{"query":"Mtt Distillation","filters":{"category":null,"platform":null,"track":null,"safety":null,"include_blocked":false,"min_stars":0},"total":10,"skills":[{"rank":1,"match_type":"related","match_score":17,"raw_match_score":122.9,"semantic_relevance":30,"slug":"haitongli-knowledge-distillation-pytorch","name":"Knowledge Distillation Pytorch","description":"A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility","tagline":"A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility","category":"robotics-iot","tags":["computer-vision","automation","robotics-iot","cifar10","dark-knowledge","deep-neural-networks","knowledge-distillation","model-compression","pytorch","python"],"author":{"name":"haitongli","verified":true,"url":"https://github.com/haitongli"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"haitongli/knowledge-distillation-pytorch","creatorName":"haitongli","creatorUrl":"https://github.com/haitongli","sourceUrl":"https://github.com/haitongli/knowledge-distillation-pytorch","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/haitongli-knowledge-distillation-pytorch#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":1994,"forks":354,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":49.8},"quality":{"score":67,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"2.0K","tone":"positive"},{"label":"Freshness","value":"3y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":80,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"2.0K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"2.0K stars, 354 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":22,"weight":0.14,"status":"fail","detail":"3y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":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 haitongli/knowledge-distillation-pytorch"},{"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/haitongli/knowledge-distillation-pytorch"},{"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":"2.0K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"2.0K stars, 354 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"3y 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 haitongli/knowledge-distillation-pytorch"},{"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/haitongli/knowledge-distillation-pytorch"},{"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":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push"],"evidence":{"stars":"2.0K GitHub stars","repoActivity":"2.0K stars, 354 forks","lastPushed":"3y since push","license":"MIT","repository":"https://github.com/haitongli/knowledge-distillation-pytorch","install":"npx skills add haitongli/knowledge-distillation-pytorch","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 haitongli/knowledge-distillation-pytorch","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3y since push"]},"agentCompatibility":["Python","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: 3y 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","cifar10","dark-knowledge","deep-neural-networks"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push"]},"safety":{"score":59,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Documentation summary is thin","59/100 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":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Documentation summary is thin","59/100 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":"rag-knowledge","title":"RAG and knowledge"},{"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 haitongli/knowledge-distillation-pytorch","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":1994,"starsLabel":"2.0K","forks":354,"license":"MIT","qualityScore":67,"trustScore":80,"auditScore":71},"maintenance":{"status":"stale","label":"3y since push","daysSincePush":1246,"lastPushedAt":"2023-03-25T00:03:08+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: 3y since push"]},"coverageTags":["Coding","GitHub automation","robotics-iot","computer-vision","automation","cifar10","dark-knowledge","deep-neural-networks"]},"audit":{"audit_score":71,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 3y since push"]},"decision":{"readiness_score":69,"readiness_label":"Prototype first","headline":"Fallback candidate for RAG and knowledge","role":"Fallback candidate","primary_fit":"RAG and knowledge","best_for":["RAG and knowledge workflows","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 RAG and knowledge task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"haitongli-knowledge-distillation-pytorch","name":"Knowledge Distillation Pytorch","description":"A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility","category":"robotics-iot","url":"https://www.openagentskill.com/skills/haitongli-knowledge-distillation-pytorch","repository":"https://github.com/haitongli/knowledge-distillation-pytorch","github_repo":"haitongli/knowledge-distillation-pytorch"},"suited_tasks":["RAG and knowledge workflows","general agent builders","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Navigate pages","Click and type safely"],"suited_agents":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add haitongli/knowledge-distillation-pytorch","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 haitongli-knowledge-distillation-pytorch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Knowledge Distillation Pytorch\" agent skill from https://github.com/haitongli/knowledge-distillation-pytorch. 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 PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility 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\":\"haitongli-knowledge-distillation-pytorch\",\"task\":\"Install Knowledge Distillation Pytorch\",\"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 \"Knowledge Distillation Pytorch\" as a Claude Code skill from https://github.com/haitongli/knowledge-distillation-pytorch. 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 PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility 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\":\"haitongli-knowledge-distillation-pytorch\",\"task\":\"Install Knowledge Distillation Pytorch\",\"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 \"Knowledge Distillation Pytorch\" from https://github.com/haitongli/knowledge-distillation-pytorch 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 PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility 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\":\"haitongli-knowledge-distillation-pytorch\",\"task\":\"Install Knowledge Distillation Pytorch\",\"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/haitongli-knowledge-distillation-pytorch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/haitongli-knowledge-distillation-pytorch"},"trust":{"score":80,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"2.0K GitHub stars","repoActivity":"2.0K stars, 354 forks","lastPushed":"3y since push","license":"MIT","repository":"https://github.com/haitongli/knowledge-distillation-pytorch","install":"npx skills add haitongli/knowledge-distillation-pytorch","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","cifar10","dark-knowledge","deep-neural-networks"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y 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":71,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 3y since push"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":67,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"3y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Documentation summary is thin","Repository appears stale","Quality score needs review","Recent maintenance: 3y since push"],"agent_contract":{"task_input":"Use Knowledge Distillation Pytorch in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 80/100 Strong shortlist","Audit: 71/100 Needs review","Safety: 59/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"haitongli-knowledge-distillation-pytorch (Knowledge Distillation Pytorch)","install_command":"npx skills add haitongli/knowledge-distillation-pytorch","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":"haitongli-knowledge-distillation-pytorch","task":"Use Knowledge Distillation Pytorch 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/haitongli-knowledge-distillation-pytorch","api":"https://www.openagentskill.com/api/agent/skills/haitongli-knowledge-distillation-pytorch","audit":"https://www.openagentskill.com/skills/haitongli-knowledge-distillation-pytorch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=haitongli-knowledge-distillation-pytorch&task=Use%20Knowledge%20Distillation%20Pytorch%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Knowledge%20Distillation%20Pytorch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Knowledge%20Distillation%20Pytorch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/haitongli-knowledge-distillation-pytorch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/haitongli-knowledge-distillation-pytorch"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"haitongli-knowledge-distillation-pytorch","name":"Knowledge Distillation Pytorch","description":"A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility","category":"robotics-iot","url":"https://www.openagentskill.com/skills/haitongli-knowledge-distillation-pytorch","repository":"https://github.com/haitongli/knowledge-distillation-pytorch","github_repo":"haitongli/knowledge-distillation-pytorch"},"suited_tasks":["RAG and knowledge workflows","general agent builders","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Navigate pages","Click and type safely"],"suited_agents":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add haitongli/knowledge-distillation-pytorch","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 haitongli-knowledge-distillation-pytorch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Knowledge Distillation Pytorch\" agent skill from https://github.com/haitongli/knowledge-distillation-pytorch. 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 PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility 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\":\"haitongli-knowledge-distillation-pytorch\",\"task\":\"Install Knowledge Distillation Pytorch\",\"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 \"Knowledge Distillation Pytorch\" as a Claude Code skill from https://github.com/haitongli/knowledge-distillation-pytorch. 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 PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility 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\":\"haitongli-knowledge-distillation-pytorch\",\"task\":\"Install Knowledge Distillation Pytorch\",\"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 \"Knowledge Distillation Pytorch\" from https://github.com/haitongli/knowledge-distillation-pytorch 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 PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility 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\":\"haitongli-knowledge-distillation-pytorch\",\"task\":\"Install Knowledge Distillation Pytorch\",\"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/haitongli-knowledge-distillation-pytorch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/haitongli-knowledge-distillation-pytorch"},"trust":{"score":80,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"2.0K GitHub stars","repoActivity":"2.0K stars, 354 forks","lastPushed":"3y since push","license":"MIT","repository":"https://github.com/haitongli/knowledge-distillation-pytorch","install":"npx skills add haitongli/knowledge-distillation-pytorch","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","cifar10","dark-knowledge","deep-neural-networks"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y 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":71,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Repository appears stale","Repository looks stale","Quality score needs review","Recent maintenance: 3y since push"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":67,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"3y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Documentation summary is thin","Repository appears stale","Quality score needs review","Recent maintenance: 3y since push"],"agent_contract":{"task_input":"Use Knowledge Distillation Pytorch in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 80/100 Strong shortlist","Audit: 71/100 Needs review","Safety: 59/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"haitongli-knowledge-distillation-pytorch (Knowledge Distillation Pytorch)","install_command":"npx skills add haitongli/knowledge-distillation-pytorch","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":"haitongli-knowledge-distillation-pytorch","task":"Use Knowledge Distillation Pytorch 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/haitongli-knowledge-distillation-pytorch","api":"https://www.openagentskill.com/api/agent/skills/haitongli-knowledge-distillation-pytorch","audit":"https://www.openagentskill.com/skills/haitongli-knowledge-distillation-pytorch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=haitongli-knowledge-distillation-pytorch&task=Use%20Knowledge%20Distillation%20Pytorch%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Knowledge%20Distillation%20Pytorch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Knowledge%20Distillation%20Pytorch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/haitongli-knowledge-distillation-pytorch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/haitongli-knowledge-distillation-pytorch"}},"platforms":["Python","Computer Vision"],"use_cases":[{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"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 haitongli/knowledge-distillation-pytorch","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 haitongli-knowledge-distillation-pytorch","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 \"Knowledge Distillation Pytorch\" agent skill from https://github.com/haitongli/knowledge-distillation-pytorch. 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 PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility 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\":\"haitongli-knowledge-distillation-pytorch\",\"task\":\"Install Knowledge Distillation Pytorch\",\"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 \"Knowledge Distillation Pytorch\" as a Claude Code skill from https://github.com/haitongli/knowledge-distillation-pytorch. 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 PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility 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\":\"haitongli-knowledge-distillation-pytorch\",\"task\":\"Install Knowledge Distillation Pytorch\",\"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 \"Knowledge Distillation Pytorch\" from https://github.com/haitongli/knowledge-distillation-pytorch 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 PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility 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\":\"haitongli-knowledge-distillation-pytorch\",\"task\":\"Install Knowledge Distillation Pytorch\",\"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/haitongli/knowledge-distillation-pytorch","github_repo":"haitongli/knowledge-distillation-pytorch","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"haitongli/knowledge-distillation-pytorch","recommendation_reasons":["Matches task terms: distillation","Useful GitHub adoption: 1,994 stars","Install handoff is available","Repository freshness signal is available","Registry match score 17"],"urls":{"web":"https://www.openagentskill.com/skills/haitongli-knowledge-distillation-pytorch","api":"https://www.openagentskill.com/api/agent/skills/haitongli-knowledge-distillation-pytorch","install_api":"https://www.openagentskill.com/api/skills/haitongli-knowledge-distillation-pytorch/install","audit":"https://www.openagentskill.com/skills/haitongli-knowledge-distillation-pytorch/audit","repository":"https://github.com/haitongli/knowledge-distillation-pytorch"}},{"rank":2,"match_type":"related","match_score":16,"raw_match_score":114.7,"semantic_relevance":30,"slug":"mliu98-awesome-human-distillation","name":"Awesome Human Distillation","description":"A curated catalog of human distillliation agent skills","tagline":"A curated catalog of human distillliation agent skills","category":"agent-skills","tags":["agent-skills","skills","awesome-list","claude-code","claude-code-skills","digital-life","human-distillation","python","github"],"author":{"name":"mliu98","verified":false,"url":"https://github.com/mliu98"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"mliu98/awesome-human-distillation","creatorName":"mliu98","creatorUrl":"https://github.com/mliu98","sourceUrl":"https://github.com/mliu98/awesome-human-distillation","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/mliu98-awesome-human-distillation#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":650,"forks":60,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":50.4},"quality":{"score":68,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"650","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":75,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":76,"weight":0.13,"status":"info","detail":"650 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":71,"weight":0.08,"status":"info","detail":"650 stars, 60 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"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 mliu98/awesome-human-distillation"},{"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/mliu98/awesome-human-distillation"},{"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":"650 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"650 stars, 60 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"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 mliu98/awesome-human-distillation"},{"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/mliu98/awesome-human-distillation"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"650 GitHub stars","repoActivity":"650 stars, 60 forks","lastPushed":"2mo since push","license":"Unknown","repository":"https://github.com/mliu98/awesome-human-distillation","install":"npx skills add mliu98/awesome-human-distillation","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 mliu98/awesome-human-distillation","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","2mo since push"]},"agentCompatibility":["Python","AI Agents","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","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["agent-skills","skills","awesome-list","claude-code","claude-code-skills","digital-life"],"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","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":65,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["License is unclear","65/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"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","65/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"github-automation","title":"GitHub automation"},{"slug":"web-scraping","title":"Web scraping"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","Python"],"install":{"ready":true,"command":"npx skills add mliu98/awesome-human-distillation","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":650,"starsLabel":"650","forks":60,"license":"Unknown","qualityScore":68,"trustScore":75,"auditScore":77},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":69,"lastPushedAt":"2026-06-14T06:24:58+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","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"coverageTags":["Coding","Coding agents","agent-skills","skills","awesome-list","claude-code","claude-code-skills","digital-life"]},"audit":{"audit_score":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","Quality score needs review","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"decision":{"readiness_score":79,"readiness_label":"Strong shortlist","headline":"Companion skill for Coding agents","role":"Companion skill","primary_fit":"Coding agents","best_for":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"mliu98-awesome-human-distillation","name":"Awesome Human Distillation","description":"A curated catalog of human distillliation agent skills","category":"agent-skills","url":"https://www.openagentskill.com/skills/mliu98-awesome-human-distillation","repository":"https://github.com/mliu98/awesome-human-distillation","github_repo":"mliu98/awesome-human-distillation"},"suited_tasks":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add mliu98/awesome-human-distillation","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 mliu98-awesome-human-distillation"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Awesome Human Distillation\" agent skill from https://github.com/mliu98/awesome-human-distillation. 