{"task":"Use karpathy","agent":"codex","constraints":{"max_risk":"medium","needs_install_command":true,"min_stars":0},"feedback":{"event_id":"resolve_013e884c-6dad-4779-beeb-bf280901a319","outcome_api":"https://www.openagentskill.com/api/agent/outcome","method":"POST","selected_skill_slug":"multica-ai-andrej-karpathy-skills","selected_skill_name":"Andrej Karpathy Skills","alternative_skill_slugs":["astro-han-karpathy-llm-wiki","kbwen-karpathy-principles","gaasher-karpathy","k-dense-ai-andrej-karpathy"],"expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"report_after":["After trying the selected skill, report whether it solved the task.","Mark blocked_by_risk when audit, license, credentials, shell, or network risk prevents safe use.","Mark setup_required when the skill looks relevant but needs missing keys, data, or manual configuration.","Mark not_relevant when the selected skill does not match the task after inspection.","Include output_quality, error_type, workspace, human_review_required, evidence_url, and time_to_useful_ms when available."],"json_example":{"event_id":"resolve_013e884c-6dad-4779-beeb-bf280901a319","skill_slug":"multica-ai-andrej-karpathy-skills","task":"Use karpathy","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":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_013e884c-6dad-4779-beeb-bf280901a319\" --skill \"multica-ai-andrej-karpathy-skills\" --task \"Use karpathy\" --agent \"codex\" --outcome success"},"agent_feedback_loop":{"version":"openagentskill-agent-feedback-loop-v3","status":"active","purpose":"Report the result of one resolved skill run so Trust Score v5 and future Resolve rankings learn from real use.","event_id":"resolve_013e884c-6dad-4779-beeb-bf280901a319","selected_skill_slug":"multica-ai-andrej-karpathy-skills","selected_skill_name":"Andrej Karpathy Skills","endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","idempotency":"Retrying the same event_id updates the previous outcome.","dry_run":{"supported":true,"instruction":"Set dry_run=true to validate a payload before wiring a new agent integration."},"expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"error_types":["install_failed","runtime_error","not_relevant","permission_blocked","risk_blocked","setup_required","low_quality_output","missing_dependency","timeout","other"],"workspaces":["sandbox","local","ci","production","unknown"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url"],"payload_template":{"event_id":"resolve_013e884c-6dad-4779-beeb-bf280901a319","skill_slug":"multica-ai-andrej-karpathy-skills","task":"Use karpathy","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":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_013e884c-6dad-4779-beeb-bf280901a319\" --skill \"multica-ai-andrej-karpathy-skills\" --task \"Use karpathy\" --agent \"codex\" --outcome success","ranking_inputs_updated":["Trust Score v5 outcome confidence","Resolve ranking outcome evidence","Skill detail outcome signal block","Outcome leaderboard"]},"install_receipt":{"version":"openagentskill-install-receipt-v2","receipt_id":"receipt_013e884c-6dad-4779-beeb-bf280901a319","resolve_event_id":"resolve_013e884c-6dad-4779-beeb-bf280901a319","generated_at":"2026-09-08T13:11:02.632Z","task":"Use karpathy","agent":"codex","constraints":{"max_risk":"medium","needs_install_command":true,"min_stars":0},"urls":{"web":"https://www.openagentskill.com/resolve?task=Use+karpathy&agent=codex&max_risk=medium","json":"https://www.openagentskill.com/api/agent/receipt?task=Use+karpathy&agent=codex&max_risk=medium","text":"https://www.openagentskill.com/api/agent/receipt?task=Use+karpathy&agent=codex&max_risk=medium&format=text","resolve_json":"https://www.openagentskill.com/api/agent/resolve?task=Use+karpathy&agent=codex&max_risk=medium","resolve_text":"https://www.openagentskill.com/api/agent/resolve?task=Use+karpathy&agent=codex&max_risk=medium&format=text"},"selected_skill":{"slug":"multica-ai-andrej-karpathy-skills","name":"Andrej Karpathy Skills","description":"A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.","category":"development","url":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills","api_url":"https://www.openagentskill.com/api/agent/skills/multica-ai-andrej-karpathy-skills","audit_url":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=multica-ai-andrej-karpathy-skills&task=Use%20karpathy&max_risk=medium","install_api_url":"https://www.openagentskill.com/api/skills/multica-ai-andrej-karpathy-skills/install","repository":"https://github.com/multica-ai/andrej-karpathy-skills","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"install":{"command":"npx skills add multica-ai/andrej-karpathy-skills","target":"codex","label":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Andrej Karpathy Skills\" agent skill from https://github.com/multica-ai/andrej-karpathy-skills. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"multica-ai-andrej-karpathy-skills\",\"task\":\"Install Andrej Karpathy Skills\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","ready":true,"policy":"review","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"blocked":false},"decision":{"recommendation":"Review the audit page, then allow agent install in a sandboxed workflow.","why_selected":["Matches task terms: karpathy","Strong GitHub adoption: 175,191 stars","Quality score 83/100","Install handoff is available","Repository freshness signal is available","Primary pick for Coding agents","75/100 Trust Score","63/100 Agent Proven Score"],"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":["Claude Code","Codex","Cursor","OpenAgentSkill CLI","CLI"]},"trust":{"score":75,"label":"Sandbox only","version":"trust-score-v5","base_score":88,"outcome_confidence":0.65,"outcome_signal":"Early agent signal: 100% success from 5 agent outcomes","outcome_total":5,"outcome_success_rate":100,"decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["75/100 Trust Score v5","88/100 Trust Score v4 baseline","Early agent signal: 100% success from 5 agent outcomes; outcome confidence 65%","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]}},"agent_proven":{"score":63,"label":"Early agent signal","summary":"Early agent signal: 5 outcomes, 100% success, Agent Proven Score 63/100.","metrics":{"totalOutcomes":5,"successRate":100,"recentSuccessRate":100,"recentFailureRate":0,"installAttempts":5,"installSuccessRate":100,"riskBlocked":0,"setupRequired":0,"avgOutputQuality":null,"productionOutcomes":0}},"risk":{"level":"Safe to try","safety_tier":"Reviewed","safety_score":71,"audit_score":87,"notes":["License is unclear","Documentation summary is thin","License clarity: Unknown","Safe-to-try audit","71/100 agent safety score"],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"minimum_review_before_use":["Trust: 88/100 Production candidate","Audit: 87/100 Safe to try","Safety: 71/100 Review before install","Review repository, license, install command, and permission surface before production use."]},"alternatives":[{"slug":"astro-han-karpathy-llm-wiki","name":"Karpathy Llm Wiki","url":"https://www.openagentskill.com/skills/astro-han-karpathy-llm-wiki","audit_url":"https://www.openagentskill.com/skills/astro-han-karpathy-llm-wiki/audit","install_command":"npx skills add Astro-Han/karpathy-llm-wiki","trust_score":88,"audit_score":90,"safety_score":78,"reason":"Matches task terms: karpathy","policy":"review"},{"slug":"kbwen-karpathy-principles","name":"karpathy-principles","url":"https://www.openagentskill.com/skills/kbwen-karpathy-principles","audit_url":"https://www.openagentskill.com/skills/kbwen-karpathy-principles/audit","install_command":"npx skills add KbWen/agentic-os --skill karpathy-principles","trust_score":78,"audit_score":80,"safety_score":68,"reason":"Matches task terms: karpathy","policy":"review"},{"slug":"gaasher-karpathy","name":"karpathy","url":"https://www.openagentskill.com/skills/gaasher-karpathy","audit_url":"https://www.openagentskill.com/skills/gaasher-karpathy/audit","install_command":"npx skills add gaasher/Agent-Loop-Skills --skill karpathy","trust_score":73,"audit_score":76,"safety_score":52,"reason":"Matches task terms: karpathy","policy":"review"},{"slug":"k-dense-ai-andrej-karpathy","name":"andrej-karpathy","url":"https://www.openagentskill.com/skills/k-dense-ai-andrej-karpathy","audit_url":"https://www.openagentskill.com/skills/k-dense-ai-andrej-karpathy/audit","install_command":"npx skills add K-Dense-AI/mimeographs --skill andrej-karpathy","trust_score":69,"audit_score":78,"safety_score":66,"reason":"Matches task terms: karpathy","policy":"review"}],"outcome_feedback":{"event_id":"resolve_013e884c-6dad-4779-beeb-bf280901a319","endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"resolve_013e884c-6dad-4779-beeb-bf280901a319","skill_slug":"multica-ai-andrej-karpathy-skills","task":"Use karpathy","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":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"dry_run_payload":{"event_id":"resolve_013e884c-6dad-4779-beeb-bf280901a319","skill_slug":"multica-ai-andrej-karpathy-skills","task":"Use karpathy","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":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"},"dry_run":true},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_013e884c-6dad-4779-beeb-bf280901a319\" --skill \"multica-ai-andrej-karpathy-skills\" --task \"Use karpathy\" --agent \"codex\" --outcome success","instruction":"After one narrow sandbox run, report success, failed, not_relevant, blocked_by_risk, or setup_required so Trust Score v5 and future agent rankings learn from real usage."},"next_steps":["Read the audit page: https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills/audit","Fetch the pre-install eval: https://www.openagentskill.com/api/agent/evals?slug=multica-ai-andrej-karpathy-skills&task=Use%20karpathy&max_risk=medium","Do not auto-install yet. Ask for human review before running: npx skills add multica-ai/andrej-karpathy-skills","Run one narrow task with no production secrets or irreversible side effects.","Report the result to https://www.openagentskill.com/api/agent/outcome using event_id resolve_013e884c-6dad-4779-beeb-bf280901a319."],"stable_fields":["receipt_id","selected_skill","install","trust","risk","alternatives","outcome_feedback","next_steps"],"freshness_policy":"Re-resolve before production use or after 24 hours to refresh trust, audit, and outcome signals."},"recommendation":{"task":"Use karpathy","agent":"codex","best_skill":{"slug":"multica-ai-andrej-karpathy-skills","name":"Andrej Karpathy Skills","description":"A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.","category":"development","url":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills","api_url":"https://www.openagentskill.com/api/agent/skills/multica-ai-andrej-karpathy-skills","audit_url":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=multica-ai-andrej-karpathy-skills&task=Use%20karpathy&max_risk=medium","repository":"https://github.com/multica-ai/andrej-karpathy-skills","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"install":{"command":"npx skills add multica-ai/andrej-karpathy-skills","target":"codex","label":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Andrej Karpathy Skills\" agent skill from https://github.com/multica-ai/andrej-karpathy-skills. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"multica-ai-andrej-karpathy-skills\",\"task\":\"Install Andrej Karpathy Skills\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","install_api":"https://www.openagentskill.com/api/skills/multica-ai-andrej-karpathy-skills/install","ready":true,"review_required":true,"auto_install_allowed":false,"policy":"review"},"why_recommended":["Matches task terms: karpathy","Strong GitHub adoption: 175,191 stars","Quality score 83/100","Install handoff is available","Repository freshness signal is available","Primary pick for Coding agents","75/100 OpenAgentSkill Trust Score v5","87/100 audit score"],"trust_score_v5":{"score":75,"base_score":88,"outcome_confidence":0.65,"tier":"review","label":"Sandbox only","version":"trust-score-v5","install_policy":"human_review_before_install","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["75/100 Trust Score v5","88/100 Trust Score v4 baseline","Early agent signal: 100% success from 5 agent outcomes; outcome confidence 65%","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"evidence":{"stars":"175K GitHub stars","repoActivity":"175K stars, 18K forks","lastPushed":"5mo since push","license":"Unknown","repository":"https://github.com/multica-ai/andrej-karpathy-skills","install":"npx skills add multica-ai/andrej-karpathy-skills","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"Early agent signal: 100% success from 5 agent outcomes","agentProvenScore":63,"outcomeConfidence":"65%","installPolicy":"human_review_before_install"},"agent_compatibility":["Claude Code","Codex","Cursor","OpenAgentSkill CLI"],"risk":{"level":"medium","label":"Review before production","notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"outcomes":{"total":5,"successes":5,"failures":0,"notRelevant":0,"successRate":100,"installAttempts":5,"riskBlocked":0,"setupRequired":0,"installSuccessRate":100,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":100,"recentFailureRate":0,"uniqueAgents":1,"agentProvenScore":63,"agentProvenLabel":"Early agent signal","lastOutcomeAt":"2026-09-07T11:19:38.644233+00:00","label":"Early agent signal: 100% success from 5 agent outcomes"},"auto_install":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["development","claude-code","agent-skills","developer-tools","github","Claude Code"],"suited_agents":["Claude Code","Codex","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add multica-ai/andrej-karpathy-skills","trust_score":75,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["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"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"best_for":["development","claude-code","agent-skills","developer-tools","github","Claude Code"],"do_not_use_for":["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"],"known_risks":["License is unclear","Documentation summary is thin","License clarity: Unknown"],"backward_compatible":{"trust_score_v4":{"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."}}},"trust_score_v4":{"score":88,"tier":"production","label":"Production candidate","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"175K GitHub stars","repoActivity":"175K stars, 18K forks","lastPushed":"5mo since push","license":"Unknown","repository":"https://github.com/multica-ai/andrej-karpathy-skills","install":"npx skills add multica-ai/andrej-karpathy-skills","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"Early agent signal: 100% success from 5 agent outcomes"},"agent_compatibility":["Claude Code","Codex","Cursor","OpenAgentSkill CLI"],"risk":{"level":"medium","label":"Review before production","notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"outcomes":{"total":5,"successes":5,"failures":0,"notRelevant":0,"successRate":100,"installAttempts":5,"riskBlocked":0,"setupRequired":0,"installSuccessRate":100,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":100,"recentFailureRate":0,"uniqueAgents":1,"agentProvenScore":63,"agentProvenLabel":"Early agent signal","lastOutcomeAt":"2026-09-07T11:19:38.644233+00:00","label":"Early agent signal: 100% success from 5 agent outcomes"},"auto_install":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["development","claude-code","agent-skills","developer-tools","github","Claude Code"],"do_not_use_for":["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"],"known_risks":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"trust_score_v3":{"score":88,"tier":"production","label":"Production candidate","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"175K GitHub stars","repoActivity":"175K stars, 18K forks","lastPushed":"5mo since push","license":"Unknown","repository":"https://github.com/multica-ai/andrej-karpathy-skills","install":"npx skills add multica-ai/andrej-karpathy-skills","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"Early agent signal: 100% success from 5 agent outcomes"},"agent_compatibility":["Claude Code","Codex","Cursor","OpenAgentSkill CLI"],"risk":{"level":"medium","label":"Review before production","notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"]}},"trust_score_v2":{"score":88,"tier":"production","label":"Production candidate","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"175K GitHub stars","repoActivity":"175K stars, 18K forks","lastPushed":"5mo since push","license":"Unknown","repository":"https://github.com/multica-ai/andrej-karpathy-skills","install":"npx skills add multica-ai/andrej-karpathy-skills","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"Early agent signal: 100% success from 5 agent outcomes"},"agent_compatibility":["Claude Code","Codex","Cursor","OpenAgentSkill CLI"],"risk":{"level":"medium","label":"Review before production","notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"]}},"risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"71/100 Review before install","trust":"88/100 Production candidate","notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","71/100 agent safety score"]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"multica-ai-andrej-karpathy-skills","name":"Andrej Karpathy Skills","description":"A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.","category":"development","url":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills","repository":"https://github.com/multica-ai/andrej-karpathy-skills","github_repo":"multica-ai/andrej-karpathy-skills"},"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":["Claude Code","Codex","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add multica-ai/andrej-karpathy-skills","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add multica-ai-andrej-karpathy-skills"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Andrej Karpathy Skills\" agent skill from https://github.com/multica-ai/andrej-karpathy-skills. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"multica-ai-andrej-karpathy-skills\",\"task\":\"Install Andrej Karpathy Skills\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Andrej Karpathy Skills\" as a Claude Code skill from https://github.com/multica-ai/andrej-karpathy-skills. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"multica-ai-andrej-karpathy-skills\",\"task\":\"Install Andrej Karpathy Skills\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Andrej Karpathy Skills\" from https://github.com/multica-ai/andrej-karpathy-skills into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"multica-ai-andrej-karpathy-skills\",\"task\":\"Install Andrej Karpathy Skills\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/multica-ai-andrej-karpathy-skills/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/multica-ai-andrej-karpathy-skills"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"175K GitHub stars","repoActivity":"175K stars, 18K forks","lastPushed":"5mo since push","license":"Unknown","repository":"https://github.com/multica-ai/andrej-karpathy-skills","install":"npx skills add multica-ai/andrej-karpathy-skills","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"Early agent signal: 100% success from 5 agent outcomes"},"outcome_evidence":{"total":5,"successes":5,"failures":0,"not_relevant":0,"success_rate":100,"recent_success_rate":100,"recent_failure_rate":0,"install_attempts":5,"install_success_rate":100,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":"2026-09-07T11:19:38.644233+00:00","label":"Early agent signal: 100% success from 5 agent outcomes"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["development","claude-code","agent-skills","developer-tools","github","Claude Code"],"known_risks":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":63,"tier":"early","label":"Early agent signal","summary":"Early agent signal: 5 outcomes, 100% success, Agent Proven Score 63/100.","metrics":{"totalOutcomes":5,"successfulOutcomes":5,"failedOutcomes":0,"installAttempts":5,"installSuccessRate":100,"successRate":100,"recentSuccessRate":100,"recentFailureRate":0,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":1,"lastOutcomeAt":"2026-09-07T11:19:38.644233+00:00"},"signals":["100% all-time success","100% recent success","5 install attempts","1 agent surface"],"penalties":[]},"audit":{"score":87,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"5mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use karpathy","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: 87/100 Safe to try","Safety: 71/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"multica-ai-andrej-karpathy-skills (Andrej Karpathy Skills)","install_command":"npx skills add multica-ai/andrej-karpathy-skills","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":"multica-ai-andrej-karpathy-skills","task":"Use karpathy","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/multica-ai-andrej-karpathy-skills","api":"https://www.openagentskill.com/api/agent/skills/multica-ai-andrej-karpathy-skills","audit":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=multica-ai-andrej-karpathy-skills&task=Use%20karpathy&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20karpathy&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20karpathy&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/multica-ai-andrej-karpathy-skills/install","manifest":"https://www.openagentskill.com/api/registry/manifest/multica-ai-andrej-karpathy-skills"}},"agent_contract":{"version":"openagentskill-resolve-contract-v2","input_task":"Use karpathy","recommended_skill_slug":"multica-ai-andrej-karpathy-skills","recommended_skill_name":"Andrej Karpathy Skills","install_command":"npx skills add multica-ai/andrej-karpathy-skills","install_policy":"review","auto_install_allowed":false,"human_review_required":true,"audit_url":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=multica-ai-andrej-karpathy-skills&task=Use%20karpathy&max_risk=medium","skill_api_url":"https://www.openagentskill.com/api/agent/skills/multica-ai-andrej-karpathy-skills","do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"minimum_review_before_use":["Trust: 88/100 Production candidate","Audit: 87/100 Safe to try","Safety: 71/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"multica-ai-andrej-karpathy-skills (Andrej Karpathy Skills)","install_command":"npx skills add multica-ai/andrej-karpathy-skills","risk_summary":"Safe to try; Reviewed; Review before production","verification_result":"Report the smallest successful task, files touched, warnings, and any missing setup."