\",\"task\":\"Install ISAT With Segment Anything\",\"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 \"ISAT With Segment Anything\" as a Claude Code skill from https://github.com/yatengLG/ISAT_with_segment_anything. 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: Labeling tool with SAM(segment anything model),supports SAM, SAM2, SAM3, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具 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\":\"yatenglg-isat-with-segment-anything\",\"task\":\"Install ISAT With Segment Anything\",\"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 \"ISAT With Segment Anything\" from https://github.com/yatengLG/ISAT_with_segment_anything 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: Labeling tool with SAM(segment anything model),supports SAM, SAM2, SAM3, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具 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\":\"yatenglg-isat-with-segment-anything\",\"task\":\"Install ISAT With Segment Anything\",\"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/yatenglg-isat-with-segment-anything/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/yatenglg-isat-with-segment-anything"},"trust":{"score":81,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"2.1K GitHub stars","repoActivity":"2.1K stars, 207 forks","lastPushed":"7mo since push","license":"Unknown","repository":"https://github.com/yatengLG/ISAT_with_segment_anything","install":"npx skills add yatengLG/ISAT_with_segment_anything","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","annotation-tool","labeling","labeling-tool"],"known_risks":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","Quality score needs review","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":76,"label":"Strong"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"7mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","Quality score needs review","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use ISAT With Segment Anything in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 81/100 Strong shortlist","Audit: 78/100 Needs review","Safety: 66/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"yatenglg-isat-with-segment-anything (ISAT With Segment Anything)","install_command":"npx skills add yatengLG/ISAT_with_segment_anything","risk_summary":"Needs review; Reviewed with permission notes; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"yatenglg-isat-with-segment-anything","task":"Use ISAT With Segment Anything 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/yatenglg-isat-with-segment-anything","api":"https://www.openagentskill.com/api/agent/skills/yatenglg-isat-with-segment-anything","audit":"https://www.openagentskill.com/skills/yatenglg-isat-with-segment-anything/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=yatenglg-isat-with-segment-anything&task=Use%20ISAT%20With%20Segment%20Anything%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20ISAT%20With%20Segment%20Anything%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20ISAT%20With%20Segment%20Anything%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/yatenglg-isat-with-segment-anything/install","manifest":"https://www.openagentskill.com/api/registry/manifest/yatenglg-isat-with-segment-anything"}},"platforms":["Python","Computer Vision"],"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"slug":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"},{"slug":"customer-support","title":"Customer support","url":"https://www.openagentskill.com/use-cases/customer-support"}],"install":"npx skills add yatengLG/ISAT_with_segment_anything","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 yatenglg-isat-with-segment-anything","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 \"ISAT With Segment Anything\" agent skill from https://github.com/yatengLG/ISAT_with_segment_anything. 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: Labeling tool with SAM(segment anything model),supports SAM, SAM2, SAM3, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具 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\":\"yatenglg-isat-with-segment-anything\",\"task\":\"Install ISAT With Segment Anything\",\"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 \"ISAT With Segment Anything\" as a Claude Code skill from https://github.com/yatengLG/ISAT_with_segment_anything. 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: Labeling tool with SAM(segment anything model),supports SAM, SAM2, SAM3, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具 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\":\"yatenglg-isat-with-segment-anything\",\"task\":\"Install ISAT With Segment Anything\",\"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 \"ISAT With Segment Anything\" from https://github.com/yatengLG/ISAT_with_segment_anything 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: Labeling tool with SAM(segment anything model),supports SAM, SAM2, SAM3, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具 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\":\"yatenglg-isat-with-segment-anything\",\"task\":\"Install ISAT With Segment Anything\",\"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/yatengLG/ISAT_with_segment_anything","github_repo":"yatengLG/ISAT_with_segment_anything","version":"1.0.0","license":"Unknown","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"yatenglg/isat_with_segment_anything","recommendation_reasons":["Matches task terms: sam","Useful GitHub adoption: 2,130 stars","Install handoff is available","Repository freshness signal is available","Registry match score 9"],"urls":{"web":"https://www.openagentskill.com/skills/yatenglg-isat-with-segment-anything","api":"https://www.openagentskill.com/api/agent/skills/yatenglg-isat-with-segment-anything","install_api":"https://www.openagentskill.com/api/skills/yatenglg-isat-with-segment-anything/install","audit":"https://www.openagentskill.com/skills/yatenglg-isat-with-segment-anything/audit","repository":"https://github.com/yatengLG/ISAT_with_segment_anything"}},{"rank":8,"match_type":"related","match_score":8,"raw_match_score":58.5,"semantic_relevance":42,"slug":"roboflow-notebooks","name":"Notebooks","description":"A collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like RF-DETR, YOLO11, SAM 3, and Qwen3-VL.","tagline":"A collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like RF-DETR, YOLO11, SAM 3, and Qwen3-VL.","category":"ml-automation","tags":["machine-learning","automation","ml-media","automatic-labeling-system","computer-vision","deep-learning","deep-neural-networks","google-colab","image-classification","image-segmentation"],"author":{"name":"roboflow","verified":true,"url":"https://github.com/roboflow"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"roboflow/notebooks","creatorName":"roboflow","creatorUrl":"https://github.com/roboflow","sourceUrl":"https://github.com/roboflow/notebooks","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/roboflow-notebooks#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":9462,"forks":1464,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":66.53},"quality":{"score":94,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"9.5K","tone":"positive"},{"label":"Freshness","value":"3mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":84,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"weight":0.13,"status":"pass","detail":"9.5K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":93,"weight":0.08,"status":"pass","detail":"9.5K stars, 1.5K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"3mo since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"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 roboflow/notebooks"},{"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/roboflow/notebooks"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"9.5K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"9.5K stars, 1.5K forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"3mo since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add roboflow/notebooks"},{"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/roboflow/notebooks"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown"],"evidence":{"stars":"9.5K GitHub stars","repoActivity":"9.5K stars, 1.5K forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/roboflow/notebooks","install":"npx skills add roboflow/notebooks","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 roboflow/notebooks","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","No Agent Proven outcome evidence yet","3mo since push"]},"agentCompatibility":["Jupyter Notebook","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["ml-automation","machine-learning","automation","ml-media","automatic-labeling-system","computer-vision"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"safety":{"score":74,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","74/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["License is unclear"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","74/100 agent safety score"]},"supply_profile":{"track":{"slug":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Multimodal media","description":"I need my agent to process images, video, or audio and extract useful information.","useCases":[{"slug":"multimodal-media","title":"Multimodal media"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"workflow-automation","title":"Workflow automation"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Jupyter Notebook"],"install":{"ready":true,"command":"npx skills add roboflow/notebooks","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":9462,"starsLabel":"9.5K","forks":1464,"license":"Unknown","qualityScore":94,"trustScore":84,"auditScore":86},"maintenance":{"status":"active","label":"3mo since push","daysSincePush":93,"lastPushedAt":"2026-05-21T16:15:53+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"coverageTags":["Design","Multimodal media","ml-automation","machine-learning","automation","ml-media","automatic-labeling-system","computer-vision"]},"audit":{"audit_score":86,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Multimodal media","role":"Primary pick","primary_fit":"Multimodal media","best_for":["Multimodal media workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Multimodal media task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"roboflow-notebooks","name":"Notebooks","description":"A collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like RF-DETR, YOLO11, SAM 3, and Qwen3-VL.","category":"ml-automation","url":"https://www.openagentskill.com/skills/roboflow-notebooks","repository":"https://github.com/roboflow/notebooks","github_repo":"roboflow/notebooks"},"suited_tasks":["Multimodal media workflows","general agent builders","teams that value GitHub adoption signals","Read media metadata","Convert formats","Summarize visual or audio content","Navigate pages","Click and type safely"],"suited_agents":["Jupyter Notebook","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add roboflow/notebooks","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 roboflow-notebooks"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Notebooks\" agent skill from https://github.com/roboflow/notebooks. 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 collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like RF-DETR, YOLO11, SAM 3, and Qwen3-VL. 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\":\"roboflow-notebooks\",\"task\":\"Install Notebooks\",\"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 \"Notebooks\" as a Claude Code skill from https://github.com/roboflow/notebooks. 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 collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like RF-DETR, YOLO11, SAM 3, and Qwen3-VL. 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\":\"roboflow-notebooks\",\"task\":\"Install Notebooks\",\"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 \"Notebooks\" from https://github.com/roboflow/notebooks 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 collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like RF-DETR, YOLO11, SAM 3, and Qwen3-VL. 