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 curated catalog of human distillliation agent skills 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\":\"mliu98-awesome-human-distillation\",\"task\":\"Install Awesome Human Distillation\",\"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 \"Awesome Human Distillation\" as a Claude Code skill from https://github.com/mliu98/awesome-human-distillation. 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 curated catalog of human distillliation agent skills 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\":\"mliu98-awesome-human-distillation\",\"task\":\"Install Awesome Human Distillation\",\"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 \"Awesome Human Distillation\" from https://github.com/mliu98/awesome-human-distillation 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 curated catalog of human distillliation agent skills 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\":\"mliu98-awesome-human-distillation\",\"task\":\"Install Awesome Human Distillation\",\"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/mliu98-awesome-human-distillation/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/mliu98-awesome-human-distillation"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"650 GitHub stars","repoActivity":"650 stars, 60 forks","lastPushed":"2mo since push","license":"Unknown","repository":"https://github.com/mliu98/awesome-human-distillation","install":"npx skills add mliu98/awesome-human-distillation","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":["agent-skills","skills","awesome-list","claude-code","claude-code-skills","digital-life"],"known_risks":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","Quality score needs review","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":68,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","Quality score needs review","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"agent_contract":{"task_input":"Use Awesome Human Distillation in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 77/100 Needs review","Safety: 65/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"mliu98-awesome-human-distillation (Awesome Human Distillation)","install_command":"npx skills add mliu98/awesome-human-distillation","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":"mliu98-awesome-human-distillation","task":"Use Awesome Human Distillation 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/mliu98-awesome-human-distillation","api":"https://www.openagentskill.com/api/agent/skills/mliu98-awesome-human-distillation","audit":"https://www.openagentskill.com/skills/mliu98-awesome-human-distillation/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=mliu98-awesome-human-distillation&task=Use%20Awesome%20Human%20Distillation%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Awesome%20Human%20Distillation%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Awesome%20Human%20Distillation%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/mliu98-awesome-human-distillation/install","manifest":"https://www.openagentskill.com/api/registry/manifest/mliu98-awesome-human-distillation"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"mliu98-awesome-human-distillation","name":"Awesome Human Distillation","description":"A curated catalog of human distillliation agent skills","category":"agent-skills","url":"https://www.openagentskill.com/skills/mliu98-awesome-human-distillation","repository":"https://github.com/mliu98/awesome-human-distillation","github_repo":"mliu98/awesome-human-distillation"},"suited_tasks":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Inspect repository metadata","Compare code changes"],"suited_agents":["Python","AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add mliu98/awesome-human-distillation","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 mliu98-awesome-human-distillation"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Awesome Human Distillation\" agent skill from https://github.com/mliu98/awesome-human-distillation. 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 curated catalog of human distillliation agent skills 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\":\"mliu98-awesome-human-distillation\",\"task\":\"Install Awesome Human Distillation\",\"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 \"Awesome Human Distillation\" as a Claude Code skill from https://github.com/mliu98/awesome-human-distillation. 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 curated catalog of human distillliation agent skills 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\":\"mliu98-awesome-human-distillation\",\"task\":\"Install Awesome Human Distillation\",\"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 \"Awesome Human Distillation\" from https://github.com/mliu98/awesome-human-distillation 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 curated catalog of human distillliation agent skills 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\":\"mliu98-awesome-human-distillation\",\"task\":\"Install Awesome Human Distillation\",\"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/mliu98-awesome-human-distillation/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/mliu98-awesome-human-distillation"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"650 GitHub stars","repoActivity":"650 stars, 60 forks","lastPushed":"2mo since push","license":"Unknown","repository":"https://github.com/mliu98/awesome-human-distillation","install":"npx skills add mliu98/awesome-human-distillation","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":["agent-skills","skills","awesome-list","claude-code","claude-code-skills","digital-life"],"known_risks":["License is unclear","Quality score needs review","Documentation summary is thin","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","Quality score needs review","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":68,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","Quality score needs review","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"agent_contract":{"task_input":"Use Awesome Human Distillation in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 77/100 Needs review","Safety: 65/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"mliu98-awesome-human-distillation (Awesome Human Distillation)","install_command":"npx skills add mliu98/awesome-human-distillation","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":"mliu98-awesome-human-distillation","task":"Use Awesome Human Distillation 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/mliu98-awesome-human-distillation","api":"https://www.openagentskill.com/api/agent/skills/mliu98-awesome-human-distillation","audit":"https://www.openagentskill.com/skills/mliu98-awesome-human-distillation/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=mliu98-awesome-human-distillation&task=Use%20Awesome%20Human%20Distillation%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Awesome%20Human%20Distillation%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Awesome%20Human%20Distillation%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/mliu98-awesome-human-distillation/install","manifest":"https://www.openagentskill.com/api/registry/manifest/mliu98-awesome-human-distillation"}},"platforms":["Python","AI Agents","Claude Code"],"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"}],"install":"npx skills add mliu98/awesome-human-distillation","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 mliu98-awesome-human-distillation","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 \"Awesome Human Distillation\" agent skill from https://github.com/mliu98/awesome-human-distillation. 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 curated catalog of human distillliation agent skills 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\":\"mliu98-awesome-human-distillation\",\"task\":\"Install Awesome Human Distillation\",\"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 \"Awesome Human Distillation\" as a Claude Code skill from https://github.com/mliu98/awesome-human-distillation. 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 curated catalog of human distillliation agent skills 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\":\"mliu98-awesome-human-distillation\",\"task\":\"Install Awesome Human Distillation\",\"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 \"Awesome Human Distillation\" from https://github.com/mliu98/awesome-human-distillation 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 curated catalog of human distillliation agent skills 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\":\"mliu98-awesome-human-distillation\",\"task\":\"Install Awesome Human Distillation\",\"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/mliu98/awesome-human-distillation","github_repo":"mliu98/awesome-human-distillation","version":"1.0.0","license":"Unknown","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"mliu98/awesome-human-distillation","recommendation_reasons":["Matches task terms: distillation","Useful GitHub adoption: 650 stars","Install handoff is available","Repository freshness signal is available","Registry match score 16"],"urls":{"web":"https://www.openagentskill.com/skills/mliu98-awesome-human-distillation","api":"https://www.openagentskill.com/api/agent/skills/mliu98-awesome-human-distillation","install_api":"https://www.openagentskill.com/api/skills/mliu98-awesome-human-distillation/install","audit":"https://www.openagentskill.com/skills/mliu98-awesome-human-distillation/audit","repository":"https://github.com/mliu98/awesome-human-distillation"}},{"rank":3,"match_type":"related","match_score":15,"raw_match_score":107.7,"semantic_relevance":30,"slug":"tientrandinh-revisiting-reverse-distillation","name":"Revisiting Reverse Distillation","description":"(CVPR 2023) Revisiting Reverse Distillation for Anomaly Detection","tagline":"(CVPR 2023) Revisiting Reverse Distillation for Anomaly Detection","category":"robotics-iot","tags":["computer-vision","automation","robotics-iot","anomaly-detection","cvpr2023","deep-learning","knowledge-distillation","python","github"],"author":{"name":"tientrandinh","verified":false,"url":"https://github.com/tientrandinh"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"tientrandinh/Revisiting-Reverse-Distillation","creatorName":"tientrandinh","creatorUrl":"https://github.com/tientrandinh","sourceUrl":"https://github.com/tientrandinh/Revisiting-Reverse-Distillation","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/tientrandinh-revisiting-reverse-distillation#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":170,"forks":32,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":34.33},"quality":{"score":42,"tier":"review","label":"Needs review","summary":"Inspect the repository carefully before adding it to an agent workflow.","signals":[{"label":"GitHub stars","value":"170","tone":"neutral"},{"label":"Freshness","value":"3y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":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":"170 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"170 stars, 32 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":22,"weight":0.14,"status":"fail","detail":"3y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add tientrandinh/Revisiting-Reverse-Distillation"},{"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/tientrandinh/Revisiting-Reverse-Distillation"},{"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":"170 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"170 stars, 32 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"3y since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add tientrandinh/Revisiting-Reverse-Distillation"},{"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/tientrandinh/Revisiting-Reverse-Distillation"},{"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: 170 stars, 32 forks; issue activity unavailable in current metadata","Recent maintenance: 3y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"170 GitHub stars","repoActivity":"170 stars, 32 forks","lastPushed":"3y since push","license":"MIT","repository":"https://github.com/tientrandinh/Revisiting-Reverse-Distillation","install":"npx skills add tientrandinh/Revisiting-Reverse-Distillation","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 tientrandinh/Revisiting-Reverse-Distillation","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3y since push"]},"agentCompatibility":["Python","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","Stars/forks activity: 170 stars, 32 forks; issue activity unavailable in current metadata","Recent maintenance: 3y 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","anomaly-detection","cvpr2023","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","Automatic installation in a production workspace"],"knownRisks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 170 stars, 32 forks; issue activity unavailable in current metadata","Recent maintenance: 3y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":48,"level":"avoid_auto_install","label":"Avoid automatic install","safety_tier":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","summary":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","auto_install_policy":"review","reasons":["Documentation summary is thin","48/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","reasons":["Documentation summary is thin","48/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"GitHub automation","description":"I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.","useCases":[{"slug":"github-automation","title":"GitHub automation"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add tientrandinh/Revisiting-Reverse-Distillation","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":170,"starsLabel":"170","forks":32,"license":"MIT","qualityScore":42,"trustScore":68,"auditScore":60},"maintenance":{"status":"stale","label":"3y since push","daysSincePush":968,"lastPushedAt":"2023-12-28T15:46:06+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: 170 stars, 32 forks; issue activity unavailable in current metadata"]},"coverageTags":["Coding","GitHub automation","robotics-iot","computer-vision","automation","anomaly-detection","cvpr2023","deep-learning"]},"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: 170 stars, 32 forks; issue activity unavailable in current metadata"]},"decision":{"readiness_score":32,"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":"tientrandinh-revisiting-reverse-distillation","name":"Revisiting Reverse Distillation","description":"(CVPR 2023) Revisiting Reverse Distillation for Anomaly Detection","category":"robotics-iot","url":"https://www.openagentskill.com/skills/tientrandinh-revisiting-reverse-distillation","repository":"https://github.com/tientrandinh/Revisiting-Reverse-Distillation","github_repo":"tientrandinh/Revisiting-Reverse-Distillation"},"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 tientrandinh/Revisiting-Reverse-Distillation","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 tientrandinh-revisiting-reverse-distillation"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Revisiting Reverse Distillation\" agent skill from https://github.com/tientrandinh/Revisiting-Reverse-Distillation. 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 2023) Revisiting Reverse Distillation for Anomaly Detection 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\":\"tientrandinh-revisiting-reverse-distillation\",\"task\":\"Install Revisiting Reverse Distillation\",\"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 \"Revisiting Reverse Distillation\" as a Claude Code skill from https://github.com/tientrandinh/Revisiting-Reverse-Distillation. 