}},"supply_asset":{"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":"workflow-automation","title":"Workflow automation"}]},"maintenance":{"status":"active","label":"5mo since push","daysSincePush":141,"lastPushedAt":"2026-04-20T10:05:04+00:00"},"github_quality":{"stars":175191,"starsLabel":"175K","forks":17868,"license":"Unknown","qualityScore":100,"trustScore":85,"auditScore":87},"coverage_tags":["Coding","Coding agents","development","claude-code","agent-skills","developer-tools","github","Claude Code"]},"alternatives":[{"slug":"astro-han-karpathy-llm-wiki","name":"Karpathy Llm Wiki","url":"https://www.openagentskill.com/skills/astro-han-karpathy-llm-wiki","install_command":"npx skills add Astro-Han/karpathy-llm-wiki","trust_score":88,"audit_score":90,"safety_score":78,"why_consider":"Matches task terms: karpathy","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"78/100 Review before install","trust":"88/100 Production candidate","notes":["Documentation summary is thin"]}},{"slug":"kbwen-karpathy-principles","name":"karpathy-principles","url":"https://www.openagentskill.com/skills/kbwen-karpathy-principles","install_command":"npx skills add KbWen/agentic-os --skill karpathy-principles","trust_score":78,"audit_score":80,"safety_score":68,"why_consider":"Matches task terms: karpathy","risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"68/100 Review before install","trust":"78/100 Strong shortlist","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 155 stars, 35 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},{"slug":"gaasher-karpathy","name":"karpathy","url":"https://www.openagentskill.com/skills/gaasher-karpathy","install_command":"npx skills add gaasher/Agent-Loop-Skills --skill karpathy","trust_score":73,"audit_score":76,"safety_score":52,"why_consider":"Matches task terms: karpathy","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"52/100 Avoid automatic install","trust":"73/100 Strong shortlist","notes":["High-risk permission hints: Secrets or environment access","Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},{"slug":"k-dense-ai-andrej-karpathy","name":"andrej-karpathy","url":"https://www.openagentskill.com/skills/k-dense-ai-andrej-karpathy","install_command":"npx skills add K-Dense-AI/mimeographs --skill andrej-karpathy","trust_score":69,"audit_score":78,"safety_score":66,"why_consider":"Matches task terms: karpathy","risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"66/100 Review before install","trust":"69/100 Manual review","notes":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","The skill does not document explicit limitations or safe operating boundaries, though it is a mental-model/persona skill rather than a tool-executing workflow.","The submission includes internal `_workspace` artifacts (critique files, generated JSON) that are not part of the skill itself and add clutter.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata"]}}],"decision_packet":{"version":"openagentskill-agent-decision-packet-v1","task":"Use karpathy","agent":"codex","selected_skill":{"slug":"multica-ai-andrej-karpathy-skills","name":"Andrej Karpathy Skills","url":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills","api_url":"https://www.openagentskill.com/api/agent/skills/multica-ai-andrej-karpathy-skills","audit_url":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills/audit","repository":"https://github.com/multica-ai/andrej-karpathy-skills","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"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":["Claude Code","Codex","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add multica-ai/andrej-karpathy-skills","target":"codex","label":"Codex install prompt","policy":"review","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true},"trust":{"score":75,"label":"Sandbox only","version":"trust-score-v5","base_score":88,"outcome_confidence":0.65,"decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["75/100 Trust Score v5","88/100 Trust Score v4 baseline","Early agent signal: 100% success from 5 agent outcomes; outcome confidence 65%","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"status":"pass","detail":"175K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"status":"pass","detail":"175K stars, 18K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"status":"info","detail":"5mo since push"},{"id":"license","label":"License clarity","score":42,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"status":"pass","detail":"npx skills add multica-ai/andrej-karpathy-skills"},{"id":"install_safety","label":"Install command safety","score":92,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"status":"pass","detail":"https://github.com/multica-ai/andrej-karpathy-skills"},{"id":"review_status","label":"Review status","score":88,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":63,"status":"info","detail":"Early agent signal: 100% success from 5 agent outcomes"}]},"risk":{"level":"Safe to try","audit_label":"Safe to try","safety":"71/100 Review before install","trust":"88/100 Production candidate","safety_tier":"Reviewed","notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"minimum_review_before_use":["Trust: 88/100 Production candidate","Audit: 87/100 Safe to try","Safety: 71/100 Review before install","Review repository, license, install command, and permission surface before production use."]},"alternatives":[{"slug":"astro-han-karpathy-llm-wiki","name":"Karpathy Llm Wiki","url":"https://www.openagentskill.com/skills/astro-han-karpathy-llm-wiki","install_command":"npx skills add Astro-Han/karpathy-llm-wiki","trust_score":88,"audit_score":90,"safety_score":78,"why_consider":"Matches task terms: karpathy","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"78/100 Review before install","trust":"88/100 Production candidate","notes":["Documentation summary is thin"]}},{"slug":"kbwen-karpathy-principles","name":"karpathy-principles","url":"https://www.openagentskill.com/skills/kbwen-karpathy-principles","install_command":"npx skills add KbWen/agentic-os --skill karpathy-principles","trust_score":78,"audit_score":80,"safety_score":68,"why_consider":"Matches task terms: karpathy","risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"68/100 Review before install","trust":"78/100 Strong shortlist","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 155 stars, 35 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},{"slug":"gaasher-karpathy","name":"karpathy","url":"https://www.openagentskill.com/skills/gaasher-karpathy","install_command":"npx skills add gaasher/Agent-Loop-Skills --skill karpathy","trust_score":73,"audit_score":76,"safety_score":52,"why_consider":"Matches task terms: karpathy","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"52/100 Avoid automatic install","trust":"73/100 Strong shortlist","notes":["High-risk permission hints: Secrets or environment access","Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},{"slug":"k-dense-ai-andrej-karpathy","name":"andrej-karpathy","url":"https://www.openagentskill.com/skills/k-dense-ai-andrej-karpathy","install_command":"npx skills add K-Dense-AI/mimeographs --skill andrej-karpathy","trust_score":69,"audit_score":78,"safety_score":66,"why_consider":"Matches task terms: karpathy","risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"66/100 Review before install","trust":"69/100 Manual review","notes":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","The skill does not document explicit limitations or safe operating boundaries, though it is a mental-model/persona skill rather than a tool-executing workflow.","The submission includes internal `_workspace` artifacts (critique files, generated JSON) that are not part of the skill itself and add clutter.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata"]}}],"outcome_feedback":{"event_id":"resolve_013e884c-6dad-4779-beeb-bf280901a319","endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"resolve_013e884c-6dad-4779-beeb-bf280901a319","skill_slug":"multica-ai-andrej-karpathy-skills","task":"Use karpathy","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":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_013e884c-6dad-4779-beeb-bf280901a319\" --skill \"multica-ai-andrej-karpathy-skills\" --task \"Use karpathy\" --agent \"codex\" --outcome success"},"next_agent_action":"Ask for human approval or choose a safer alternative before installing.","stable_fields":["decision_packet.selected_skill","decision_packet.install","decision_packet.risk.do_not_use_when","decision_packet.alternatives","decision_packet.outcome_feedback","decision_packet.trust.decision"]},"agent_instruction":"Use Andrej Karpathy Skills for: Use karpathy\nReview audit: https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills/audit\nAsk for human approval before installing: npx skills add multica-ai/andrej-karpathy-skills\nIf the audit or policy warnings are unacceptable, choose one of the alternatives."},"recommendation_lanes":{"best_match":{"rank":1,"match_score":30,"raw_match_score":128,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"multica-ai-andrej-karpathy-skills","name":"Andrej Karpathy Skills","description":"A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.","category":"development","github_stars":175191,"created_at":"2026-06-14T16:01:34.129875+00:00","updated_at":"2026-04-20T10:05:04+00:00","repository":"https://github.com/multica-ai/andrej-karpathy-skills","github_repo":"multica-ai/andrej-karpathy-skills","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"recommendation_reasons":["Matches task terms: karpathy","Strong GitHub adoption: 175,191 stars","Quality score 83/100","Install handoff is available","Repository freshness signal is available"],"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":"workflow-automation","title":"Workflow automation"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add multica-ai/andrej-karpathy-skills","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":175191,"starsLabel":"175K","forks":17868,"license":"Unknown","qualityScore":100,"trustScore":85,"auditScore":87},"maintenance":{"status":"active","label":"5mo since push","daysSincePush":141,"lastPushedAt":"2026-04-20T10:05:04+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"coverageTags":["Coding","Coding agents","development","claude-code","agent-skills","developer-tools","github","Claude Code"]},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"175K","tone":"positive"},{"label":"Freshness","value":"5mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","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":"175K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"175K stars, 18K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"5mo 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 multica-ai/andrej-karpathy-skills"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":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/multica-ai/andrej-karpathy-skills"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":63,"weight":0.13,"status":"info","detail":"Early agent signal: 100% success from 5 agent outcomes"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"175K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"175K stars, 18K forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"5mo 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 multica-ai/andrej-karpathy-skills"},{"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/multica-ai/andrej-karpathy-skills"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"Early agent signal: 100% success from 5 agent outcomes"},{"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":"Early agent signal: 100% success from 5 agent outcomes"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Large GitHub adoption signal","Install command has no obvious high-risk pattern","Agent Proven evidence available: Early agent signal: 100% success from 5 agent