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\":\"roboflow-notebooks\",\"task\":\"Install Notebooks\",\"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/roboflow-notebooks/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/roboflow-notebooks"},"trust":{"score":84,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"9.5K GitHub stars","repoActivity":"9.5K stars, 1.5K forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/roboflow/notebooks","install":"npx skills add roboflow/notebooks","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":["ml-automation","machine-learning","automation","ml-media","automatic-labeling-system","computer-vision"],"known_risks":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":86,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":94,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"3mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Notebooks in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 84/100 Strong shortlist","Audit: 86/100 Safe to try","Safety: 74/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"roboflow-notebooks (Notebooks)","install_command":"npx skills add roboflow/notebooks","risk_summary":"Safe to try; Reviewed; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"roboflow-notebooks","task":"Use Notebooks 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/roboflow-notebooks","api":"https://www.openagentskill.com/api/agent/skills/roboflow-notebooks","audit":"https://www.openagentskill.com/skills/roboflow-notebooks/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=roboflow-notebooks&task=Use%20Notebooks%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Notebooks%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Notebooks%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/roboflow-notebooks/install","manifest":"https://www.openagentskill.com/api/registry/manifest/roboflow-notebooks"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"roboflow-notebooks","name":"Notebooks","description":"A collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like RF-DETR, YOLO11, SAM 3, and Qwen3-VL.","category":"ml-automation","url":"https://www.openagentskill.com/skills/roboflow-notebooks","repository":"https://github.com/roboflow/notebooks","github_repo":"roboflow/notebooks"},"suited_tasks":["Multimodal media workflows","general agent builders","teams that value GitHub adoption signals","Read media metadata","Convert formats","Summarize visual or audio content","Navigate pages","Click and type safely"],"suited_agents":["Jupyter Notebook","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add roboflow/notebooks","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 roboflow-notebooks"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Notebooks\" agent skill from https://github.com/roboflow/notebooks. 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 collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like RF-DETR, YOLO11, SAM 3, and Qwen3-VL. 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\":\"roboflow-notebooks\",\"task\":\"Install Notebooks\",\"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 \"Notebooks\" as a Claude Code skill from https://github.com/roboflow/notebooks. 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 collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like RF-DETR, YOLO11, SAM 3, and Qwen3-VL. 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\":\"roboflow-notebooks\",\"task\":\"Install Notebooks\",\"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 \"Notebooks\" from https://github.com/roboflow/notebooks 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 collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like RF-DETR, YOLO11, SAM 3, and Qwen3-VL. 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\":\"roboflow-notebooks\",\"task\":\"Install Notebooks\",\"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/roboflow-notebooks/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/roboflow-notebooks"},"trust":{"score":84,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"9.5K GitHub stars","repoActivity":"9.5K stars, 1.5K forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/roboflow/notebooks","install":"npx skills add roboflow/notebooks","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":["ml-automation","machine-learning","automation","ml-media","automatic-labeling-system","computer-vision"],"known_risks":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":86,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":94,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"3mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Notebooks in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 84/100 Strong shortlist","Audit: 86/100 Safe to try","Safety: 74/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"roboflow-notebooks (Notebooks)","install_command":"npx skills add roboflow/notebooks","risk_summary":"Safe to try; Reviewed; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"roboflow-notebooks","task":"Use Notebooks 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/roboflow-notebooks","api":"https://www.openagentskill.com/api/agent/skills/roboflow-notebooks","audit":"https://www.openagentskill.com/skills/roboflow-notebooks/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=roboflow-notebooks&task=Use%20Notebooks%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Notebooks%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Notebooks%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/roboflow-notebooks/install","manifest":"https://www.openagentskill.com/api/registry/manifest/roboflow-notebooks"}},"platforms":["Jupyter Notebook","Machine Learning"],"use_cases":[{"slug":"multimodal-media","title":"Multimodal media","url":"https://www.openagentskill.com/use-cases/multimodal-media"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"slug":"data-analysis","title":"Data analysis","url":"https://www.openagentskill.com/use-cases/data-analysis"}],"install":"npx skills add roboflow/notebooks","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 roboflow-notebooks","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 \"Notebooks\" agent skill from https://github.com/roboflow/notebooks. 