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 2023) Revisiting Reverse Distillation for Anomaly Detection 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\":\"tientrandinh-revisiting-reverse-distillation\",\"task\":\"Install Revisiting Reverse Distillation\",\"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 \"Revisiting Reverse Distillation\" from https://github.com/tientrandinh/Revisiting-Reverse-Distillation 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 2023) Revisiting Reverse Distillation for Anomaly Detection 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\":\"tientrandinh-revisiting-reverse-distillation\",\"task\":\"Install Revisiting Reverse Distillation\",\"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/tientrandinh-revisiting-reverse-distillation/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/tientrandinh-revisiting-reverse-distillation"},"trust":{"score":68,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"170 GitHub stars","repoActivity":"170 stars, 32 forks","lastPushed":"3y since push","license":"MIT","repository":"https://github.com/tientrandinh/Revisiting-Reverse-Distillation","install":"npx skills add tientrandinh/Revisiting-Reverse-Distillation","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["robotics-iot","computer-vision","automation","anomaly-detection","cvpr2023","deep-learning"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 170 stars, 32 forks; issue activity unavailable in current metadata","Recent maintenance: 3y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":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: 170 stars, 32 forks; issue activity unavailable in current metadata","Recent maintenance: 3y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":42,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"3y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Documentation summary is thin","Repository appears stale","Quality score needs review","Stars/forks activity: 170 stars, 32 forks; issue activity unavailable in current metadata"],"agent_contract":{"task_input":"Use Revisiting Reverse Distillation 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":"tientrandinh-revisiting-reverse-distillation (Revisiting Reverse Distillation)","install_command":"npx skills add tientrandinh/Revisiting-Reverse-Distillation","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":"tientrandinh-revisiting-reverse-distillation","task":"Use Revisiting Reverse Distillation 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/tientrandinh-revisiting-reverse-distillation","api":"https://www.openagentskill.com/api/agent/skills/tientrandinh-revisiting-reverse-distillation","audit":"https://www.openagentskill.com/skills/tientrandinh-revisiting-reverse-distillation/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=tientrandinh-revisiting-reverse-distillation&task=Use%20Revisiting%20Reverse%20Distillation%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Revisiting%20Reverse%20Distillation%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Revisiting%20Reverse%20Distillation%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/tientrandinh-revisiting-reverse-distillation/install","manifest":"https://www.openagentskill.com/api/registry/manifest/tientrandinh-revisiting-reverse-distillation"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"tientrandinh-revisiting-reverse-distillation","name":"Revisiting Reverse Distillation","description":"(CVPR 2023) Revisiting Reverse Distillation for Anomaly Detection","category":"robotics-iot","url":"https://www.openagentskill.com/skills/tientrandinh-revisiting-reverse-distillation","repository":"https://github.com/tientrandinh/Revisiting-Reverse-Distillation","github_repo":"tientrandinh/Revisiting-Reverse-Distillation"},"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 tientrandinh/Revisiting-Reverse-Distillation","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 tientrandinh-revisiting-reverse-distillation"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Revisiting Reverse Distillation\" agent skill from https://github.com/tientrandinh/Revisiting-Reverse-Distillation. 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 2023) Revisiting Reverse Distillation for Anomaly Detection 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\":\"tientrandinh-revisiting-reverse-distillation\",\"task\":\"Install Revisiting Reverse Distillation\",\"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 \"Revisiting Reverse Distillation\" as a Claude Code skill from https://github.com/tientrandinh/Revisiting-Reverse-Distillation. 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 2023) Revisiting Reverse Distillation for Anomaly Detection 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\":\"tientrandinh-revisiting-reverse-distillation\",\"task\":\"Install Revisiting Reverse Distillation\",\"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 \"Revisiting Reverse Distillation\" from https://github.com/tientrandinh/Revisiting-Reverse-Distillation 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 2023) Revisiting Reverse Distillation for Anomaly Detection 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\":\"tientrandinh-revisiting-reverse-distillation\",\"task\":\"Install Revisiting Reverse Distillation\",\"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/tientrandinh-revisiting-reverse-distillation/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/tientrandinh-revisiting-reverse-distillation"},"trust":{"score":68,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"170 GitHub stars","repoActivity":"170 stars, 32 forks","lastPushed":"3y since push","license":"MIT","repository":"https://github.com/tientrandinh/Revisiting-Reverse-Distillation","install":"npx skills add tientrandinh/Revisiting-Reverse-Distillation","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["robotics-iot","computer-vision","automation","anomaly-detection","cvpr2023","deep-learning"],"known_risks":["Repository looks stale","Quality score needs review","Documentation summary is thin","Stars/forks activity: 170 stars, 32 forks; issue activity unavailable in current metadata","Recent maintenance: 3y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":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: 170 stars, 32 forks; issue activity unavailable in current metadata","Recent maintenance: 3y since push","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":42,"label":"Needs review"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"3y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Documentation summary is thin","Repository appears stale","Quality score needs review","Stars/forks activity: 170 stars, 32 forks; issue activity unavailable in current metadata"],"agent_contract":{"task_input":"Use Revisiting Reverse Distillation 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":"tientrandinh-revisiting-reverse-distillation (Revisiting Reverse Distillation)","install_command":"npx skills add tientrandinh/Revisiting-Reverse-Distillation","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":"tientrandinh-revisiting-reverse-distillation","task":"Use Revisiting Reverse Distillation 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/tientrandinh-revisiting-reverse-distillation","api":"https://www.openagentskill.com/api/agent/skills/tientrandinh-revisiting-reverse-distillation","audit":"https://www.openagentskill.com/skills/tientrandinh-revisiting-reverse-distillation/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=tientrandinh-revisiting-reverse-distillation&task=Use%20Revisiting%20Reverse%20Distillation%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Revisiting%20Reverse%20Distillation%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Revisiting%20Reverse%20Distillation%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/tientrandinh-revisiting-reverse-distillation/install","manifest":"https://www.openagentskill.com/api/registry/manifest/tientrandinh-revisiting-reverse-distillation"}},"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":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"install":"npx skills add tientrandinh/Revisiting-Reverse-Distillation","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 tientrandinh-revisiting-reverse-distillation","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 \"Revisiting Reverse Distillation\" agent skill from https://github.com/tientrandinh/Revisiting-Reverse-Distillation. 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 2023) Revisiting Reverse Distillation for Anomaly Detection 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\":\"tientrandinh-revisiting-reverse-distillation\",\"task\":\"Install Revisiting Reverse Distillation\",\"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 \"Revisiting Reverse Distillation\" as a Claude Code skill from https://github.com/tientrandinh/Revisiting-Reverse-Distillation. 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 2023) Revisiting Reverse Distillation for Anomaly Detection 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\":\"tientrandinh-revisiting-reverse-distillation\",\"task\":\"Install Revisiting Reverse Distillation\",\"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 \"Revisiting Reverse Distillation\" from https://github.com/tientrandinh/Revisiting-Reverse-Distillation 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 2023) Revisiting Reverse Distillation for Anomaly Detection 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\":\"tientrandinh-revisiting-reverse-distillation\",\"task\":\"Install Revisiting Reverse Distillation\",\"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/tientrandinh/Revisiting-Reverse-Distillation","github_repo":"tientrandinh/Revisiting-Reverse-Distillation","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"tientrandinh/revisiting-reverse-distillation","recommendation_reasons":["Matches task terms: distillation","Install handoff is available","Repository freshness signal is available","Registry match score 15"],"urls":{"web":"https://www.openagentskill.com/skills/tientrandinh-revisiting-reverse-distillation","api":"https://www.openagentskill.com/api/agent/skills/tientrandinh-revisiting-reverse-distillation","install_api":"https://www.openagentskill.com/api/skills/tientrandinh-revisiting-reverse-distillation/install","audit":"https://www.openagentskill.com/skills/tientrandinh-revisiting-reverse-distillation/audit","repository":"https://github.com/tientrandinh/Revisiting-Reverse-Distillation"}},{"rank":4,"match_type":"related","match_score":12,"raw_match_score":85.6,"semantic_relevance":30,"slug":"nuwa-skill","name":"女娲.Skill","description":"你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式。","tagline":"蒸馏任何人，不只是同事","category":"Personal AI","tags":["distillation","thinking","chinese","mental-models","蒸馏","心智模型","知识传承","同事宇宙"],"author":{"name":"alchaincyf","verified":true,"url":"https://github.com/alchaincyf"},"attribution":{"status":"registry_indexed","statusLabel":"Registry indexed","shortLabel":"REGISTRY INDEXED","sourceLabel":"admin","sourceDetail":"alchaincyf/nuwa-skill","creatorName":"alchaincyf","creatorUrl":"https://github.com/alchaincyf","sourceUrl":"https://github.com/alchaincyf/nuwa-skill","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/nuwa-skill#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":28246,"forks":3983,"verified_installs":2,"install_attempts":2,"successful_runs":2,"total_outcomes":2,"downloads":0,"rating":0,"review_count":0,"quality_score":73.66},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"28K","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":100,"weight":0.13,"status":"pass","detail":"28K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":97,"weight":0.08,"status":"pass","detail":"28K stars, 4.0K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"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 alchaincyf/nuwa-skill"},{"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/alchaincyf/nuwa-skill"},{"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":"28K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"28K stars, 4.0K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add alchaincyf/nuwa-skill"},{"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/alchaincyf/nuwa-skill"},{"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","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"28K GitHub stars","repoActivity":"28K stars, 4.0K forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/alchaincyf/nuwa-skill","install":"npx skills add alchaincyf/nuwa-skill","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 alchaincyf/nuwa-skill","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","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["Personal AI","distillation","thinking","chinese","mental-models","蒸馏"],"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","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":79,"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","79/100 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","79/100 agent safety score"]},"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"RAG and knowledge","description":"I need my agent to build a RAG workflow over documents and retrieve reliable context.","useCases":[{"slug":"web-scraping","title":"Web scraping"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add alchaincyf/nuwa-skill","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":28246,"starsLabel":"28K","forks":3983,"license":"MIT","qualityScore":100,"trustScore":88,"auditScore":91},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":51,"lastPushedAt":"2026-07-02T03:11:38+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"coverageTags":["Research","RAG and knowledge","Personal AI","distillation","thinking","chinese","mental-models","蒸馏"]},"audit":{"audit_score":91,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Web scraping","role":"Primary pick","primary_fit":"Web scraping","best_for":["Web scraping 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 Web scraping 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":"nuwa-skill","name":"女娲.Skill","description":"你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式。","category":"Personal AI","url":"https://www.openagentskill.com/skills/nuwa-skill","repository":"https://github.com/alchaincyf/nuwa-skill","github_repo":"alchaincyf/nuwa-skill"},"suited_tasks":["Web scraping workflows","general agent builders","teams that value GitHub adoption signals","Crawl target URLs","Extract tables and metadata","Normalize messy page content","Inspect source files","Explain architecture"],"suited_agents":["Python","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add alchaincyf/nuwa-skill","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 nuwa-skill"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"女娲.Skill\" agent skill from https://github.com/alchaincyf/nuwa-skill. 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: 你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式。 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\":\"nuwa-skill\",\"task\":\"Install 女娲.Skill\",\"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 \"女娲.Skill\" as a Claude Code skill from https://github.com/alchaincyf/nuwa-skill. 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: 你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式。 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\":\"nuwa-skill\",\"task\":\"Install 女娲.Skill\",\"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 \"女娲.Skill\" from https://github.com/alchaincyf/nuwa-skill 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: 你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式。 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\":\"nuwa-skill\",\"task\":\"Install 女娲.Skill\",\"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/nuwa-skill/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/nuwa-skill"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"28K GitHub stars","repoActivity":"28K stars, 4.0K forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/alchaincyf/nuwa-skill","install":"npx skills add alchaincyf/nuwa-skill","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":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["Personal AI","distillation","thinking","chinese","mental-models","蒸馏"],"known_risks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":91,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use 女娲.Skill 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: 91/100 Safe to try","Safety: 79/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"nuwa-skill (女娲.Skill)","install_command":"npx skills add alchaincyf/nuwa-skill","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":"nuwa-skill","task":"Use 女娲.Skill 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/nuwa-skill","api":"https://www.openagentskill.com/api/agent/skills/nuwa-skill","audit":"https://www.openagentskill.com/skills/nuwa-skill/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=nuwa-skill&task=Use%20%E5%A5%B3%E5%A8%B2.Skill%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20%E5%A5%B3%E5%A8%B2.Skill%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20%E5%A5%B3%E5%A8%B2.Skill%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/nuwa-skill/install","manifest":"https://www.openagentskill.com/api/registry/manifest/nuwa-skill"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"nuwa-skill","name":"女娲.Skill","description":"你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式。","category":"Personal AI","url":"https://www.openagentskill.com/skills/nuwa-skill","repository":"https://github.com/alchaincyf/nuwa-skill","github_repo":"alchaincyf/nuwa-skill"},"suited_tasks":["Web scraping workflows","general agent builders","teams that value GitHub adoption signals","Crawl target URLs","Extract tables and metadata","Normalize messy page content","Inspect source files","Explain architecture"],"suited_agents":["Python","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add alchaincyf/nuwa-skill","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 nuwa-skill"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"女娲.Skill\" agent skill from https://github.com/alchaincyf/nuwa-skill. 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: 你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式。 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\":\"nuwa-skill\",\"task\":\"Install 女娲.Skill\",\"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 \"女娲.Skill\" as a Claude Code skill from https://github.com/alchaincyf/nuwa-skill. 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: 你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式。 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\":\"nuwa-skill\",\"task\":\"Install 女娲.Skill\",\"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 \"女娲.Skill\" from https://github.com/alchaincyf/nuwa-skill 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: 你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式。 