outcomes"],"warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown"],"evidence":{"stars":"175K GitHub stars","repoActivity":"175K stars, 18K forks","lastPushed":"5mo since push","license":"Unknown","repository":"https://github.com/multica-ai/andrej-karpathy-skills","install":"npx skills add multica-ai/andrej-karpathy-skills","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"Early agent signal: 100% success from 5 agent outcomes"},"installReadiness":{"ready":true,"command":"npx skills add multica-ai/andrej-karpathy-skills","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","Early agent signal (63/100 Agent Proven)","5mo since push"]},"agentCompatibility":["Claude Code","Codex","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"outcomeEvidence":{"total":5,"successes":5,"failures":0,"notRelevant":0,"successRate":100,"installAttempts":5,"riskBlocked":0,"setupRequired":0,"installSuccessRate":100,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":100,"recentFailureRate":0,"uniqueAgents":1,"agentProvenScore":63,"agentProvenLabel":"Early agent signal","lastOutcomeAt":"2026-09-07T11:19:38.644233+00:00","label":"Early agent signal: 100% success from 5 agent outcomes"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["development","claude-code","agent-skills","developer-tools","github","Claude Code"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"trust_v5":{"version":"trust-score-v5","score":75,"base_score":88,"outcome_confidence":0.65,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["75/100 Trust Score v5","88/100 Trust Score v4 baseline","Early agent signal: 100% success from 5 agent outcomes; outcome confidence 65%","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"175K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"175K stars, 18K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"5mo 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 multica-ai/andrej-karpathy-skills"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":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/multica-ai/andrej-karpathy-skills"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":63,"weight":0.13,"status":"info","detail":"Early agent signal: 100% success from 5 agent outcomes"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"175K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"175K stars, 18K forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"5mo 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 multica-ai/andrej-karpathy-skills"},{"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/multica-ai/andrej-karpathy-skills"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"Early agent signal: 100% success from 5 agent outcomes"},{"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":"Early agent signal: 100% success from 5 agent outcomes"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Large GitHub adoption signal","Install command has no obvious high-risk pattern","Agent Proven evidence available: Early agent signal: 100% success from 5 agent outcomes","Outcome confidence 65% from 5 report(s)"],"warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown","Human review required before unattended installation"],"evidence":{"stars":"175K GitHub stars","repoActivity":"175K stars, 18K forks","lastPushed":"5mo since push","license":"Unknown","repository":"https://github.com/multica-ai/andrej-karpathy-skills","install":"npx skills add multica-ai/andrej-karpathy-skills","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"Early agent signal: 100% success from 5 agent outcomes","agentProvenScore":63,"outcomeConfidence":"65%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add multica-ai/andrej-karpathy-skills","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","Early agent signal (63/100 Agent Proven)","5mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Claude Code","Codex","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"outcomeEvidence":{"total":5,"successes":5,"failures":0,"notRelevant":0,"successRate":100,"installAttempts":5,"riskBlocked":0,"setupRequired":0,"installSuccessRate":100,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":100,"recentFailureRate":0,"uniqueAgents":1,"agentProvenScore":63,"agentProvenLabel":"Early agent signal","lastOutcomeAt":"2026-09-07T11:19:38.644233+00:00","label":"Early agent signal: 100% success from 5 agent outcomes"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["development","claude-code","agent-skills","developer-tools","github","Claude Code"],"suited_agents":["Claude Code","Codex","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add multica-ai/andrej-karpathy-skills","trust_score":75,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["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"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["development","claude-code","agent-skills","developer-tools","github","Claude Code"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","Documentation summary is thin","License clarity: Unknown"],"backward_compatible":{"trust_score_v4":{"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."}}},"agent_proven":{"version":"agent-proven-v1","score":63,"tier":"early","label":"Early agent signal","summary":"Early agent signal: 5 outcomes, 100% success, Agent Proven Score 63/100.","metrics":{"totalOutcomes":5,"successfulOutcomes":5,"failedOutcomes":0,"installAttempts":5,"installSuccessRate":100,"successRate":100,"recentSuccessRate":100,"recentFailureRate":0,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":1,"lastOutcomeAt":"2026-09-07T11:19:38.644233+00:00"},"signals":["100% all-time success","100% recent success","5 install attempts","1 agent surface"],"penalties":[]},"audit":{"audit_score":87,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"safety":{"score":71,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","71/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["License is unclear"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","71/100 agent safety score"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Coding agents","role":"Primary pick","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."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add multica-ai/andrej-karpathy-skills","value":"Install the \"Andrej Karpathy Skills\" agent skill from https://github.com/multica-ai/andrej-karpathy-skills. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"multica-ai-andrej-karpathy-skills\",\"task\":\"Install Andrej Karpathy Skills\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review Andrej Karpathy Skills trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add multica-ai-andrej-karpathy-skills","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Andrej Karpathy Skills\" agent skill from https://github.com/multica-ai/andrej-karpathy-skills. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"multica-ai-andrej-karpathy-skills\",\"task\":\"Install Andrej Karpathy Skills\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Andrej Karpathy Skills\" as a Claude Code skill from https://github.com/multica-ai/andrej-karpathy-skills. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"multica-ai-andrej-karpathy-skills\",\"task\":\"Install Andrej Karpathy Skills\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Andrej Karpathy Skills\" from https://github.com/multica-ai/andrej-karpathy-skills into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"multica-ai-andrej-karpathy-skills\",\"task\":\"Install Andrej Karpathy Skills\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"multica-ai-andrej-karpathy-skills","name":"Andrej Karpathy Skills","description":"A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.","category":"development","url":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills","repository":"https://github.com/multica-ai/andrej-karpathy-skills","github_repo":"multica-ai/andrej-karpathy-skills"},"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":["Claude Code","Codex","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add multica-ai/andrej-karpathy-skills","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add multica-ai-andrej-karpathy-skills"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Andrej Karpathy Skills\" agent skill from https://github.com/multica-ai/andrej-karpathy-skills. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"multica-ai-andrej-karpathy-skills\",\"task\":\"Install Andrej Karpathy Skills\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Andrej Karpathy Skills\" as a Claude Code skill from https://github.com/multica-ai/andrej-karpathy-skills. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"multica-ai-andrej-karpathy-skills\",\"task\":\"Install Andrej Karpathy Skills\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Andrej Karpathy Skills\" from https://github.com/multica-ai/andrej-karpathy-skills into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"multica-ai-andrej-karpathy-skills\",\"task\":\"Install Andrej Karpathy Skills\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/multica-ai-andrej-karpathy-skills/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/multica-ai-andrej-karpathy-skills"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"175K GitHub stars","repoActivity":"175K stars, 18K forks","lastPushed":"5mo since push","license":"Unknown","repository":"https://github.com/multica-ai/andrej-karpathy-skills","install":"npx skills add multica-ai/andrej-karpathy-skills","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"Early agent signal: 100% success from 5 agent outcomes"},"outcome_evidence":{"total":5,"successes":5,"failures":0,"not_relevant":0,"success_rate":100,"recent_success_rate":100,"recent_failure_rate":0,"install_attempts":5,"install_success_rate":100,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":"2026-09-07T11:19:38.644233+00:00","label":"Early agent signal: 100% success from 5 agent outcomes"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["development","claude-code","agent-skills","developer-tools","github","Claude Code"],"known_risks":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":63,"tier":"early","label":"Early agent signal","summary":"Early agent signal: 5 outcomes, 100% success, Agent Proven Score 63/100.","metrics":{"totalOutcomes":5,"successfulOutcomes":5,"failedOutcomes":0,"installAttempts":5,"installSuccessRate":100,"successRate":100,"recentSuccessRate":100,"recentFailureRate":0,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":1,"lastOutcomeAt":"2026-09-07T11:19:38.644233+00:00"},"signals":["100% all-time success","100% recent success","5 install attempts","1 agent surface"],"penalties":[]},"audit":{"score":87,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"5mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use karpathy","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: 87/100 Safe to try","Safety: 71/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"multica-ai-andrej-karpathy-skills (Andrej Karpathy Skills)","install_command":"npx skills add multica-ai/andrej-karpathy-skills","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":"multica-ai-andrej-karpathy-skills","task":"Use