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 collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like RF-DETR, YOLO11, SAM 3, and Qwen3-VL. 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\":\"roboflow-notebooks\",\"task\":\"Install Notebooks\",\"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 \"Notebooks\" as a Claude Code skill from https://github.com/roboflow/notebooks. 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 collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like RF-DETR, YOLO11, SAM 3, and Qwen3-VL. 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\":\"roboflow-notebooks\",\"task\":\"Install Notebooks\",\"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 \"Notebooks\" from https://github.com/roboflow/notebooks 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 collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like RF-DETR, YOLO11, SAM 3, and Qwen3-VL. 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\":\"roboflow-notebooks\",\"task\":\"Install Notebooks\",\"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/roboflow/notebooks","github_repo":"roboflow/notebooks","version":"1.0.0","license":"Unknown","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"roboflow/notebooks","recommendation_reasons":["Matches task terms: sam, detr","Useful GitHub adoption: 9,462 stars","Install handoff is available","Repository freshness signal is available","Registry match score 8"],"urls":{"web":"https://www.openagentskill.com/skills/roboflow-notebooks","api":"https://www.openagentskill.com/api/agent/skills/roboflow-notebooks","install_api":"https://www.openagentskill.com/api/skills/roboflow-notebooks/install","audit":"https://www.openagentskill.com/skills/roboflow-notebooks/audit","repository":"https://github.com/roboflow/notebooks"}},{"rank":9,"match_type":"related","match_score":7,"raw_match_score":55.5,"semantic_relevance":30,"slug":"augmentedstartups-as-one","name":"AS One","description":"Easy & Modular Computer Vision Detectors, Trackers & SAM - Run YOLOv9,v8,v7,v6,v5,R,X in under 10 lines of code.","tagline":"Easy & Modular Computer Vision Detectors, Trackers & SAM - Run YOLOv9,v8,v7,v6,v5,R,X in under 10 lines of code.","category":"robotics-iot","tags":["computer-vision","automation","robotics-iot","deep-learning","object-detection","opencv","pytorch","sam","tracking","ultralytics"],"author":{"name":"augmentedstartups","verified":false,"url":"https://github.com/augmentedstartups"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"augmentedstartups/AS-One","creatorName":"augmentedstartups","creatorUrl":"https://github.com/augmentedstartups","sourceUrl":"https://github.com/augmentedstartups/AS-One","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/augmentedstartups-as-one#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":612,"forks":106,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":38.21},"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":"612","tone":"positive"},{"label":"Freshness","value":"2y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"GPL-3.0","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":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":"612 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":71,"weight":0.08,"status":"info","detail":"612 stars, 106 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":"GPL-3.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add augmentedstartups/AS-One"},{"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/augmentedstartups/AS-One"},{"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":"612 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"612 stars, 106 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"2y since push"},{"status":"pass","label":"License clarity","detail":"GPL-3.0"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add augmentedstartups/AS-One"},{"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/augmentedstartups/AS-One"},{"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: 2y since push"],"evidence":{"stars":"612 GitHub stars","repoActivity":"612 stars, 106 forks","lastPushed":"2y since push","license":"GPL-3.0","repository":"https://github.com/augmentedstartups/AS-One","install":"npx skills add augmentedstartups/AS-One","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 augmentedstartups/AS-One","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2y since push"]},"agentCompatibility":["Python","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: 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","computer-vision","automation","deep-learning","object-detection","opencv"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 2y since push"]},"safety":{"score":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":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"workflow-automation","title":"Workflow automation"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add augmentedstartups/AS-One","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":612,"starsLabel":"612","forks":106,"license":"GPL-3.0","qualityScore":48,"trustScore":73,"auditScore":63},"maintenance":{"status":"stale","label":"2y since push","daysSincePush":821,"lastPushedAt":"2024-05-23T18:11:22+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 2y since push"]},"coverageTags":["Coding","Coding agents","robotics-iot","computer-vision","automation","deep-learning","object-detection","opencv"]},"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: 2y since push"]},"decision":{"readiness_score":50,"readiness_label":"Needs manual review","headline":"Needs validation for Coding agents","role":"Needs validation","primary_fit":"Coding agents","best_for":["Coding agents workflows","general agent builders","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 Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"augmentedstartups-as-one","name":"AS One","description":"Easy & Modular Computer Vision Detectors, Trackers & SAM - Run YOLOv9,v8,v7,v6,v5,R,X in under 10 lines of code.","category":"robotics-iot","url":"https://www.openagentskill.com/skills/augmentedstartups-as-one","repository":"https://github.com/augmentedstartups/AS-One","github_repo":"augmentedstartups/AS-One"},"suited_tasks":["Coding agents workflows","general agent builders","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Navigate pages","Click and type safely"],"suited_agents":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add augmentedstartups/AS-One","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 augmentedstartups-as-one"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"AS One\" agent skill from https://github.com/augmentedstartups/AS-One. 