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\":\"nuwa-skill\",\"task\":\"Install 女娲.Skill\",\"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/nuwa-skill/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/nuwa-skill"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"28K GitHub stars","repoActivity":"28K stars, 4.0K forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/alchaincyf/nuwa-skill","install":"npx skills add alchaincyf/nuwa-skill","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":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["Personal AI","distillation","thinking","chinese","mental-models","蒸馏"],"known_risks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":91,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use 女娲.Skill 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: 91/100 Safe to try","Safety: 79/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"nuwa-skill (女娲.Skill)","install_command":"npx skills add alchaincyf/nuwa-skill","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":"nuwa-skill","task":"Use 女娲.Skill 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/nuwa-skill","api":"https://www.openagentskill.com/api/agent/skills/nuwa-skill","audit":"https://www.openagentskill.com/skills/nuwa-skill/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=nuwa-skill&task=Use%20%E5%A5%B3%E5%A8%B2.Skill%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20%E5%A5%B3%E5%A8%B2.Skill%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20%E5%A5%B3%E5%A8%B2.Skill%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/nuwa-skill/install","manifest":"https://www.openagentskill.com/api/registry/manifest/nuwa-skill"}},"platforms":["Python"],"use_cases":[{"slug":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"install":"npx skills add alchaincyf/nuwa-skill","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 nuwa-skill","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 \"女娲.Skill\" agent skill from https://github.com/alchaincyf/nuwa-skill. 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: 你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式。 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\":\"nuwa-skill\",\"task\":\"Install 女娲.Skill\",\"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 \"女娲.Skill\" as a Claude Code skill from https://github.com/alchaincyf/nuwa-skill. 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: 你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式。 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\":\"nuwa-skill\",\"task\":\"Install 女娲.Skill\",\"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 \"女娲.Skill\" from https://github.com/alchaincyf/nuwa-skill 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: 你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式。 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\":\"nuwa-skill\",\"task\":\"Install 女娲.Skill\",\"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/alchaincyf/nuwa-skill","github_repo":"alchaincyf/nuwa-skill","version":"1.0.0","license":"MIT","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"alchaincyf/nuwa-skill","recommendation_reasons":["Matches task terms: distillation","Strong GitHub adoption: 28,246 stars","Quality score 74/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/nuwa-skill","api":"https://www.openagentskill.com/api/agent/skills/nuwa-skill","install_api":"https://www.openagentskill.com/api/skills/nuwa-skill/install","audit":"https://www.openagentskill.com/skills/nuwa-skill/audit","repository":"https://github.com/alchaincyf/nuwa-skill"}},{"rank":5,"match_type":"related","match_score":10,"raw_match_score":69.3,"semantic_relevance":30,"slug":"lightly-ai-lightly-train","name":"Lightly Train","description":"All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.","tagline":"All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.","category":"robotics-iot","tags":["computer-vision","automation","robotics-iot","contrastive-learning","deep-learning","dinov2","dinov3","distillation","embeddings","eomt"],"author":{"name":"lightly-ai","verified":true,"url":"https://github.com/lightly-ai"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"lightly-ai/lightly-train","creatorName":"lightly-ai","creatorUrl":"https://github.com/lightly-ai","sourceUrl":"https://github.com/lightly-ai/lightly-train","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/lightly-ai-lightly-train#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":1581,"forks":80,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":61.09},"quality":{"score":91,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"1.6K","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"AGPL-3.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":87,"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":"1.6K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":77,"weight":0.08,"status":"info","detail":"1.6K stars, 80 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":"AGPL-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 lightly-ai/lightly-train"},{"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/lightly-ai/lightly-train"},{"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":"1.6K GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"1.6K stars, 80 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"AGPL-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 lightly-ai/lightly-train"},{"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/lightly-ai/lightly-train"},{"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":"1.6K GitHub stars","repoActivity":"1.6K stars, 80 forks","lastPushed":"2mo since push","license":"AGPL-3.0","repository":"https://github.com/lightly-ai/lightly-train","install":"npx skills add lightly-ai/lightly-train","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 lightly-ai/lightly-train","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","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","contrastive-learning","deep-learning","dinov2"],"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":77,"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","77/100 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","77/100 agent safety score"]},"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"RAG and knowledge","description":"I need my agent to build a RAG workflow over documents and retrieve reliable context.","useCases":[{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"workflow-automation","title":"Workflow automation"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add lightly-ai/lightly-train","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":1581,"starsLabel":"1.6K","forks":80,"license":"AGPL-3.0","qualityScore":91,"trustScore":87,"auditScore":89},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":67,"lastPushedAt":"2026-06-16T08:42:47+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Research","RAG and knowledge","robotics-iot","computer-vision","automation","contrastive-learning","deep-learning","dinov2"]},"audit":{"audit_score":89,"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 RAG and knowledge","role":"Primary pick","primary_fit":"RAG and knowledge","best_for":["RAG and knowledge 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 RAG and knowledge task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"lightly-ai-lightly-train","name":"Lightly Train","description":"All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.","category":"robotics-iot","url":"https://www.openagentskill.com/skills/lightly-ai-lightly-train","repository":"https://github.com/lightly-ai/lightly-train","github_repo":"lightly-ai/lightly-train"},"suited_tasks":["RAG and knowledge workflows","general agent builders","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Navigate pages","Click and type safely"],"suited_agents":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add lightly-ai/lightly-train","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 lightly-ai-lightly-train"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Lightly Train\" agent skill from https://github.com/lightly-ai/lightly-train. 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: All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation. 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\":\"lightly-ai-lightly-train\",\"task\":\"Install Lightly Train\",\"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 \"Lightly Train\" as a Claude Code skill from https://github.com/lightly-ai/lightly-train. 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: All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation. 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\":\"lightly-ai-lightly-train\",\"task\":\"Install Lightly Train\",\"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 \"Lightly Train\" from https://github.com/lightly-ai/lightly-train 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: All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation. 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\":\"lightly-ai-lightly-train\",\"task\":\"Install Lightly Train\",\"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/lightly-ai-lightly-train/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/lightly-ai-lightly-train"},"trust":{"score":87,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"1.6K GitHub stars","repoActivity":"1.6K stars, 80 forks","lastPushed":"2mo since push","license":"AGPL-3.0","repository":"https://github.com/lightly-ai/lightly-train","install":"npx skills add lightly-ai/lightly-train","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","contrastive-learning","deep-learning","dinov2"],"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":89,"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":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","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 Lightly Train 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: 87/100 Production candidate","Audit: 89/100 Safe to try","Safety: 77/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"lightly-ai-lightly-train (Lightly Train)","install_command":"npx skills add lightly-ai/lightly-train","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":"lightly-ai-lightly-train","task":"Use Lightly Train 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/lightly-ai-lightly-train","api":"https://www.openagentskill.com/api/agent/skills/lightly-ai-lightly-train","audit":"https://www.openagentskill.com/skills/lightly-ai-lightly-train/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=lightly-ai-lightly-train&task=Use%20Lightly%20Train%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Lightly%20Train%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Lightly%20Train%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/lightly-ai-lightly-train/install","manifest":"https://www.openagentskill.com/api/registry/manifest/lightly-ai-lightly-train"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"lightly-ai-lightly-train","name":"Lightly Train","description":"All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation.","category":"robotics-iot","url":"https://www.openagentskill.com/skills/lightly-ai-lightly-train","repository":"https://github.com/lightly-ai/lightly-train","github_repo":"lightly-ai/lightly-train"},"suited_tasks":["RAG and knowledge workflows","general agent builders","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Navigate pages","Click and type safely"],"suited_agents":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add lightly-ai/lightly-train","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 lightly-ai-lightly-train"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Lightly Train\" agent skill from https://github.com/lightly-ai/lightly-train. 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: All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation. 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\":\"lightly-ai-lightly-train\",\"task\":\"Install Lightly Train\",\"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 \"Lightly Train\" as a Claude Code skill from https://github.com/lightly-ai/lightly-train. 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: All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation. 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\":\"lightly-ai-lightly-train\",\"task\":\"Install Lightly Train\",\"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 \"Lightly Train\" from https://github.com/lightly-ai/lightly-train 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: All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation. 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\":\"lightly-ai-lightly-train\",\"task\":\"Install Lightly Train\",\"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/lightly-ai-lightly-train/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/lightly-ai-lightly-train"},"trust":{"score":87,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"1.6K GitHub stars","repoActivity":"1.6K stars, 80 forks","lastPushed":"2mo since push","license":"AGPL-3.0","repository":"https://github.com/lightly-ai/lightly-train","install":"npx skills add lightly-ai/lightly-train","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","contrastive-learning","deep-learning","dinov2"],"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":89,"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":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","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 Lightly Train 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: 87/100 Production candidate","Audit: 89/100 Safe to try","Safety: 77/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"lightly-ai-lightly-train (Lightly Train)","install_command":"npx skills add lightly-ai/lightly-train","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":"lightly-ai-lightly-train","task":"Use Lightly Train 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/lightly-ai-lightly-train","api":"https://www.openagentskill.com/api/agent/skills/lightly-ai-lightly-train","audit":"https://www.openagentskill.com/skills/lightly-ai-lightly-train/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=lightly-ai-lightly-train&task=Use%20Lightly%20Train%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Lightly%20Train%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Lightly%20Train%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/lightly-ai-lightly-train/install","manifest":"https://www.openagentskill.com/api/registry/manifest/lightly-ai-lightly-train"}},"platforms":["Python","Computer Vision"],"use_cases":[{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"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"}],"install":"npx skills add lightly-ai/lightly-train","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 lightly-ai-lightly-train","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 \"Lightly Train\" agent skill from https://github.com/lightly-ai/lightly-train. 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: All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation. 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\":\"lightly-ai-lightly-train\",\"task\":\"Install Lightly Train\",\"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 \"Lightly Train\" as a Claude Code skill from https://github.com/lightly-ai/lightly-train. 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: All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation. 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\":\"lightly-ai-lightly-train\",\"task\":\"Install Lightly Train\",\"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 \"Lightly Train\" from https://github.com/lightly-ai/lightly-train 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: All-in-one training for vision models (YOLO, ViTs, RT-DETR, DINOv3): pretraining, fine-tuning, distillation. 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\":\"lightly-ai-lightly-train\",\"task\":\"Install Lightly Train\",\"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/lightly-ai/lightly-train","github_repo":"lightly-ai/lightly-train","version":"1.0.0","license":"AGPL-3.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"lightly-ai/lightly-train","recommendation_reasons":["Matches task terms: distillation","Useful GitHub adoption: 1,581 stars","Install handoff is available","Repository freshness signal is available","Registry match score 10"],"urls":{"web":"https://www.openagentskill.com/skills/lightly-ai-lightly-train","api":"https://www.openagentskill.com/api/agent/skills/lightly-ai-lightly-train","install_api":"https://www.openagentskill.com/api/skills/lightly-ai-lightly-train/install","audit":"https://www.openagentskill.com/skills/lightly-ai-lightly-train/audit","repository":"https://github.com/lightly-ai/lightly-train"}},{"rank":6,"match_type":"related","match_score":8,"raw_match_score":59.2,"semantic_relevance":30,"slug":"thu-ml-causal-forcing","name":"Causal Forcing","description":"[ICML 2026] Official codebase for \"Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation\" & Causal Forcing++","tagline":"[ICML 2026] Official codebase for \"Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation\" & Causal Forcing++","category":"media-automation","tags":["video-generation","creative","media","design","auto-regressive-diffusion-model","autoregressive-models","consistency-models","diffusion","diffusion-models","distillation"],"author":{"name":"thu-ml","verified":false,"url":"https://github.com/thu-ml"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"thu-ml/Causal-Forcing","creatorName":"thu-ml","creatorUrl":"https://github.com/thu-ml","sourceUrl":"https://github.com/thu-ml/Causal-Forcing","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/thu-ml-causal-forcing#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":786,"forks":45,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":50.97},"quality":{"score":74,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"786","tone":"positive"},{"label":"Freshness","value":"3mo 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":80,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":76,"weight":0.13,"status":"info","detail":"786 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":65,"weight":0.08,"status":"info","detail":"786 stars, 45 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"3mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"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 thu-ml/Causal-Forcing"},{"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/thu-ml/Causal-Forcing"},{"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":"786 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"786 stars, 45 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3mo 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 thu-ml/Causal-Forcing"},{"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/thu-ml/Causal-Forcing"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin"],"evidence":{"stars":"786 GitHub stars","repoActivity":"786 stars, 45 forks","lastPushed":"3mo since push","license":"Apache-2.0","repository":"https://github.com/thu-ml/Causal-Forcing","install":"npx skills add thu-ml/Causal-Forcing","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 thu-ml/Causal-Forcing","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3mo since push"]},"agentCompatibility":["Python","Video Generation","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":["media-automation","video-generation","creative","media","design","auto-regressive-diffusion-model"],"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":70,"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","70/100 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":["Quality score needs review"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","70/100 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":"Design and creative","description":"I need my agent to produce design assets, UI directions, presentations, or creative media workflows.","useCases":[{"slug":"design-creative","title":"Design and creative"},{"slug":"video-creation","title":"Video creation"},{"slug":"multimodal-media","title":"Multimodal media"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add thu-ml/Causal-Forcing","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":786,"starsLabel":"786","forks":45,"license":"Apache-2.0","qualityScore":74,"trustScore":80,"auditScore":82},"maintenance":{"status":"active","label":"3mo since push","daysSincePush":78,"lastPushedAt":"2026-06-05T11:51:00+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Quality score needs review","Documentation summary is thin"]},"coverageTags":["Design","Design and creative","media-automation","video-generation","creative","media","auto-regressive-diffusion-model","autoregressive-models"]},"audit":{"audit_score":82,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review","Documentation summary is thin"]},"decision":{"readiness_score":85,"readiness_label":"Production-ready","headline":"Primary pick for Design and creative","role":"Primary pick","primary_fit":"Design and creative","best_for":["Design and creative 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 Design and creative 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":"thu-ml-causal-forcing","name":"Causal Forcing","description":"[ICML 2026] Official codebase for \"Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation\" & Causal Forcing++","category":"media-automation","url":"https://www.openagentskill.com/skills/thu-ml-causal-forcing","repository":"https://github.com/thu-ml/Causal-Forcing","github_repo":"thu-ml/Causal-Forcing"},"suited_tasks":["Design and creative workflows","general agent builders","teams that value GitHub adoption signals","Inspect visual requirements","Generate reusable assets","Package output for review","Turn a brief into a shot plan","Assign references and camera motion"],"suited_agents":["Python","Video Generation","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add thu-ml/Causal-Forcing","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 thu-ml-causal-forcing"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Causal Forcing\" agent skill from https://github.com/thu-ml/Causal-Forcing. 