karpathy","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/multica-ai-andrej-karpathy-skills","api":"https://www.openagentskill.com/api/agent/skills/multica-ai-andrej-karpathy-skills","audit":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=multica-ai-andrej-karpathy-skills&task=Use%20karpathy&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20karpathy&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20karpathy&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/multica-ai-andrej-karpathy-skills/install","manifest":"https://www.openagentskill.com/api/registry/manifest/multica-ai-andrej-karpathy-skills"}},"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":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"urls":{"web":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills","api":"https://www.openagentskill.com/api/agent/skills/multica-ai-andrej-karpathy-skills","install_api":"https://www.openagentskill.com/api/skills/multica-ai-andrej-karpathy-skills/install","audit":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=multica-ai-andrej-karpathy-skills&task=Use%20karpathy&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/multica-ai-andrej-karpathy-skills?metric=audit","repository":"https://github.com/multica-ai/andrej-karpathy-skills"}},"safer_alternative":{"rank":12,"match_score":30,"raw_match_score":73.9,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"uditgoenka-autoresearch","name":"Autoresearch","description":"Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.","category":"development","github_stars":5975,"created_at":"2026-06-16T08:45:37.929318+00:00","updated_at":"2026-08-12T22:28:18+00:00","repository":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch","github_repo":"uditgoenka/autoresearch","source_version":{"version":"2.2.2","commit_sha":"050e30dc4ba0974b03f2873111b9901ec3211390","content_hash":"c3ec24a5c90e72bfeca1f69702d5c9159c90b3c8546e94a87eead20a715e6045","ref":"master","path":".agents/skills/autoresearch/SKILL.md","sync_status":"changed"}},"recommendation_reasons":["Matches task terms: karpathy","Useful GitHub adoption: 5,975 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"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":"research-agents","title":"Research agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","JavaScript"],"install":{"ready":true,"command":"npx skills add uditgoenka/autoresearch","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":5975,"starsLabel":"6.0K","forks":446,"license":"MIT","qualityScore":100,"trustScore":90,"auditScore":94},"maintenance":{"status":"fresh","label":"26d since push","daysSincePush":26,"lastPushedAt":"2026-08-12T22:28:18+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Coding","Coding agents","development","claude-code","agent-skills","developer-tools","ai","autonomous-agent"]},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"6.0K","tone":"positive"},{"label":"Freshness","value":"26d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":90,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"weight":0.13,"status":"pass","detail":"6.0K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"6.0K stars, 446 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"26d 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 uditgoenka/autoresearch"},{"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/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch"},{"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":"6.0K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"6.0K stars, 446 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"26d 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 uditgoenka/autoresearch"},{"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/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin"],"evidence":{"stars":"6.0K GitHub stars","repoActivity":"6.0K stars, 446 forks","lastPushed":"26d since push","license":"MIT","repository":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch","install":"npx skills add uditgoenka/autoresearch","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 uditgoenka/autoresearch","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","26d since push"]},"agentCompatibility":["JavaScript","Claude Code","Codex","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":["development","claude-code","agent-skills","developer-tools","ai","autonomous-agent"],"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"]},"trust_v5":{"version":"trust-score-v5","score":87,"base_score":90,"outcome_confidence":0,"tier":"strong","label":"Review then install","summary":"Good shortlist signal, but the agent should review audit notes, install policy, and outcome evidence before running it.","recommendedAction":"Use as the primary candidate after human or sandbox review.","decision":{"install_policy":"agent_install_candidate","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Ask for approval or run a sandbox-only trial before installing.","reasoning":["87/100 Trust Score v5","90/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Low metadata risk"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":94,"weight":0.13,"status":"pass","detail":"6.0K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":88,"weight":0.08,"status":"pass","detail":"6.0K stars, 446 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"26d 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 uditgoenka/autoresearch"},{"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/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch"},{"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":"6.0K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"6.0K stars, 446 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"26d 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 uditgoenka/autoresearch"},{"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/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch"},{"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","Outcome loop is ready but needs first real agent run"],"warnings":["Documentation summary is thin","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"6.0K GitHub stars","repoActivity":"6.0K stars, 446 forks","lastPushed":"26d since push","license":"MIT","repository":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch","install":"npx skills add uditgoenka/autoresearch","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","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"agent_install_candidate"},"installReadiness":{"ready":true,"command":"npx skills add uditgoenka/autoresearch","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","26d since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["JavaScript","Claude Code","Codex","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":false,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Ask for approval or run a sandbox-only trial before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["development","claude-code","agent-skills","developer-tools","ai","autonomous-agent"],"suited_agents":["JavaScript","Claude Code","Codex","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add uditgoenka/autoresearch","trust_score":87,"trust_version":"trust-score-v5","risk_level":"low","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["development","claude-code","agent-skills","developer-tools","ai","autonomous-agent"],"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"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":90,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability."}}},"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":{"audit_score":94,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety":{"score":82,"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","82/100 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","82/100 agent safety score"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Coding agents","role":"Primary pick","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."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add uditgoenka/autoresearch","value":"Install the \"Autoresearch\" agent skill from https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch. 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: Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"uditgoenka-autoresearch\",\"task\":\"Install Autoresearch\",\"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.","kind":"agent-prompt","steps":["Review Autoresearch trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add uditgoenka-autoresearch","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 \"Autoresearch\" agent skill from https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch. 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: Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"uditgoenka-autoresearch\",\"task\":\"Install Autoresearch\",\"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 \"Autoresearch\" as a Claude Code skill from https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch. 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: Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"uditgoenka-autoresearch\",\"task\":\"Install Autoresearch\",\"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 \"Autoresearch\" from https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch 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: Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"uditgoenka-autoresearch\",\"task\":\"Install Autoresearch\",\"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"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"uditgoenka-autoresearch","name":"Autoresearch","description":"Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.","category":"development","url":"https://www.openagentskill.com/skills/uditgoenka-autoresearch","repository":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch","github_repo":"uditgoenka/autoresearch"},"suited_tasks":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Search sources","Extract claims"],"suited_agents":["JavaScript","Claude Code","Codex","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add uditgoenka/autoresearch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add uditgoenka-autoresearch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Autoresearch\" agent skill from https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch. 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: Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"uditgoenka-autoresearch\",\"task\":\"Install Autoresearch\",\"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 \"Autoresearch\" as a Claude Code skill from https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch. 