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: Easy & Modular Computer Vision Detectors, Trackers & SAM - Run YOLOv9,v8,v7,v6,v5,R,X in under 10 lines of code. 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\":\"augmentedstartups-as-one\",\"task\":\"Install AS One\",\"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 \"AS One\" as a Claude Code skill from https://github.com/augmentedstartups/AS-One. 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: Easy & Modular Computer Vision Detectors, Trackers & SAM - Run YOLOv9,v8,v7,v6,v5,R,X in under 10 lines of code. 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\":\"augmentedstartups-as-one\",\"task\":\"Install AS One\",\"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 \"AS One\" from https://github.com/augmentedstartups/AS-One 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: Easy & Modular Computer Vision Detectors, Trackers & SAM - Run YOLOv9,v8,v7,v6,v5,R,X in under 10 lines of code. 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\":\"augmentedstartups-as-one\",\"task\":\"Install AS One\",\"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/augmentedstartups-as-one/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/augmentedstartups-as-one"},"trust":{"score":73,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"612 GitHub stars","repoActivity":"612 stars, 106 forks","lastPushed":"2y since push","license":"GPL-3.0","repository":"https://github.com/augmentedstartups/AS-One","install":"npx skills add augmentedstartups/AS-One","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","deep-learning","object-detection","opencv"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 2y since push"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":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: 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":48,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"2y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Documentation summary is thin","Repository appears stale","Quality score needs review","Recent maintenance: 2y since push"],"agent_contract":{"task_input":"Use AS One 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: 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":"augmentedstartups-as-one (AS One)","install_command":"npx skills add augmentedstartups/AS-One","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":"augmentedstartups-as-one","task":"Use AS One 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/augmentedstartups-as-one","api":"https://www.openagentskill.com/api/agent/skills/augmentedstartups-as-one","audit":"https://www.openagentskill.com/skills/augmentedstartups-as-one/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=augmentedstartups-as-one&task=Use%20AS%20One%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20AS%20One%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20AS%20One%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/augmentedstartups-as-one/install","manifest":"https://www.openagentskill.com/api/registry/manifest/augmentedstartups-as-one"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"augmentedstartups-as-one","name":"AS One","description":"Easy & Modular Computer Vision Detectors, Trackers & SAM - Run YOLOv9,v8,v7,v6,v5,R,X in under 10 lines of code.","category":"robotics-iot","url":"https://www.openagentskill.com/skills/augmentedstartups-as-one","repository":"https://github.com/augmentedstartups/AS-One","github_repo":"augmentedstartups/AS-One"},"suited_tasks":["Coding agents workflows","general agent builders","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Navigate pages","Click and type safely"],"suited_agents":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add augmentedstartups/AS-One","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 augmentedstartups-as-one"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"AS One\" agent skill from https://github.com/augmentedstartups/AS-One. 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: Easy & Modular Computer Vision Detectors, Trackers & SAM - Run YOLOv9,v8,v7,v6,v5,R,X in under 10 lines of code. 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\":\"augmentedstartups-as-one\",\"task\":\"Install AS One\",\"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 \"AS One\" as a Claude Code skill from https://github.com/augmentedstartups/AS-One. 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: Easy & Modular Computer Vision Detectors, Trackers & SAM - Run YOLOv9,v8,v7,v6,v5,R,X in under 10 lines of code. 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\":\"augmentedstartups-as-one\",\"task\":\"Install AS One\",\"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 \"AS One\" from https://github.com/augmentedstartups/AS-One 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: Easy & Modular Computer Vision Detectors, Trackers & SAM - Run YOLOv9,v8,v7,v6,v5,R,X in under 10 lines of code. 