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: [ICML 2026] Official codebase for \"Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation\" & Causal Forcing++ 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\":\"thu-ml-causal-forcing\",\"task\":\"Install Causal Forcing\",\"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 \"Causal Forcing\" as a Claude Code skill from https://github.com/thu-ml/Causal-Forcing. 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: [ICML 2026] Official codebase for \"Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation\" & Causal Forcing++ 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\":\"thu-ml-causal-forcing\",\"task\":\"Install Causal Forcing\",\"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 \"Causal Forcing\" from https://github.com/thu-ml/Causal-Forcing 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: [ICML 2026] Official codebase for \"Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation\" & Causal Forcing++ 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\":\"thu-ml-causal-forcing\",\"task\":\"Install Causal Forcing\",\"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/thu-ml-causal-forcing/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/thu-ml-causal-forcing"},"trust":{"score":80,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"786 GitHub stars","repoActivity":"786 stars, 45 forks","lastPushed":"3mo since push","license":"Apache-2.0","repository":"https://github.com/thu-ml/Causal-Forcing","install":"npx skills add thu-ml/Causal-Forcing","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":["media-automation","video-generation","creative","media","design","auto-regressive-diffusion-model"],"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":82,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review","Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","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":74,"label":"Strong"},"supply":{"track":"Design and creative production","scenario":"Design and creative","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","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 Causal Forcing 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: 80/100 Strong shortlist","Audit: 82/100 Safe to try","Safety: 70/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"thu-ml-causal-forcing (Causal Forcing)","install_command":"npx skills add thu-ml/Causal-Forcing","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":"thu-ml-causal-forcing","task":"Use Causal Forcing 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/thu-ml-causal-forcing","api":"https://www.openagentskill.com/api/agent/skills/thu-ml-causal-forcing","audit":"https://www.openagentskill.com/skills/thu-ml-causal-forcing/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=thu-ml-causal-forcing&task=Use%20Causal%20Forcing%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Causal%20Forcing%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Causal%20Forcing%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/thu-ml-causal-forcing/install","manifest":"https://www.openagentskill.com/api/registry/manifest/thu-ml-causal-forcing"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"thu-ml-causal-forcing","name":"Causal Forcing","description":"[ICML 2026] Official codebase for \"Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation\" & Causal Forcing++","category":"media-automation","url":"https://www.openagentskill.com/skills/thu-ml-causal-forcing","repository":"https://github.com/thu-ml/Causal-Forcing","github_repo":"thu-ml/Causal-Forcing"},"suited_tasks":["Design and creative workflows","general agent builders","teams that value GitHub adoption signals","Inspect visual requirements","Generate reusable assets","Package output for review","Turn a brief into a shot plan","Assign references and camera motion"],"suited_agents":["Python","Video Generation","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add thu-ml/Causal-Forcing","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 thu-ml-causal-forcing"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Causal Forcing\" agent skill from https://github.com/thu-ml/Causal-Forcing. 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: [ICML 2026] Official codebase for \"Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation\" & Causal Forcing++ 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\":\"thu-ml-causal-forcing\",\"task\":\"Install Causal Forcing\",\"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 \"Causal Forcing\" as a Claude Code skill from https://github.com/thu-ml/Causal-Forcing. 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: [ICML 2026] Official codebase for \"Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation\" & Causal Forcing++ 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\":\"thu-ml-causal-forcing\",\"task\":\"Install Causal Forcing\",\"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 \"Causal Forcing\" from https://github.com/thu-ml/Causal-Forcing 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: [ICML 2026] Official codebase for \"Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation\" & Causal Forcing++ 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\":\"thu-ml-causal-forcing\",\"task\":\"Install Causal Forcing\",\"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/thu-ml-causal-forcing/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/thu-ml-causal-forcing"},"trust":{"score":80,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"786 GitHub stars","repoActivity":"786 stars, 45 forks","lastPushed":"3mo since push","license":"Apache-2.0","repository":"https://github.com/thu-ml/Causal-Forcing","install":"npx skills add thu-ml/Causal-Forcing","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":["media-automation","video-generation","creative","media","design","auto-regressive-diffusion-model"],"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":82,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review","Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","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":74,"label":"Strong"},"supply":{"track":"Design and creative production","scenario":"Design and creative","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","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 Causal Forcing 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: 80/100 Strong shortlist","Audit: 82/100 Safe to try","Safety: 70/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"thu-ml-causal-forcing (Causal Forcing)","install_command":"npx skills add thu-ml/Causal-Forcing","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":"thu-ml-causal-forcing","task":"Use Causal Forcing 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/thu-ml-causal-forcing","api":"https://www.openagentskill.com/api/agent/skills/thu-ml-causal-forcing","audit":"https://www.openagentskill.com/skills/thu-ml-causal-forcing/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=thu-ml-causal-forcing&task=Use%20Causal%20Forcing%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Causal%20Forcing%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Causal%20Forcing%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/thu-ml-causal-forcing/install","manifest":"https://www.openagentskill.com/api/registry/manifest/thu-ml-causal-forcing"}},"platforms":["Python","Video Generation"],"use_cases":[{"slug":"design-creative","title":"Design and creative","url":"https://www.openagentskill.com/use-cases/design-creative"},{"slug":"video-creation","title":"Video creation","url":"https://www.openagentskill.com/use-cases/video-creation"},{"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 thu-ml/Causal-Forcing","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 thu-ml-causal-forcing","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 \"Causal Forcing\" agent skill from https://github.com/thu-ml/Causal-Forcing. 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: [ICML 2026] Official codebase for \"Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation\" & Causal Forcing++ 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\":\"thu-ml-causal-forcing\",\"task\":\"Install Causal Forcing\",\"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 \"Causal Forcing\" as a Claude Code skill from https://github.com/thu-ml/Causal-Forcing. 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: [ICML 2026] Official codebase for \"Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation\" & Causal Forcing++ 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\":\"thu-ml-causal-forcing\",\"task\":\"Install Causal Forcing\",\"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 \"Causal Forcing\" from https://github.com/thu-ml/Causal-Forcing 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: [ICML 2026] Official codebase for \"Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation\" & Causal Forcing++ 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\":\"thu-ml-causal-forcing\",\"task\":\"Install Causal Forcing\",\"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/thu-ml/Causal-Forcing","github_repo":"thu-ml/Causal-Forcing","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"thu-ml/causal-forcing","recommendation_reasons":["Matches task terms: distillation","Useful GitHub adoption: 786 stars","Install handoff is available","Repository freshness signal is available","Registry match score 8"],"urls":{"web":"https://www.openagentskill.com/skills/thu-ml-causal-forcing","api":"https://www.openagentskill.com/api/agent/skills/thu-ml-causal-forcing","install_api":"https://www.openagentskill.com/api/skills/thu-ml-causal-forcing/install","audit":"https://www.openagentskill.com/skills/thu-ml-causal-forcing/audit","repository":"https://github.com/thu-ml/Causal-Forcing"}},{"rank":7,"match_type":"related","match_score":8,"raw_match_score":58.9,"semantic_relevance":30,"slug":"nvlabs-rcm","name":"Rcm","description":"rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale","tagline":"rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale","category":"media-automation","tags":["video-generation","creative","media","design","autoregressive-video-generation","consistency-model","diffusion","distillation","distribution-matching","few-step-generation"],"author":{"name":"NVlabs","verified":false,"url":"https://github.com/NVlabs"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"NVlabs/rcm","creatorName":"NVlabs","creatorUrl":"https://github.com/NVlabs","sourceUrl":"https://github.com/NVlabs/rcm","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/nvlabs-rcm#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":701,"forks":26,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":50.62},"quality":{"score":74,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"701","tone":"positive"},{"label":"Freshness","value":"3mo 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":80,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":76,"weight":0.13,"status":"info","detail":"701 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":65,"weight":0.08,"status":"info","detail":"701 stars, 26 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"3mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"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 NVlabs/rcm"},{"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/NVlabs/rcm"},{"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":"701 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"701 stars, 26 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"3mo 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 NVlabs/rcm"},{"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/NVlabs/rcm"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin"],"evidence":{"stars":"701 GitHub stars","repoActivity":"701 stars, 26 forks","lastPushed":"3mo since push","license":"Apache-2.0","repository":"https://github.com/NVlabs/rcm","install":"npx skills add NVlabs/rcm","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 NVlabs/rcm","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3mo since push"]},"agentCompatibility":["Python","Video Generation","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":["media-automation","video-generation","creative","media","design","autoregressive-video-generation"],"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":70,"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","70/100 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":["Quality score needs review"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","70/100 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":"Design and creative","description":"I need my agent to produce design assets, UI directions, presentations, or creative media workflows.","useCases":[{"slug":"design-creative","title":"Design and creative"},{"slug":"video-creation","title":"Video creation"},{"slug":"multimodal-media","title":"Multimodal media"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add NVlabs/rcm","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":701,"starsLabel":"701","forks":26,"license":"Apache-2.0","qualityScore":74,"trustScore":80,"auditScore":82},"maintenance":{"status":"active","label":"3mo since push","daysSincePush":78,"lastPushedAt":"2026-06-05T04:14:04+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Quality score needs review","Documentation summary is thin"]},"coverageTags":["Design","Design and creative","media-automation","video-generation","creative","media","autoregressive-video-generation","consistency-model"]},"audit":{"audit_score":82,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review","Documentation summary is thin"]},"decision":{"readiness_score":85,"readiness_label":"Production-ready","headline":"Primary pick for Design and creative","role":"Primary pick","primary_fit":"Design and creative","best_for":["Design and creative 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 Design and creative 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":"nvlabs-rcm","name":"Rcm","description":"rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale","category":"media-automation","url":"https://www.openagentskill.com/skills/nvlabs-rcm","repository":"https://github.com/NVlabs/rcm","github_repo":"NVlabs/rcm"},"suited_tasks":["Design and creative workflows","general agent builders","teams that value GitHub adoption signals","Inspect visual requirements","Generate reusable assets","Package output for review","Turn a brief into a shot plan","Assign references and camera motion"],"suited_agents":["Python","Video Generation","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add NVlabs/rcm","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 nvlabs-rcm"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Rcm\" agent skill from https://github.com/NVlabs/rcm. 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: rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale 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\":\"nvlabs-rcm\",\"task\":\"Install Rcm\",\"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 \"Rcm\" as a Claude Code skill from https://github.com/NVlabs/rcm. 