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: Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"uditgoenka-autoresearch\",\"task\":\"Install Autoresearch\",\"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 \"Autoresearch\" from https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch 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: Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"uditgoenka-autoresearch\",\"task\":\"Install Autoresearch\",\"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/uditgoenka-autoresearch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/uditgoenka-autoresearch"},"trust":{"score":90,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"6.0K GitHub stars","repoActivity":"6.0K stars, 446 forks","lastPushed":"26d since push","license":"MIT","repository":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch","install":"npx skills add uditgoenka/autoresearch","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":["development","claude-code","agent-skills","developer-tools","ai","autonomous-agent"],"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":94,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"26d 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 karpathy","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 90/100 Production candidate","Audit: 94/100 Safe to try","Safety: 82/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"uditgoenka-autoresearch (Autoresearch)","install_command":"npx skills add uditgoenka/autoresearch","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":"uditgoenka-autoresearch","task":"Use karpathy","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/uditgoenka-autoresearch","api":"https://www.openagentskill.com/api/agent/skills/uditgoenka-autoresearch","audit":"https://www.openagentskill.com/skills/uditgoenka-autoresearch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=uditgoenka-autoresearch&task=Use%20karpathy&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20karpathy&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20karpathy&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/uditgoenka-autoresearch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/uditgoenka-autoresearch"}},"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"}],"urls":{"web":"https://www.openagentskill.com/skills/uditgoenka-autoresearch","api":"https://www.openagentskill.com/api/agent/skills/uditgoenka-autoresearch","install_api":"https://www.openagentskill.com/api/skills/uditgoenka-autoresearch/install","audit":"https://www.openagentskill.com/skills/uditgoenka-autoresearch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=uditgoenka-autoresearch&task=Use%20karpathy&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/uditgoenka-autoresearch?metric=audit","repository":"https://github.com/uditgoenka/autoresearch/tree/master/.agents/skills/autoresearch"}},"popular_alternative":{"rank":2,"match_score":30,"raw_match_score":126.2,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"astro-han-karpathy-llm-wiki","name":"Karpathy Llm Wiki","description":"Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting.","category":"agent-skills","github_stars":2139,"created_at":"2026-05-24T10:00:42.099578+00:00","updated_at":"2026-07-23T16:57:44+00:00","repository":"https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md","github_repo":"Astro-Han/karpathy-llm-wiki","source_version":{"version":"1.0.0","commit_sha":"eafcc77001e496cc43499e4923b663aec722c813","content_hash":"c154f62094738b65e91dbb1c706758137290c622e386b3204e87c60a78f75748","ref":"main","path":"SKILL.md","sync_status":"current"}},"recommendation_reasons":["Matches task terms: karpathy","Useful GitHub adoption: 2,139 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"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":"rag-knowledge","title":"RAG and knowledge"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["Claude Code","OpenAI Agents","Cursor","CLI","Codex"],"install":{"ready":true,"command":"npx skills add Astro-Han/karpathy-llm-wiki","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":2139,"starsLabel":"2.1K","forks":254,"license":"MIT","qualityScore":93,"trustScore":88,"auditScore":90},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":46,"lastPushedAt":"2026-07-23T16:57:44+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Coding","Coding agents","agent-skills","agent-skill","skills","claude-code","codex","cursor"]},"quality":{"score":93,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"2.1K","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":88,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"2.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"2.1K stars, 254 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add Astro-Han/karpathy-llm-wiki"},{"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/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"2.1K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"2.1K stars, 254 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add Astro-Han/karpathy-llm-wiki"},{"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/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md"},{"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":"2.1K GitHub stars","repoActivity":"2.1K stars, 254 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md","install":"npx skills add Astro-Han/karpathy-llm-wiki","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 Astro-Han/karpathy-llm-wiki","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":["AI Agents","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":["agent-skills","agent-skill","skills","claude-code","codex","cursor"],"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"]},"trust_v5":{"version":"trust-score-v5","score":85,"base_score":88,"outcome_confidence":0,"tier":"strong","label":"Review then install","summary":"Good shortlist signal, but the agent should review audit notes, install policy, and outcome evidence before running it.","recommendedAction":"Use as the primary candidate after human or sandbox review.","decision":{"install_policy":"agent_install_candidate","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Ask for approval or run a sandbox-only trial before installing.","reasoning":["85/100 Trust Score v5","88/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Low metadata risk"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"2.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"2.1K stars, 254 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add Astro-Han/karpathy-llm-wiki"},{"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/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"2.1K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"2.1K stars, 254 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add Astro-Han/karpathy-llm-wiki"},{"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/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md"},{"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","Outcome loop is ready but needs first real agent run"],"warnings":["Documentation summary is thin","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"2.1K GitHub stars","repoActivity":"2.1K stars, 254 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md","install":"npx skills add Astro-Han/karpathy-llm-wiki","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","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"agent_install_candidate"},"installReadiness":{"ready":true,"command":"npx skills add Astro-Han/karpathy-llm-wiki","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","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["AI Agents","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":false,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Ask for approval or run a sandbox-only trial before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["agent-skills","agent-skill","skills","claude-code","codex","cursor"],"suited_agents":["AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add Astro-Han/karpathy-llm-wiki","trust_score":85,"trust_version":"trust-score-v5","risk_level":"low","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["agent-skills","agent-skill","skills","claude-code","codex","cursor"],"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"],"backward_compatible":{"trust_score_v4":{"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."}}},"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":{"audit_score":90,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety":{"score":78,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","78/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","78/100 agent safety score"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Coding agents","role":"Primary pick","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."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add Astro-Han/karpathy-llm-wiki","value":"Install the \"Karpathy Llm Wiki\" agent skill from https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md. 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: Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"astro-han-karpathy-llm-wiki\",\"task\":\"Install Karpathy Llm Wiki\",\"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.","kind":"agent-prompt","steps":["Review Karpathy Llm Wiki trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add astro-han-karpathy-llm-wiki","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 \"Karpathy Llm Wiki\" agent skill from https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md. 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: Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"astro-han-karpathy-llm-wiki\",\"task\":\"Install Karpathy Llm Wiki\",\"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 \"Karpathy Llm Wiki\" as a Claude Code skill from https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md. 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: Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"astro-han-karpathy-llm-wiki\",\"task\":\"Install Karpathy Llm Wiki\",\"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 \"Karpathy Llm Wiki\" from https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md 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: Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"astro-han-karpathy-llm-wiki\",\"task\":\"Install Karpathy Llm Wiki\",\"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"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"astro-han-karpathy-llm-wiki","name":"Karpathy Llm Wiki","description":"Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting.","category":"agent-skills","url":"https://www.openagentskill.com/skills/astro-han-karpathy-llm-wiki","repository":"https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md","github_repo":"Astro-Han/karpathy-llm-wiki"},"suited_tasks":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Chunk documents","Create embeddings"],"suited_agents":["AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add Astro-Han/karpathy-llm-wiki","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add astro-han-karpathy-llm-wiki"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Karpathy Llm Wiki\" agent skill from https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md. 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: Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"astro-han-karpathy-llm-wiki\",\"task\":\"Install Karpathy Llm Wiki\",\"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 \"Karpathy Llm Wiki\" as a Claude Code skill from https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md. 