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\":\"augmentedstartups-as-one\",\"task\":\"Install AS One\",\"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/augmentedstartups-as-one/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/augmentedstartups-as-one"},"trust":{"score":73,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"612 GitHub stars","repoActivity":"612 stars, 106 forks","lastPushed":"2y since push","license":"GPL-3.0","repository":"https://github.com/augmentedstartups/AS-One","install":"npx skills add augmentedstartups/AS-One","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","deep-learning","object-detection","opencv"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 2y since push"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":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: 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":48,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"2y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Documentation summary is thin","Repository appears stale","Quality score needs review","Recent maintenance: 2y since push"],"agent_contract":{"task_input":"Use AS One 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: 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":"augmentedstartups-as-one (AS One)","install_command":"npx skills add augmentedstartups/AS-One","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":"augmentedstartups-as-one","task":"Use AS One 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/augmentedstartups-as-one","api":"https://www.openagentskill.com/api/agent/skills/augmentedstartups-as-one","audit":"https://www.openagentskill.com/skills/augmentedstartups-as-one/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=augmentedstartups-as-one&task=Use%20AS%20One%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20AS%20One%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20AS%20One%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/augmentedstartups-as-one/install","manifest":"https://www.openagentskill.com/api/registry/manifest/augmentedstartups-as-one"}},"platforms":["Python","Computer Vision"],"use_cases":[{"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"},{"slug":"sports-analytics","title":"Sports analytics","url":"https://www.openagentskill.com/use-cases/sports-analytics"}],"install":"npx skills add augmentedstartups/AS-One","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 augmentedstartups-as-one","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 \"AS One\" agent skill from https://github.com/augmentedstartups/AS-One. 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: Easy & Modular Computer Vision Detectors, Trackers & SAM - Run YOLOv9,v8,v7,v6,v5,R,X in under 10 lines of code. 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\":\"augmentedstartups-as-one\",\"task\":\"Install AS One\",\"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 \"AS One\" as a Claude Code skill from https://github.com/augmentedstartups/AS-One. 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: Easy & Modular Computer Vision Detectors, Trackers & SAM - Run YOLOv9,v8,v7,v6,v5,R,X in under 10 lines of code. 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\":\"augmentedstartups-as-one\",\"task\":\"Install AS One\",\"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 \"AS One\" from https://github.com/augmentedstartups/AS-One 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: Easy & Modular Computer Vision Detectors, Trackers & SAM - Run YOLOv9,v8,v7,v6,v5,R,X in under 10 lines of code. 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\":\"augmentedstartups-as-one\",\"task\":\"Install AS One\",\"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/augmentedstartups/AS-One","github_repo":"augmentedstartups/AS-One","version":"1.0.0","license":"GPL-3.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"augmentedstartups/as-one","recommendation_reasons":["Matches task terms: sam","Useful GitHub adoption: 612 stars","Install handoff is available","Repository freshness signal is available","Registry match score 7"],"urls":{"web":"https://www.openagentskill.com/skills/augmentedstartups-as-one","api":"https://www.openagentskill.com/api/agent/skills/augmentedstartups-as-one","install_api":"https://www.openagentskill.com/api/skills/augmentedstartups-as-one/install","audit":"https://www.openagentskill.com/skills/augmentedstartups-as-one/audit","repository":"https://github.com/augmentedstartups/AS-One"}},{"rank":10,"match_type":"related","match_score":6,"raw_match_score":48,"semantic_relevance":30,"slug":"opengeos-segment-geospatial","name":"Segment Geospatial","description":"A Python package for segmenting geospatial data with the Segment Anything Model (SAM)","tagline":"A Python package for segmenting geospatial data with the Segment Anything Model (SAM)","category":"ml-automation","tags":["machine-learning","automation","ml-media","artificial-intelligence","deep-learning","geopython","geospatial","segment-anything","segmentation","python"],"author":{"name":"opengeos","verified":true,"url":"https://github.com/opengeos"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"opengeos/segment-geospatial","creatorName":"opengeos","creatorUrl":"https://github.com/opengeos","sourceUrl":"https://github.com/opengeos/segment-geospatial","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/opengeos-segment-geospatial#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":4015,"forks":421,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":63.93},"quality":{"score":95,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"4.0K","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":88,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"4.0K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"4.0K stars, 421 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add opengeos/segment-geospatial"},{"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/opengeos/segment-geospatial"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"4.0K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"4.0K stars, 421 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add opengeos/segment-geospatial"},{"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/opengeos/segment-geospatial"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin"],"evidence":{"stars":"4.0K GitHub stars","repoActivity":"4.0K stars, 421 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/opengeos/segment-geospatial","install":"npx skills add opengeos/segment-geospatial","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 opengeos/segment-geospatial","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["ml-automation","machine-learning","automation","ml-media","artificial-intelligence","deep-learning"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin"]},"safety":{"score":78,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","78/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","78/100 