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: rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale 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\":\"nvlabs-rcm\",\"task\":\"Install Rcm\",\"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 \"Rcm\" from https://github.com/NVlabs/rcm 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: rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale 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\":\"nvlabs-rcm\",\"task\":\"Install Rcm\",\"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/nvlabs-rcm/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/nvlabs-rcm"},"trust":{"score":80,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"701 GitHub stars","repoActivity":"701 stars, 26 forks","lastPushed":"3mo since push","license":"Apache-2.0","repository":"https://github.com/NVlabs/rcm","install":"npx skills add NVlabs/rcm","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":["media-automation","video-generation","creative","media","design","autoregressive-video-generation"],"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":82,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review","Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","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":74,"label":"Strong"},"supply":{"track":"Design and creative production","scenario":"Design and creative","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","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 Rcm 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: 80/100 Strong shortlist","Audit: 82/100 Safe to try","Safety: 70/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"nvlabs-rcm (Rcm)","install_command":"npx skills add NVlabs/rcm","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":"nvlabs-rcm","task":"Use Rcm 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/nvlabs-rcm","api":"https://www.openagentskill.com/api/agent/skills/nvlabs-rcm","audit":"https://www.openagentskill.com/skills/nvlabs-rcm/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=nvlabs-rcm&task=Use%20Rcm%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Rcm%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Rcm%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/nvlabs-rcm/install","manifest":"https://www.openagentskill.com/api/registry/manifest/nvlabs-rcm"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"nvlabs-rcm","name":"Rcm","description":"rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale","category":"media-automation","url":"https://www.openagentskill.com/skills/nvlabs-rcm","repository":"https://github.com/NVlabs/rcm","github_repo":"NVlabs/rcm"},"suited_tasks":["Design and creative workflows","general agent builders","teams that value GitHub adoption signals","Inspect visual requirements","Generate reusable assets","Package output for review","Turn a brief into a shot plan","Assign references and camera motion"],"suited_agents":["Python","Video Generation","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add NVlabs/rcm","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 nvlabs-rcm"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Rcm\" agent skill from https://github.com/NVlabs/rcm. 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: rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale 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\":\"nvlabs-rcm\",\"task\":\"Install Rcm\",\"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 \"Rcm\" as a Claude Code skill from https://github.com/NVlabs/rcm. 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: rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale 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\":\"nvlabs-rcm\",\"task\":\"Install Rcm\",\"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 \"Rcm\" from https://github.com/NVlabs/rcm 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: rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale 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\":\"nvlabs-rcm\",\"task\":\"Install Rcm\",\"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/nvlabs-rcm/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/nvlabs-rcm"},"trust":{"score":80,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"701 GitHub stars","repoActivity":"701 stars, 26 forks","lastPushed":"3mo since push","license":"Apache-2.0","repository":"https://github.com/NVlabs/rcm","install":"npx skills add NVlabs/rcm","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":["media-automation","video-generation","creative","media","design","autoregressive-video-generation"],"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":82,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Quality score needs review","Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","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":74,"label":"Strong"},"supply":{"track":"Design and creative production","scenario":"Design and creative","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","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 Rcm 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: 80/100 Strong shortlist","Audit: 82/100 Safe to try","Safety: 70/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"nvlabs-rcm (Rcm)","install_command":"npx skills add NVlabs/rcm","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":"nvlabs-rcm","task":"Use Rcm 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/nvlabs-rcm","api":"https://www.openagentskill.com/api/agent/skills/nvlabs-rcm","audit":"https://www.openagentskill.com/skills/nvlabs-rcm/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=nvlabs-rcm&task=Use%20Rcm%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Rcm%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Rcm%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/nvlabs-rcm/install","manifest":"https://www.openagentskill.com/api/registry/manifest/nvlabs-rcm"}},"platforms":["Python","Video Generation"],"use_cases":[{"slug":"design-creative","title":"Design and creative","url":"https://www.openagentskill.com/use-cases/design-creative"},{"slug":"video-creation","title":"Video creation","url":"https://www.openagentskill.com/use-cases/video-creation"},{"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"}],"install":"npx skills add NVlabs/rcm","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 nvlabs-rcm","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 \"Rcm\" agent skill from https://github.com/NVlabs/rcm. 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: rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale 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\":\"nvlabs-rcm\",\"task\":\"Install Rcm\",\"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 \"Rcm\" as a Claude Code skill from https://github.com/NVlabs/rcm. 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: rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale 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\":\"nvlabs-rcm\",\"task\":\"Install Rcm\",\"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 \"Rcm\" from https://github.com/NVlabs/rcm 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: rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale 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\":\"nvlabs-rcm\",\"task\":\"Install Rcm\",\"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/NVlabs/rcm","github_repo":"NVlabs/rcm","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"nvlabs/rcm","recommendation_reasons":["Matches task terms: distillation","Useful GitHub adoption: 701 stars","Install handoff is available","Repository freshness signal is available","Registry match score 8"],"urls":{"web":"https://www.openagentskill.com/skills/nvlabs-rcm","api":"https://www.openagentskill.com/api/agent/skills/nvlabs-rcm","install_api":"https://www.openagentskill.com/api/skills/nvlabs-rcm/install","audit":"https://www.openagentskill.com/skills/nvlabs-rcm/audit","repository":"https://github.com/NVlabs/rcm"}},{"rank":8,"match_type":"related","match_score":8,"raw_match_score":56.6,"semantic_relevance":30,"slug":"megvii-research-mdistiller","name":"Mdistiller","description":"The official implementation of [CVPR2022] Decoupled Knowledge Distillation https://arxiv.org/abs/2203.08679 and [ICCV2023] DOT: A Distillation-Oriented Trainer  https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_DOT_A_Distillation-Oriented_Trainer_ICCV_2023_paper.pdf","tagline":"The official implementation of [CVPR2022] Decoupled Knowledge Distillation https://arxiv.org/abs/2203.08679 and [ICCV2023] DOT: A Distillation-Oriented Trainer  https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_DOT_A_Distillation-Oriented_Trainer_ICCV_2023_paper.pdf","category":"robotics-iot","tags":["computer-vision","automation","robotics-iot","cifar","coco","cvpr2022","deep-learning","iccv2023","imagenet","knowledge-distillation"],"author":{"name":"megvii-research","verified":false,"url":"https://github.com/megvii-research"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"megvii-research/mdistiller","creatorName":"megvii-research","creatorUrl":"https://github.com/megvii-research","sourceUrl":"https://github.com/megvii-research/mdistiller","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/megvii-research-mdistiller#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":901,"forks":132,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":39.39},"quality":{"score":51,"tier":"review","label":"Needs review","summary":"Inspect the repository carefully before adding it to an agent workflow.","signals":[{"label":"GitHub stars","value":"901","tone":"positive"},{"label":"Freshness","value":"3y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":69,"tier":"review","label":"Manual review","summary":"Potentially useful, but at least one trust signal needs human inspection.","recommendedAction":"Inspect the repository, license, and recent activity before connecting it to agent workflows.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":76,"weight":0.13,"status":"info","detail":"901 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":71,"weight":0.08,"status":"info","detail":"901 stars, 132 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":22,"weight":0.14,"status":"fail","detail":"3y since push"},{"id":"license","label":"License clarity","score":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 megvii-research/mdistiller"},{"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/megvii-research/mdistiller"},{"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":"901 GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"901 stars, 132 forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"3y 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 megvii-research/mdistiller"},{"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/megvii-research/mdistiller"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["License is unclear","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push","License clarity: Unknown"],"evidence":{"stars":"901 GitHub stars","repoActivity":"901 stars, 132 forks","lastPushed":"3y since push","license":"Unknown","repository":"https://github.com/megvii-research/mdistiller","install":"npx skills add megvii-research/mdistiller","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 megvii-research/mdistiller","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","3y 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","Recent maintenance: 3y 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","cifar","coco","cvpr2022"],"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","Recent maintenance: 3y since push","License clarity: Unknown"]},"safety":{"score":46,"level":"avoid_auto_install","label":"Avoid automatic install","safety_tier":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","summary":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","auto_install_policy":"review","reasons":["License is unclear","46/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["License is unclear"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","reasons":["License is unclear","46/100 agent safety score"]},"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"RAG and knowledge","description":"I need my agent to build a RAG workflow over documents and retrieve reliable context.","useCases":[{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"research-agents","title":"Research agents"},{"slug":"multimodal-media","title":"Multimodal media"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add megvii-research/mdistiller","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":901,"starsLabel":"901","forks":132,"license":"Unknown","qualityScore":51,"trustScore":69,"auditScore":62},"maintenance":{"status":"stale","label":"3y since push","daysSincePush":1021,"lastPushedAt":"2023-11-05T09:23:59+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":["Research","RAG and knowledge","robotics-iot","computer-vision","automation","cifar","coco","cvpr2022"]},"audit":{"audit_score":62,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin"]},"decision":{"readiness_score":53,"readiness_label":"Needs manual review","headline":"Needs validation for RAG and knowledge","role":"Needs validation","primary_fit":"RAG and knowledge","best_for":["RAG and knowledge workflows","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 RAG and knowledge task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"megvii-research-mdistiller","name":"Mdistiller","description":"The official implementation of [CVPR2022] Decoupled Knowledge Distillation https://arxiv.org/abs/2203.08679 and [ICCV2023] DOT: A Distillation-Oriented Trainer  https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_DOT_A_Distillation-Oriented_Trainer_ICCV_2023_paper.pdf","category":"robotics-iot","url":"https://www.openagentskill.com/skills/megvii-research-mdistiller","repository":"https://github.com/megvii-research/mdistiller","github_repo":"megvii-research/mdistiller"},"suited_tasks":["RAG and knowledge workflows","general agent builders","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Search sources","Extract claims"],"suited_agents":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add megvii-research/mdistiller","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 megvii-research-mdistiller"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Mdistiller\" agent skill from https://github.com/megvii-research/mdistiller. 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: The official implementation of [CVPR2022] Decoupled Knowledge Distillation https://arxiv.org/abs/2203.08679 and [ICCV2023] DOT: A Distillation-Oriented Trainer https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_DOT_A_Distillation-Oriented_Trainer_ICCV_2023_paper.pdf 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\":\"megvii-research-mdistiller\",\"task\":\"Install Mdistiller\",\"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 \"Mdistiller\" as a Claude Code skill from https://github.com/megvii-research/mdistiller. 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: The official implementation of [CVPR2022] Decoupled Knowledge Distillation https://arxiv.org/abs/2203.08679 and [ICCV2023] DOT: A Distillation-Oriented Trainer https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_DOT_A_Distillation-Oriented_Trainer_ICCV_2023_paper.pdf 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\":\"megvii-research-mdistiller\",\"task\":\"Install Mdistiller\",\"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 \"Mdistiller\" from https://github.com/megvii-research/mdistiller 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: The official implementation of [CVPR2022] Decoupled Knowledge Distillation https://arxiv.org/abs/2203.08679 and [ICCV2023] DOT: A Distillation-Oriented Trainer https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_DOT_A_Distillation-Oriented_Trainer_ICCV_2023_paper.pdf 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\":\"megvii-research-mdistiller\",\"task\":\"Install Mdistiller\",\"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/megvii-research-mdistiller/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/megvii-research-mdistiller"},"trust":{"score":69,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"901 GitHub stars","repoActivity":"901 stars, 132 forks","lastPushed":"3y since push","license":"Unknown","repository":"https://github.com/megvii-research/mdistiller","install":"npx skills add megvii-research/mdistiller","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","cifar","coco","cvpr2022"],"known_risks":["License is unclear","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":62,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y 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":51,"label":"Needs review"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"3y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","License is unclear","Repository appears stale","Quality score needs review","Documentation summary is thin"],"agent_contract":{"task_input":"Use Mdistiller in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 69/100 Manual review","Audit: 62/100 Needs review","Safety: 46/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"megvii-research-mdistiller (Mdistiller)","install_command":"npx skills add megvii-research/mdistiller","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":"megvii-research-mdistiller","task":"Use Mdistiller 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/megvii-research-mdistiller","api":"https://www.openagentskill.com/api/agent/skills/megvii-research-mdistiller","audit":"https://www.openagentskill.com/skills/megvii-research-mdistiller/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=megvii-research-mdistiller&task=Use%20Mdistiller%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Mdistiller%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Mdistiller%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/megvii-research-mdistiller/install","manifest":"https://www.openagentskill.com/api/registry/manifest/megvii-research-mdistiller"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"megvii-research-mdistiller","name":"Mdistiller","description":"The official implementation of [CVPR2022] Decoupled Knowledge Distillation https://arxiv.org/abs/2203.08679 and [ICCV2023] DOT: A Distillation-Oriented Trainer  https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_DOT_A_Distillation-Oriented_Trainer_ICCV_2023_paper.pdf","category":"robotics-iot","url":"https://www.openagentskill.com/skills/megvii-research-mdistiller","repository":"https://github.com/megvii-research/mdistiller","github_repo":"megvii-research/mdistiller"},"suited_tasks":["RAG and knowledge workflows","general agent builders","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Search sources","Extract claims"],"suited_agents":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add megvii-research/mdistiller","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 megvii-research-mdistiller"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Mdistiller\" agent skill from https://github.com/megvii-research/mdistiller. 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: The official implementation of [CVPR2022] Decoupled Knowledge Distillation https://arxiv.org/abs/2203.08679 and [ICCV2023] DOT: A Distillation-Oriented Trainer https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_DOT_A_Distillation-Oriented_Trainer_ICCV_2023_paper.pdf 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\":\"megvii-research-mdistiller\",\"task\":\"Install Mdistiller\",\"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 \"Mdistiller\" as a Claude Code skill from https://github.com/megvii-research/mdistiller. 