agent safety score"]},"supply_profile":{"track":{"slug":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Multimodal media","description":"I need my agent to process images, video, or audio and extract useful information.","useCases":[{"slug":"browser-automation","title":"Browser automation"},{"slug":"workflow-automation","title":"Workflow automation"},{"slug":"github-automation","title":"GitHub automation"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add opengeos/segment-geospatial","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":4015,"starsLabel":"4.0K","forks":421,"license":"MIT","qualityScore":95,"trustScore":88,"auditScore":90},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":68,"lastPushedAt":"2026-06-15T20:27:22+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Design","Multimodal media","ml-automation","machine-learning","automation","ml-media","artificial-intelligence","deep-learning"]},"audit":{"audit_score":90,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Browser automation","role":"Primary pick","primary_fit":"Browser automation","best_for":["Browser automation workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Browser automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"opengeos-segment-geospatial","name":"Segment Geospatial","description":"A Python package for segmenting geospatial data with the Segment Anything Model (SAM)","category":"ml-automation","url":"https://www.openagentskill.com/skills/opengeos-segment-geospatial","repository":"https://github.com/opengeos/segment-geospatial","github_repo":"opengeos/segment-geospatial"},"suited_tasks":["Browser automation workflows","general agent builders","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Move data between tools","Transform files"],"suited_agents":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add opengeos/segment-geospatial","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 opengeos-segment-geospatial"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Segment Geospatial\" agent skill from https://github.com/opengeos/segment-geospatial. 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 Python package for segmenting geospatial data with the Segment Anything Model (SAM) 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\":\"opengeos-segment-geospatial\",\"task\":\"Install Segment Geospatial\",\"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 \"Segment Geospatial\" as a Claude Code skill from https://github.com/opengeos/segment-geospatial. 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 Python package for segmenting geospatial data with the Segment Anything Model (SAM) 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\":\"opengeos-segment-geospatial\",\"task\":\"Install Segment Geospatial\",\"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 \"Segment Geospatial\" from https://github.com/opengeos/segment-geospatial 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 Python package for segmenting geospatial data with the Segment Anything Model (SAM) 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\":\"opengeos-segment-geospatial\",\"task\":\"Install Segment Geospatial\",\"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/opengeos-segment-geospatial/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/opengeos-segment-geospatial"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"4.0K GitHub stars","repoActivity":"4.0K stars, 421 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/opengeos/segment-geospatial","install":"npx skills add opengeos/segment-geospatial","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["ml-automation","machine-learning","automation","ml-media","artificial-intelligence","deep-learning"],"known_risks":["Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":90,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":95,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Segment Geospatial in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 88/100 Production candidate","Audit: 90/100 Safe to try","Safety: 78/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"opengeos-segment-geospatial (Segment Geospatial)","install_command":"npx skills add opengeos/segment-geospatial","risk_summary":"Safe to try; Reviewed; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"opengeos-segment-geospatial","task":"Use Segment Geospatial 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/opengeos-segment-geospatial","api":"https://www.openagentskill.com/api/agent/skills/opengeos-segment-geospatial","audit":"https://www.openagentskill.com/skills/opengeos-segment-geospatial/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=opengeos-segment-geospatial&task=Use%20Segment%20Geospatial%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Segment%20Geospatial%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Segment%20Geospatial%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/opengeos-segment-geospatial/install","manifest":"https://www.openagentskill.com/api/registry/manifest/opengeos-segment-geospatial"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"opengeos-segment-geospatial","name":"Segment Geospatial","description":"A Python package for segmenting geospatial data with the Segment Anything Model (SAM)","category":"ml-automation","url":"https://www.openagentskill.com/skills/opengeos-segment-geospatial","repository":"https://github.com/opengeos/segment-geospatial","github_repo":"opengeos/segment-geospatial"},"suited_tasks":["Browser automation workflows","general agent builders","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Move data between tools","Transform files"],"suited_agents":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add opengeos/segment-geospatial","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 opengeos-segment-geospatial"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Segment Geospatial\" agent skill from https://github.com/opengeos/segment-geospatial. 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 Python package for segmenting geospatial data with the Segment Anything Model (SAM) 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\":\"opengeos-segment-geospatial\",\"task\":\"Install Segment Geospatial\",\"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 \"Segment Geospatial\" as a Claude Code skill from https://github.com/opengeos/segment-geospatial. 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 Python package for segmenting geospatial data with the Segment Anything Model (SAM) 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\":\"opengeos-segment-geospatial\",\"task\":\"Install Segment Geospatial\",\"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 \"Segment Geospatial\" from https://github.com/opengeos/segment-geospatial 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 Python package for segmenting geospatial data with the Segment Anything Model (SAM) 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\":\"opengeos-segment-geospatial\",\"task\":\"Install Segment Geospatial\",\"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/opengeos-segment-geospatial/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/opengeos-segment-geospatial"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"4.0K GitHub stars","repoActivity":"4.0K stars, 421 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/opengeos/segment-geospatial","install":"npx skills add opengeos/segment-geospatial","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["ml-automation","machine-learning","automation","ml-media","artificial-intelligence","deep-learning"],"known_risks":["Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":90,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":95,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Segment Geospatial in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 88/100 Production candidate","Audit: 90/100 Safe to try","Safety: 78/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"opengeos-segment-geospatial (Segment Geospatial)","install_command":"npx skills add opengeos/segment-geospatial","risk_summary":"Safe to try; Reviewed; Low metadata risk","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"outcome_feedback":{"endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","requires_resolve_event_id":true,"event_id_source":"Use install_receipt.outcome_feedback.event_id or feedback.event_id returned by /api/agent/resolve for the current task.","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"<install_receipt.outcome_feedback.event_id or feedback.event_id from /api/agent/resolve>","skill_slug":"opengeos-segment-geospatial","task":"Use Segment Geospatial 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/opengeos-segment-geospatial","api":"https://www.openagentskill.com/api/agent/skills/opengeos-segment-geospatial","audit":"https://www.openagentskill.com/skills/opengeos-segment-geospatial/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=opengeos-segment-geospatial&task=Use%20Segment%20Geospatial%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Segment%20Geospatial%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Segment%20Geospatial%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/opengeos-segment-geospatial/install","manifest":"https://www.openagentskill.com/api/registry/manifest/opengeos-segment-geospatial"}},"platforms":["Python","Machine Learning"],"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"testing-qa","title":"Testing and QA","url":"https://www.openagentskill.com/use-cases/testing-qa"}],"install":"npx skills add opengeos/segment-geospatial","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 opengeos-segment-geospatial","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 \"Segment Geospatial\" agent skill from https://github.com/opengeos/segment-geospatial. 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 Python package for segmenting geospatial data with the Segment Anything Model (SAM) 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\":\"opengeos-segment-geospatial\",\"task\":\"Install Segment Geospatial\",\"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 \"Segment Geospatial\" as a Claude Code skill from https://github.com/opengeos/segment-geospatial. 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 Python package for segmenting geospatial data with the Segment Anything Model (SAM) 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\":\"opengeos-segment-geospatial\",\"task\":\"Install Segment Geospatial\",\"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 \"Segment Geospatial\" from https://github.com/opengeos/segment-geospatial 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 Python package for segmenting geospatial data with the Segment Anything Model (SAM) 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\":\"opengeos-segment-geospatial\",\"task\":\"Install Segment Geospatial\",\"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/opengeos/segment-geospatial","github_repo":"opengeos/segment-geospatial","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"opengeos/segment-geospatial","recommendation_reasons":["Matches task terms: sam","Useful GitHub adoption: 4,015 stars","Install handoff is available","Repository freshness signal is available","Registry match score 6"],"urls":{"web":"https://www.openagentskill.com/skills/opengeos-segment-geospatial","api":"https://www.openagentskill.com/api/agent/skills/opengeos-segment-geospatial","install_api":"https://www.openagentskill.com/api/skills/opengeos-segment-geospatial/install","audit":"https://www.openagentskill.com/skills/opengeos-segment-geospatial/audit","repository":"https://github.com/opengeos/segment-geospatial"}}],"meta":{"endpoint":"/api/skills/search","canonical_agent_endpoint":"/api/agent/resolve","lookup_intent":false,"exact_match_found":true,"match_counts":{"exact":1,"near":0,"related":9},"no_match_message":null,"safety_policy":"Blocked candidates are excluded by default. Pass include_blocked=true only for manual audit workflows.","agent_friendly":true,"api_version":"1.0","generated_at":"2026-08-23T05:37:44.626Z"}}