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: The official implementation of [CVPR2022] Decoupled Knowledge Distillation https://arxiv.org/abs/2203.08679 and [ICCV2023] DOT: A Distillation-Oriented Trainer https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_DOT_A_Distillation-Oriented_Trainer_ICCV_2023_paper.pdf 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\":\"megvii-research-mdistiller\",\"task\":\"Install Mdistiller\",\"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 \"Mdistiller\" from https://github.com/megvii-research/mdistiller 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: The official implementation of [CVPR2022] Decoupled Knowledge Distillation https://arxiv.org/abs/2203.08679 and [ICCV2023] DOT: A Distillation-Oriented Trainer https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_DOT_A_Distillation-Oriented_Trainer_ICCV_2023_paper.pdf 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\":\"megvii-research-mdistiller\",\"task\":\"Install Mdistiller\",\"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/megvii-research-mdistiller/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/megvii-research-mdistiller"},"trust":{"score":69,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"901 GitHub stars","repoActivity":"901 stars, 132 forks","lastPushed":"3y since push","license":"Unknown","repository":"https://github.com/megvii-research/mdistiller","install":"npx skills add megvii-research/mdistiller","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","cifar","coco","cvpr2022"],"known_risks":["License is unclear","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y since push","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":62,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Repository appears stale","Repository looks stale","Quality score needs review","Documentation summary is thin","Recent maintenance: 3y 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":51,"label":"Needs review"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","maintenance":"3y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","License is unclear","Repository appears stale","Quality score needs review","Documentation summary is thin"],"agent_contract":{"task_input":"Use Mdistiller in an agent workflow","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 69/100 Manual review","Audit: 62/100 Needs review","Safety: 46/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"megvii-research-mdistiller (Mdistiller)","install_command":"npx skills add megvii-research/mdistiller","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":"megvii-research-mdistiller","task":"Use Mdistiller 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/megvii-research-mdistiller","api":"https://www.openagentskill.com/api/agent/skills/megvii-research-mdistiller","audit":"https://www.openagentskill.com/skills/megvii-research-mdistiller/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=megvii-research-mdistiller&task=Use%20Mdistiller%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Mdistiller%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Mdistiller%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/megvii-research-mdistiller/install","manifest":"https://www.openagentskill.com/api/registry/manifest/megvii-research-mdistiller"}},"platforms":["Python","Computer Vision"],"use_cases":[{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"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"}],"install":"npx skills add megvii-research/mdistiller","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 megvii-research-mdistiller","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 \"Mdistiller\" agent skill from https://github.com/megvii-research/mdistiller. 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: The official implementation of [CVPR2022] Decoupled Knowledge Distillation https://arxiv.org/abs/2203.08679 and [ICCV2023] DOT: A Distillation-Oriented Trainer https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_DOT_A_Distillation-Oriented_Trainer_ICCV_2023_paper.pdf 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\":\"megvii-research-mdistiller\",\"task\":\"Install Mdistiller\",\"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 \"Mdistiller\" as a Claude Code skill from https://github.com/megvii-research/mdistiller. 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: The official implementation of [CVPR2022] Decoupled Knowledge Distillation https://arxiv.org/abs/2203.08679 and [ICCV2023] DOT: A Distillation-Oriented Trainer https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_DOT_A_Distillation-Oriented_Trainer_ICCV_2023_paper.pdf 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\":\"megvii-research-mdistiller\",\"task\":\"Install Mdistiller\",\"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 \"Mdistiller\" from https://github.com/megvii-research/mdistiller 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: The official implementation of [CVPR2022] Decoupled Knowledge Distillation https://arxiv.org/abs/2203.08679 and [ICCV2023] DOT: A Distillation-Oriented Trainer https://openaccess.thecvf.com/content/ICCV2023/papers/Zhao_DOT_A_Distillation-Oriented_Trainer_ICCV_2023_paper.pdf 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\":\"megvii-research-mdistiller\",\"task\":\"Install Mdistiller\",\"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/megvii-research/mdistiller","github_repo":"megvii-research/mdistiller","version":"1.0.0","license":"Unknown","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"megvii-research/mdistiller","recommendation_reasons":["Matches task terms: distillation","Useful GitHub adoption: 901 stars","Install handoff is available","Repository freshness signal is available","Registry match score 8"],"urls":{"web":"https://www.openagentskill.com/skills/megvii-research-mdistiller","api":"https://www.openagentskill.com/api/agent/skills/megvii-research-mdistiller","install_api":"https://www.openagentskill.com/api/skills/megvii-research-mdistiller/install","audit":"https://www.openagentskill.com/skills/megvii-research-mdistiller/audit","repository":"https://github.com/megvii-research/mdistiller"}},{"rank":9,"match_type":"related","match_score":8,"raw_match_score":54.9,"semantic_relevance":30,"slug":"intellindust-ai-lab-edgecrafter","name":"EdgeCrafter","description":"Pytorch implementation of \"EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation\"","tagline":"Pytorch implementation of \"EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation\"","category":"robotics-iot","tags":["computer-vision","automation","robotics-iot","dinov3","distillation","instance-segmentation","lightweight","object-detection","pose-estimation","real-time"],"author":{"name":"Intellindust-AI-Lab","verified":false,"url":"https://github.com/Intellindust-AI-Lab"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"Intellindust-AI-Lab/EdgeCrafter","creatorName":"Intellindust-AI-Lab","creatorUrl":"https://github.com/Intellindust-AI-Lab","sourceUrl":"https://github.com/Intellindust-AI-Lab/EdgeCrafter","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/intellindust-ai-lab-edgecrafter#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":253,"forks":29,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":43.53},"quality":{"score":65,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"253","tone":"neutral"},{"label":"Freshness","value":"4mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":77,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"253 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"253 stars, 29 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"4mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":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 Intellindust-AI-Lab/EdgeCrafter"},{"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/Intellindust-AI-Lab/EdgeCrafter"},{"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":"253 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"253 stars, 29 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"4mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"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 Intellindust-AI-Lab/EdgeCrafter"},{"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/Intellindust-AI-Lab/EdgeCrafter"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 253 stars, 29 forks; issue activity unavailable in current metadata"],"evidence":{"stars":"253 GitHub stars","repoActivity":"253 stars, 29 forks","lastPushed":"4mo since push","license":"Apache-2.0","repository":"https://github.com/Intellindust-AI-Lab/EdgeCrafter","install":"npx skills add Intellindust-AI-Lab/EdgeCrafter","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 Intellindust-AI-Lab/EdgeCrafter","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","4mo since push"]},"agentCompatibility":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 253 stars, 29 forks; issue activity unavailable in current metadata"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["robotics-iot","computer-vision","automation","dinov3","distillation","instance-segmentation"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 253 stars, 29 forks; issue activity unavailable in current metadata"]},"safety":{"score":65,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Documentation summary is thin","65/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Documentation summary is thin","65/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"GitHub automation","description":"I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.","useCases":[{"slug":"workflow-automation","title":"Workflow automation"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"sports-analytics","title":"Sports analytics"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add Intellindust-AI-Lab/EdgeCrafter","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":253,"starsLabel":"253","forks":29,"license":"Apache-2.0","qualityScore":65,"trustScore":77,"auditScore":77},"maintenance":{"status":"active","label":"4mo since push","daysSincePush":105,"lastPushedAt":"2026-05-09T02:03:58+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 253 stars, 29 forks; issue activity unavailable in current metadata","Needs review"]},"coverageTags":["Coding","GitHub automation","robotics-iot","computer-vision","automation","dinov3","distillation","instance-segmentation"]},"audit":{"audit_score":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 253 stars, 29 forks; issue activity unavailable in current metadata"]},"decision":{"readiness_score":64,"readiness_label":"Prototype first","headline":"Fallback candidate for Workflow automation","role":"Fallback candidate","primary_fit":"Workflow automation","best_for":["Workflow 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 Workflow automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"intellindust-ai-lab-edgecrafter","name":"EdgeCrafter","description":"Pytorch implementation of \"EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation\"","category":"robotics-iot","url":"https://www.openagentskill.com/skills/intellindust-ai-lab-edgecrafter","repository":"https://github.com/Intellindust-AI-Lab/EdgeCrafter","github_repo":"Intellindust-AI-Lab/EdgeCrafter"},"suited_tasks":["Workflow automation workflows","general agent builders","builders willing to evaluate younger projects","Move data between tools","Transform files","Trigger repeatable actions","Navigate pages","Click and type safely"],"suited_agents":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add Intellindust-AI-Lab/EdgeCrafter","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 intellindust-ai-lab-edgecrafter"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"EdgeCrafter\" agent skill from https://github.com/Intellindust-AI-Lab/EdgeCrafter. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Pytorch implementation of \"EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation\" 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\":\"intellindust-ai-lab-edgecrafter\",\"task\":\"Install EdgeCrafter\",\"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 \"EdgeCrafter\" as a Claude Code skill from https://github.com/Intellindust-AI-Lab/EdgeCrafter. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Pytorch implementation of \"EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation\" 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\":\"intellindust-ai-lab-edgecrafter\",\"task\":\"Install EdgeCrafter\",\"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 \"EdgeCrafter\" from https://github.com/Intellindust-AI-Lab/EdgeCrafter into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Pytorch implementation of \"EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation\" 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\":\"intellindust-ai-lab-edgecrafter\",\"task\":\"Install EdgeCrafter\",\"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/intellindust-ai-lab-edgecrafter/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/intellindust-ai-lab-edgecrafter"},"trust":{"score":77,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"253 GitHub stars","repoActivity":"253 stars, 29 forks","lastPushed":"4mo since push","license":"Apache-2.0","repository":"https://github.com/Intellindust-AI-Lab/EdgeCrafter","install":"npx skills add Intellindust-AI-Lab/EdgeCrafter","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","dinov3","distillation","instance-segmentation"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 253 stars, 29 forks; issue activity unavailable in current metadata"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 253 stars, 29 forks; issue activity unavailable in current metadata"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":65,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"4mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Quality score needs review","Stars/forks activity: 253 stars, 29 forks; issue activity unavailable in current metadata","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use EdgeCrafter in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 77/100 Strong shortlist","Audit: 77/100 Needs review","Safety: 65/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"intellindust-ai-lab-edgecrafter (EdgeCrafter)","install_command":"npx skills add Intellindust-AI-Lab/EdgeCrafter","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":"intellindust-ai-lab-edgecrafter","task":"Use EdgeCrafter 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/intellindust-ai-lab-edgecrafter","api":"https://www.openagentskill.com/api/agent/skills/intellindust-ai-lab-edgecrafter","audit":"https://www.openagentskill.com/skills/intellindust-ai-lab-edgecrafter/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=intellindust-ai-lab-edgecrafter&task=Use%20EdgeCrafter%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20EdgeCrafter%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20EdgeCrafter%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/intellindust-ai-lab-edgecrafter/install","manifest":"https://www.openagentskill.com/api/registry/manifest/intellindust-ai-lab-edgecrafter"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"intellindust-ai-lab-edgecrafter","name":"EdgeCrafter","description":"Pytorch implementation of \"EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation\"","category":"robotics-iot","url":"https://www.openagentskill.com/skills/intellindust-ai-lab-edgecrafter","repository":"https://github.com/Intellindust-AI-Lab/EdgeCrafter","github_repo":"Intellindust-AI-Lab/EdgeCrafter"},"suited_tasks":["Workflow automation workflows","general agent builders","builders willing to evaluate younger projects","Move data between tools","Transform files","Trigger repeatable actions","Navigate pages","Click and type safely"],"suited_agents":["Python","Computer Vision","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add Intellindust-AI-Lab/EdgeCrafter","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 intellindust-ai-lab-edgecrafter"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"EdgeCrafter\" agent skill from https://github.com/Intellindust-AI-Lab/EdgeCrafter. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Pytorch implementation of \"EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation\" 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\":\"intellindust-ai-lab-edgecrafter\",\"task\":\"Install EdgeCrafter\",\"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 \"EdgeCrafter\" as a Claude Code skill from https://github.com/Intellindust-AI-Lab/EdgeCrafter. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Pytorch implementation of \"EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation\" 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\":\"intellindust-ai-lab-edgecrafter\",\"task\":\"Install EdgeCrafter\",\"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 \"EdgeCrafter\" from https://github.com/Intellindust-AI-Lab/EdgeCrafter into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Pytorch implementation of \"EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation\" 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\":\"intellindust-ai-lab-edgecrafter\",\"task\":\"Install EdgeCrafter\",\"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/intellindust-ai-lab-edgecrafter/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/intellindust-ai-lab-edgecrafter"},"trust":{"score":77,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"253 GitHub stars","repoActivity":"253 stars, 29 forks","lastPushed":"4mo since push","license":"Apache-2.0","repository":"https://github.com/Intellindust-AI-Lab/EdgeCrafter","install":"npx skills add Intellindust-AI-Lab/EdgeCrafter","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","dinov3","distillation","instance-segmentation"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 253 stars, 29 forks; issue activity unavailable in current metadata"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":77,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","Stars/forks activity: 253 stars, 29 forks; issue activity unavailable in current metadata"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":65,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"4mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Quality score needs review","Stars/forks activity: 253 stars, 29 forks; issue activity unavailable in current metadata","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use EdgeCrafter in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 77/100 Strong shortlist","Audit: 77/100 Needs review","Safety: 65/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"intellindust-ai-lab-edgecrafter (EdgeCrafter)","install_command":"npx skills add Intellindust-AI-Lab/EdgeCrafter","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":"intellindust-ai-lab-edgecrafter","task":"Use EdgeCrafter 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/intellindust-ai-lab-edgecrafter","api":"https://www.openagentskill.com/api/agent/skills/intellindust-ai-lab-edgecrafter","audit":"https://www.openagentskill.com/skills/intellindust-ai-lab-edgecrafter/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=intellindust-ai-lab-edgecrafter&task=Use%20EdgeCrafter%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20EdgeCrafter%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20EdgeCrafter%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/intellindust-ai-lab-edgecrafter/install","manifest":"https://www.openagentskill.com/api/registry/manifest/intellindust-ai-lab-edgecrafter"}},"platforms":["Python","Computer Vision"],"use_cases":[{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"sports-analytics","title":"Sports analytics","url":"https://www.openagentskill.com/use-cases/sports-analytics"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"}],"install":"npx skills add Intellindust-AI-Lab/EdgeCrafter","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 intellindust-ai-lab-edgecrafter","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 \"EdgeCrafter\" agent skill from https://github.com/Intellindust-AI-Lab/EdgeCrafter. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: Pytorch implementation of \"EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation\" 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\":\"intellindust-ai-lab-edgecrafter\",\"task\":\"Install EdgeCrafter\",\"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 \"EdgeCrafter\" as a Claude Code skill from https://github.com/Intellindust-AI-Lab/EdgeCrafter. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: Pytorch implementation of \"EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation\" 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\":\"intellindust-ai-lab-edgecrafter\",\"task\":\"Install EdgeCrafter\",\"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 \"EdgeCrafter\" from https://github.com/Intellindust-AI-Lab/EdgeCrafter into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: Pytorch implementation of \"EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation\" 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\":\"intellindust-ai-lab-edgecrafter\",\"task\":\"Install EdgeCrafter\",\"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/Intellindust-AI-Lab/EdgeCrafter","github_repo":"Intellindust-AI-Lab/EdgeCrafter","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"intellindust-ai-lab/edgecrafter","recommendation_reasons":["Matches task terms: distillation","Install handoff is available","Repository freshness signal is available","Registry match score 8"],"urls":{"web":"https://www.openagentskill.com/skills/intellindust-ai-lab-edgecrafter","api":"https://www.openagentskill.com/api/agent/skills/intellindust-ai-lab-edgecrafter","install_api":"https://www.openagentskill.com/api/skills/intellindust-ai-lab-edgecrafter/install","audit":"https://www.openagentskill.com/skills/intellindust-ai-lab-edgecrafter/audit","repository":"https://github.com/Intellindust-AI-Lab/EdgeCrafter"}},{"rank":10,"match_type":"related","match_score":7,"raw_match_score":54.4,"semantic_relevance":30,"slug":"gudaochangsheng-wadi","name":"WaDi","description":"[CVPR 2026] Official PyTorch implementation of WaDi: Weight Direction-aware Distillation for One-step Image Synthesis","tagline":"[CVPR 2026] Official PyTorch implementation of WaDi: Weight Direction-aware Distillation for One-step Image Synthesis","category":"media-automation","tags":["image-generation","creative","media","design","adaptation","controllable-generation","deep-learning","distillation","distillation-model","dmd"],"author":{"name":"gudaochangsheng","verified":false,"url":"https://github.com/gudaochangsheng"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"gudaochangsheng/WaDi","creatorName":"gudaochangsheng","creatorUrl":"https://github.com/gudaochangsheng","sourceUrl":"https://github.com/gudaochangsheng/WaDi","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/gudaochangsheng-wadi#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":153,"forks":23,"verified_installs":0,"install_attempts":0,"successful_runs":0,"total_outcomes":0,"downloads":0,"rating":0,"review_count":0,"quality_score":46.01},"quality":{"score":62,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"153","tone":"neutral"},{"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":75,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"153 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"153 stars, 23 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"3mo since push"},{"id":"license","label":"License clarity","score":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 gudaochangsheng/WaDi"},{"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/gudaochangsheng/WaDi"},{"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":"153 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"153 stars, 23 forks; issue activity unavailable in current metadata"},{"status":"pass","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 gudaochangsheng/WaDi"},{"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/gudaochangsheng/WaDi"},{"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":["License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 153 stars, 23 forks; issue activity unavailable in current metadata","License clarity: Unknown"],"evidence":{"stars":"153 GitHub stars","repoActivity":"153 stars, 23 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/gudaochangsheng/WaDi","install":"npx skills add gudaochangsheng/WaDi","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 gudaochangsheng/WaDi","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":["Python","Image Generation","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","Stars/forks activity: 153 stars, 23 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["media-automation","image-generation","creative","media","design","adaptation"],"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","Stars/forks activity: 153 stars, 23 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"safety":{"score":64,"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","64/100 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","64/100 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":"Design and creative","description":"I need my agent to produce design assets, UI directions, presentations, or creative media workflows.","useCases":[{"slug":"design-creative","title":"Design and creative"},{"slug":"multimodal-media","title":"Multimodal media"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add gudaochangsheng/WaDi","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":153,"starsLabel":"153","forks":23,"license":"Unknown","qualityScore":62,"trustScore":75,"auditScore":76},"maintenance":{"status":"active","label":"3mo since push","daysSincePush":88,"lastPushedAt":"2026-05-26T02:30:57+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["License is unclear","Documentation summary is thin","Quality score needs review","Stars/forks activity: 153 stars, 23 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"coverageTags":["Design","Design and creative","media-automation","image-generation","creative","media","adaptation","controllable-generation"]},"audit":{"audit_score":76,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","Quality score needs review","Stars/forks activity: 153 stars, 23 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"decision":{"readiness_score":61,"readiness_label":"Prototype first","headline":"Fallback candidate for Design and creative","role":"Fallback candidate","primary_fit":"Design and creative","best_for":["Design and creative 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 Design and creative 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":"gudaochangsheng-wadi","name":"WaDi","description":"[CVPR 2026] Official PyTorch implementation of WaDi: Weight Direction-aware Distillation for One-step Image Synthesis","category":"media-automation","url":"https://www.openagentskill.com/skills/gudaochangsheng-wadi","repository":"https://github.com/gudaochangsheng/WaDi","github_repo":"gudaochangsheng/WaDi"},"suited_tasks":["Design and creative workflows","general agent builders","builders willing to evaluate younger projects","Inspect visual requirements","Generate reusable assets","Package output for review","Read media metadata","Convert formats"],"suited_agents":["Python","Image Generation","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add gudaochangsheng/WaDi","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 gudaochangsheng-wadi"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"WaDi\" agent skill from https://github.com/gudaochangsheng/WaDi. 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 2026] Official PyTorch implementation of WaDi: Weight Direction-aware Distillation for One-step Image Synthesis 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\":\"gudaochangsheng-wadi\",\"task\":\"Install WaDi\",\"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 \"WaDi\" as a Claude Code skill from https://github.com/gudaochangsheng/WaDi. 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 2026] Official PyTorch implementation of WaDi: Weight Direction-aware Distillation for One-step Image Synthesis 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\":\"gudaochangsheng-wadi\",\"task\":\"Install WaDi\",\"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 \"WaDi\" from https://github.com/gudaochangsheng/WaDi 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 2026] Official PyTorch implementation of WaDi: Weight Direction-aware Distillation for One-step Image Synthesis 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\":\"gudaochangsheng-wadi\",\"task\":\"Install WaDi\",\"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/gudaochangsheng-wadi/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/gudaochangsheng-wadi"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"153 GitHub stars","repoActivity":"153 stars, 23 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/gudaochangsheng/WaDi","install":"npx skills add gudaochangsheng/WaDi","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":["media-automation","image-generation","creative","media","design","adaptation"],"known_risks":["License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 153 stars, 23 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":76,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","Quality score needs review","Stars/forks activity: 153 stars, 23 forks; issue activity unavailable in current metadata","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":62,"label":"Promising"},"supply":{"track":"Design and creative production","scenario":"Design and creative","maintenance":"3mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","Quality score needs review","Stars/forks activity: 153 stars, 23 forks; issue activity unavailable in current metadata","License clarity: Unknown"],"agent_contract":{"task_input":"Use WaDi in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 76/100 Needs review","Safety: 64/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"gudaochangsheng-wadi (WaDi)","install_command":"npx skills add gudaochangsheng/WaDi","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":"gudaochangsheng-wadi","task":"Use WaDi 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/gudaochangsheng-wadi","api":"https://www.openagentskill.com/api/agent/skills/gudaochangsheng-wadi","audit":"https://www.openagentskill.com/skills/gudaochangsheng-wadi/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=gudaochangsheng-wadi&task=Use%20WaDi%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20WaDi%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20WaDi%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/gudaochangsheng-wadi/install","manifest":"https://www.openagentskill.com/api/registry/manifest/gudaochangsheng-wadi"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"gudaochangsheng-wadi","name":"WaDi","description":"[CVPR 2026] Official PyTorch implementation of WaDi: Weight Direction-aware Distillation for One-step Image Synthesis","category":"media-automation","url":"https://www.openagentskill.com/skills/gudaochangsheng-wadi","repository":"https://github.com/gudaochangsheng/WaDi","github_repo":"gudaochangsheng/WaDi"},"suited_tasks":["Design and creative workflows","general agent builders","builders willing to evaluate younger projects","Inspect visual requirements","Generate reusable assets","Package output for review","Read media metadata","Convert formats"],"suited_agents":["Python","Image Generation","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add gudaochangsheng/WaDi","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 gudaochangsheng-wadi"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"WaDi\" agent skill from https://github.com/gudaochangsheng/WaDi. 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 2026] Official PyTorch implementation of WaDi: Weight Direction-aware Distillation for One-step Image Synthesis 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\":\"gudaochangsheng-wadi\",\"task\":\"Install WaDi\",\"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 \"WaDi\" as a Claude Code skill from https://github.com/gudaochangsheng/WaDi. 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 2026] Official PyTorch implementation of WaDi: Weight Direction-aware Distillation for One-step Image Synthesis 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\":\"gudaochangsheng-wadi\",\"task\":\"Install WaDi\",\"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 \"WaDi\" from https://github.com/gudaochangsheng/WaDi 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 2026] Official PyTorch implementation of WaDi: Weight Direction-aware Distillation for One-step Image Synthesis 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\":\"gudaochangsheng-wadi\",\"task\":\"Install WaDi\",\"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/gudaochangsheng-wadi/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/gudaochangsheng-wadi"},"trust":{"score":75,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"153 GitHub stars","repoActivity":"153 stars, 23 forks","lastPushed":"3mo since push","license":"Unknown","repository":"https://github.com/gudaochangsheng/WaDi","install":"npx skills add gudaochangsheng/WaDi","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":["media-automation","image-generation","creative","media","design","adaptation"],"known_risks":["License is unclear","Quality score needs review","Documentation summary is thin","Stars/forks activity: 153 stars, 23 forks; issue activity unavailable in current metadata","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":76,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","Quality score needs review","Stars/forks activity: 153 stars, 23 forks; issue activity unavailable in current metadata","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":62,"label":"Promising"},"supply":{"track":"Design and creative production","scenario":"Design and creative","maintenance":"3mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","Quality score needs review","Stars/forks activity: 153 stars, 23 forks; issue activity unavailable in current metadata","License clarity: Unknown"],"agent_contract":{"task_input":"Use WaDi in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 75/100 Strong shortlist","Audit: 76/100 Needs review","Safety: 64/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"gudaochangsheng-wadi (WaDi)","install_command":"npx skills add gudaochangsheng/WaDi","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":"gudaochangsheng-wadi","task":"Use WaDi 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/gudaochangsheng-wadi","api":"https://www.openagentskill.com/api/agent/skills/gudaochangsheng-wadi","audit":"https://www.openagentskill.com/skills/gudaochangsheng-wadi/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=gudaochangsheng-wadi&task=Use%20WaDi%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20WaDi%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20WaDi%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/gudaochangsheng-wadi/install","manifest":"https://www.openagentskill.com/api/registry/manifest/gudaochangsheng-wadi"}},"platforms":["Python","Image Generation"],"use_cases":[{"slug":"design-creative","title":"Design and creative","url":"https://www.openagentskill.com/use-cases/design-creative"},{"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"}],"install":"npx skills add gudaochangsheng/WaDi","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 gudaochangsheng-wadi","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 \"WaDi\" agent skill from https://github.com/gudaochangsheng/WaDi. 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 2026] Official PyTorch implementation of WaDi: Weight Direction-aware Distillation for One-step Image Synthesis 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\":\"gudaochangsheng-wadi\",\"task\":\"Install WaDi\",\"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 \"WaDi\" as a Claude Code skill from https://github.com/gudaochangsheng/WaDi. 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 2026] Official PyTorch implementation of WaDi: Weight Direction-aware Distillation for One-step Image Synthesis 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\":\"gudaochangsheng-wadi\",\"task\":\"Install WaDi\",\"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 \"WaDi\" from https://github.com/gudaochangsheng/WaDi 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 2026] Official PyTorch implementation of WaDi: Weight Direction-aware Distillation for One-step Image Synthesis 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\":\"gudaochangsheng-wadi\",\"task\":\"Install WaDi\",\"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/gudaochangsheng/WaDi","github_repo":"gudaochangsheng/WaDi","version":"1.0.0","license":"Unknown","updated_at":"2026-08-18T17:22:21.819119+00:00","canonical_key":"gudaochangsheng/wadi","recommendation_reasons":["Matches task terms: distillation","Install handoff is available","Repository freshness signal is available","Registry match score 7"],"urls":{"web":"https://www.openagentskill.com/skills/gudaochangsheng-wadi","api":"https://www.openagentskill.com/api/agent/skills/gudaochangsheng-wadi","install_api":"https://www.openagentskill.com/api/skills/gudaochangsheng-wadi/install","audit":"https://www.openagentskill.com/skills/gudaochangsheng-wadi/audit","repository":"https://github.com/gudaochangsheng/WaDi"}}],"meta":{"endpoint":"/api/skills/search","canonical_agent_endpoint":"/api/agent/resolve","lookup_intent":false,"exact_match_found":false,"match_counts":{"exact":0,"near":0,"related":10},"no_match_message":null,"safety_policy":"Blocked candidates are excluded by default. Pass include_blocked=true only for manual audit workflows.","agent_friendly":true,"api_version":"1.0","generated_at":"2026-08-22T21:03:29.148Z"}}