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: Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"astro-han-karpathy-llm-wiki\",\"task\":\"Install Karpathy Llm Wiki\",\"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 \"Karpathy Llm Wiki\" from https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md 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: Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"astro-han-karpathy-llm-wiki\",\"task\":\"Install Karpathy Llm Wiki\",\"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/astro-han-karpathy-llm-wiki/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/astro-han-karpathy-llm-wiki"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"2.1K GitHub stars","repoActivity":"2.1K stars, 254 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md","install":"npx skills add Astro-Han/karpathy-llm-wiki","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":["agent-skills","agent-skill","skills","claude-code","codex","cursor"],"known_risks":["Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":90,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":93,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","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 karpathy","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 88/100 Production candidate","Audit: 90/100 Safe to try","Safety: 78/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"astro-han-karpathy-llm-wiki (Karpathy Llm Wiki)","install_command":"npx skills add Astro-Han/karpathy-llm-wiki","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":"astro-han-karpathy-llm-wiki","task":"Use karpathy","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/astro-han-karpathy-llm-wiki","api":"https://www.openagentskill.com/api/agent/skills/astro-han-karpathy-llm-wiki","audit":"https://www.openagentskill.com/skills/astro-han-karpathy-llm-wiki/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=astro-han-karpathy-llm-wiki&task=Use%20karpathy&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20karpathy&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20karpathy&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/astro-han-karpathy-llm-wiki/install","manifest":"https://www.openagentskill.com/api/registry/manifest/astro-han-karpathy-llm-wiki"}},"use_cases":[{"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"}],"urls":{"web":"https://www.openagentskill.com/skills/astro-han-karpathy-llm-wiki","api":"https://www.openagentskill.com/api/agent/skills/astro-han-karpathy-llm-wiki","install_api":"https://www.openagentskill.com/api/skills/astro-han-karpathy-llm-wiki/install","audit":"https://www.openagentskill.com/skills/astro-han-karpathy-llm-wiki/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=astro-han-karpathy-llm-wiki&task=Use%20karpathy&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/astro-han-karpathy-llm-wiki?metric=audit","repository":"https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md"}},"new_contender":{"rank":5,"match_score":30,"raw_match_score":83.8,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"k-dense-ai-andrej-karpathy","name":"andrej-karpathy","description":"Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs). Use this skill whenever you are helping the user build neural networks from scratch, debug deep learning pipelines, evaluate AI agent workflows, design LLM apps, or navigate the transition to Software 3.0 (vibe coding). It is highly relevant for pedagogy (untangling complex knowledge), assessing AI capabilities vs. limitations (jagged intelligence, tokenization limits), and architectural decisions (end-to-end optimization vs. complex pipelines). Reach for this whenever discussing LLM training, autonomous systems, or AI-assisted coding.","category":"design-creative","github_stars":122,"created_at":"2026-09-06T23:10:36.590761+00:00","updated_at":"2026-08-18T22:59:08+00:00","repository":"https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy","github_repo":"K-Dense-AI/mimeographs","source_version":{"version":"1.0.0","commit_sha":"a38f5fcad0853be3e98a6cd95d8e6bf8c66f7c7b","content_hash":"64a25ee376be2594548b1ac44446911ecbc346d1cf907fabcd01754e580ca018","ref":"main","path":"mimeographs/andrej-karpathy/SKILL.md","sync_status":"current"}},"recommendation_reasons":["Matches task terms: karpathy","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"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":"coding-agents","title":"Coding agents"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"testing-qa","title":"Testing and QA"}]},"applicableAgents":["Claude Code","OpenAI Agents","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add K-Dense-AI/mimeographs --skill andrej-karpathy","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":122,"starsLabel":"122","forks":18,"license":"MIT","qualityScore":67,"trustScore":69,"auditScore":78},"maintenance":{"status":"fresh","label":"20d since push","daysSincePush":20,"lastPushedAt":"2026-08-18T22:59:08+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","The skill does not document explicit limitations or safe operating boundaries, though it is a mental-model/persona skill rather than a tool-executing workflow.","The submission includes internal `_workspace` artifacts (critique files, generated JSON) that are not part of the skill itself and add clutter.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata"]},"coverageTags":["Design","Design and creative","design-creative","agent-skill"]},"quality":{"score":67,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"122","tone":"neutral"},{"label":"Freshness","value":"20d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory."]},"trust":{"version":"trust-score-v4","score":69,"tier":"review","label":"Manual review","summary":"Potentially useful, but at least one trust signal needs human inspection.","recommendedAction":"Inspect the repository, license, and recent activity before connecting it to agent workflows.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"122 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"122 stars, 18 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"20d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"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 K-Dense-AI/mimeographs --skill andrej-karpathy"},{"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/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","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":"122 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"122 stars, 18 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"20d 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 K-Dense-AI/mimeographs --skill andrej-karpathy"},{"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/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy"},{"status":"info","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":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"122 GitHub stars","repoActivity":"122 stars, 18 forks","lastPushed":"20d since push","license":"MIT","repository":"https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy","install":"npx skills add K-Dense-AI/mimeographs --skill andrej-karpathy","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 K-Dense-AI/mimeographs --skill andrej-karpathy","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","20d since push"]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["design-creative","agent-skill"],"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":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":61,"base_score":69,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["61/100 Trust Score v5","69/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"122 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"122 stars, 18 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"20d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"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 K-Dense-AI/mimeographs --skill andrej-karpathy"},{"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/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","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":"122 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"122 stars, 18 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"20d 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 K-Dense-AI/mimeographs --skill andrej-karpathy"},{"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/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy"},{"status":"info","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","Outcome loop is ready but needs first real agent run"],"warnings":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"122 GitHub stars","repoActivity":"122 stars, 18 forks","lastPushed":"20d since push","license":"MIT","repository":"https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy","install":"npx skills add K-Dense-AI/mimeographs --skill andrej-karpathy","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","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add K-Dense-AI/mimeographs --skill andrej-karpathy","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","20d since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["design-creative","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add K-Dense-AI/mimeographs --skill andrej-karpathy","trust_score":61,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["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"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["design-creative","agent-skill"],"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":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":69,"tier":"review","label":"Manual review","summary":"Potentially useful, but at least one trust signal needs human inspection."}}},"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":{"audit_score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","The skill does not document explicit limitations or safe operating boundaries, though it is a mental-model/persona skill rather than a tool-executing workflow.","The submission includes internal `_workspace` artifacts (critique files, generated JSON) that are not part of the skill itself and add clutter.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata"]},"safety":{"score":66,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","66/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory."],"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":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","66/100 agent safety score"]},"decision":{"readiness_score":66,"readiness_label":"Prototype first","headline":"Fallback candidate for Coding agents","role":"Fallback candidate","best_for":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects"],"risks":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","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."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add K-Dense-AI/mimeographs --skill andrej-karpathy","value":"Install the \"andrej-karpathy\" agent skill from https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy. 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: Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs). Use this skill whenever you are helping the user build neural networks from scratch, debug deep learning pipelines, evaluate AI agent workflows, design LLM apps, or navigate the transition to Software 3.0 (vibe coding). It is highly relevant for pedagogy (untangling complex knowledge), assessing AI capabilities vs. limitations (jagged intelligence, tokenization limits), and architectural decisions (end-to-end optimization vs. complex pipelines). Reach for this whenever discussing LLM training, autonomous systems, or AI-assisted coding. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"k-dense-ai-andrej-karpathy\",\"task\":\"Install andrej-karpathy\",\"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.","kind":"agent-prompt","steps":["Review andrej-karpathy trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add k-dense-ai-andrej-karpathy","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 \"andrej-karpathy\" agent skill from https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy. 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: Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs). Use this skill whenever you are helping the user build neural networks from scratch, debug deep learning pipelines, evaluate AI agent workflows, design LLM apps, or navigate the transition to Software 3.0 (vibe coding). It is highly relevant for pedagogy (untangling complex knowledge), assessing AI capabilities vs. limitations (jagged intelligence, tokenization limits), and architectural decisions (end-to-end optimization vs. complex pipelines). Reach for this whenever discussing LLM training, autonomous systems, or AI-assisted coding. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"k-dense-ai-andrej-karpathy\",\"task\":\"Install andrej-karpathy\",\"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 \"andrej-karpathy\" as a Claude Code skill from https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy. 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: Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs). Use this skill whenever you are helping the user build neural networks from scratch, debug deep learning pipelines, evaluate AI agent workflows, design LLM apps, or navigate the transition to Software 3.0 (vibe coding). It is highly relevant for pedagogy (untangling complex knowledge), assessing AI capabilities vs. limitations (jagged intelligence, tokenization limits), and architectural decisions (end-to-end optimization vs. complex pipelines). Reach for this whenever discussing LLM training, autonomous systems, or AI-assisted coding. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"k-dense-ai-andrej-karpathy\",\"task\":\"Install andrej-karpathy\",\"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 \"andrej-karpathy\" from https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy 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: Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs). Use this skill whenever you are helping the user build neural networks from scratch, debug deep learning pipelines, evaluate AI agent workflows, design LLM apps, or navigate the transition to Software 3.0 (vibe coding). It is highly relevant for pedagogy (untangling complex knowledge), assessing AI capabilities vs. limitations (jagged intelligence, tokenization limits), and architectural decisions (end-to-end optimization vs. complex pipelines). Reach for this whenever discussing LLM training, autonomous systems, or AI-assisted coding. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"k-dense-ai-andrej-karpathy\",\"task\":\"Install andrej-karpathy\",\"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"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"k-dense-ai-andrej-karpathy","name":"andrej-karpathy","description":"Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs). Use this skill whenever you are helping the user build neural networks from scratch, debug deep learning pipelines, evaluate AI agent workflows, design LLM apps, or navigate the transition to Software 3.0 (vibe coding). It is highly relevant for pedagogy (untangling complex knowledge), assessing AI capabilities vs. limitations (jagged intelligence, tokenization limits), and architectural decisions (end-to-end optimization vs. complex pipelines). Reach for this whenever discussing LLM training, autonomous systems, or AI-assisted coding.","category":"design-creative","url":"https://www.openagentskill.com/skills/k-dense-ai-andrej-karpathy","repository":"https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy","github_repo":"K-Dense-AI/mimeographs"},"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Navigate pages","Click and type safely"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add K-Dense-AI/mimeographs --skill andrej-karpathy","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add k-dense-ai-andrej-karpathy"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"andrej-karpathy\" agent skill from https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy. 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: Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs). Use this skill whenever you are helping the user build neural networks from scratch, debug deep learning pipelines, evaluate AI agent workflows, design LLM apps, or navigate the transition to Software 3.0 (vibe coding). It is highly relevant for pedagogy (untangling complex knowledge), assessing AI capabilities vs. limitations (jagged intelligence, tokenization limits), and architectural decisions (end-to-end optimization vs. complex pipelines). Reach for this whenever discussing LLM training, autonomous systems, or AI-assisted coding. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"k-dense-ai-andrej-karpathy\",\"task\":\"Install andrej-karpathy\",\"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 \"andrej-karpathy\" as a Claude Code skill from https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy. 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: Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs). Use this skill whenever you are helping the user build neural networks from scratch, debug deep learning pipelines, evaluate AI agent workflows, design LLM apps, or navigate the transition to Software 3.0 (vibe coding). It is highly relevant for pedagogy (untangling complex knowledge), assessing AI capabilities vs. limitations (jagged intelligence, tokenization limits), and architectural decisions (end-to-end optimization vs. complex pipelines). Reach for this whenever discussing LLM training, autonomous systems, or AI-assisted coding. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"k-dense-ai-andrej-karpathy\",\"task\":\"Install andrej-karpathy\",\"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 \"andrej-karpathy\" from https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy 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: Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs). Use this skill whenever you are helping the user build neural networks from scratch, debug deep learning pipelines, evaluate AI agent workflows, design LLM apps, or navigate the transition to Software 3.0 (vibe coding). It is highly relevant for pedagogy (untangling complex knowledge), assessing AI capabilities vs. limitations (jagged intelligence, tokenization limits), and architectural decisions (end-to-end optimization vs. complex pipelines). Reach for this whenever discussing LLM training, autonomous systems, or AI-assisted coding. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"k-dense-ai-andrej-karpathy\",\"task\":\"Install andrej-karpathy\",\"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/k-dense-ai-andrej-karpathy/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/k-dense-ai-andrej-karpathy"},"trust":{"score":69,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"122 GitHub stars","repoActivity":"122 stars, 18 forks","lastPushed":"20d since push","license":"MIT","repository":"https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy","install":"npx skills add K-Dense-AI/mimeographs --skill andrej-karpathy","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":["design-creative","agent-skill"],"known_risks":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","The skill does not document explicit limitations or safe operating boundaries, though it is a mental-model/persona skill rather than a tool-executing workflow.","The submission includes internal `_workspace` artifacts (critique files, generated JSON) that are not part of the skill itself and add clutter.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":67,"label":"Promising"},"supply":{"track":"Design and creative production","scenario":"Design and creative","maintenance":"20d since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","production agents without a repository review","SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","No OpenAgentSkill engagement data yet","The skill does not document explicit limitations or safe operating boundaries, though it is a mental-model/persona skill rather than a tool-executing workflow.","The submission includes internal `_workspace` artifacts (critique files, generated JSON) that are not part of the skill itself and add clutter.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata"],"agent_contract":{"task_input":"Use karpathy","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 69/100 Manual review","Audit: 78/100 Needs review","Safety: 66/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"k-dense-ai-andrej-karpathy (andrej-karpathy)","install_command":"npx skills add K-Dense-AI/mimeographs --skill andrej-karpathy","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":"k-dense-ai-andrej-karpathy","task":"Use karpathy","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/k-dense-ai-andrej-karpathy","api":"https://www.openagentskill.com/api/agent/skills/k-dense-ai-andrej-karpathy","audit":"https://www.openagentskill.com/skills/k-dense-ai-andrej-karpathy/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=k-dense-ai-andrej-karpathy&task=Use%20karpathy&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20karpathy&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20karpathy&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/k-dense-ai-andrej-karpathy/install","manifest":"https://www.openagentskill.com/api/registry/manifest/k-dense-ai-andrej-karpathy"}},"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"testing-qa","title":"Testing and QA","url":"https://www.openagentskill.com/use-cases/testing-qa"}],"urls":{"web":"https://www.openagentskill.com/skills/k-dense-ai-andrej-karpathy","api":"https://www.openagentskill.com/api/agent/skills/k-dense-ai-andrej-karpathy","install_api":"https://www.openagentskill.com/api/skills/k-dense-ai-andrej-karpathy/install","audit":"https://www.openagentskill.com/skills/k-dense-ai-andrej-karpathy/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=k-dense-ai-andrej-karpathy&task=Use%20karpathy&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/k-dense-ai-andrej-karpathy?metric=audit","repository":"https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy"}},"no_skill_option":{"recommended":true,"label":"Build without a third-party skill","reason":"Use a native agent workflow when the third-party permission or maintenance surface is not acceptable.","action":"Use the agent’s built-in tools for one narrow run, then reconsider a skill only if the workflow repeats."}},"selected":{"rank":1,"match_score":30,"raw_match_score":128,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"multica-ai-andrej-karpathy-skills","name":"Andrej Karpathy Skills","description":"A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.","category":"development","github_stars":175191,"created_at":"2026-06-14T16:01:34.129875+00:00","updated_at":"2026-04-20T10:05:04+00:00","repository":"https://github.com/multica-ai/andrej-karpathy-skills","github_repo":"multica-ai/andrej-karpathy-skills","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"recommendation_reasons":["Matches task terms: karpathy","Strong GitHub adoption: 175,191 stars","Quality score 83/100","Install handoff is available","Repository freshness signal is available"],"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":"workflow-automation","title":"Workflow automation"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add multica-ai/andrej-karpathy-skills","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":175191,"starsLabel":"175K","forks":17868,"license":"Unknown","qualityScore":100,"trustScore":85,"auditScore":87},"maintenance":{"status":"active","label":"5mo since push","daysSincePush":141,"lastPushedAt":"2026-04-20T10:05:04+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"coverageTags":["Coding","Coding agents","development","claude-code","agent-skills","developer-tools","github","Claude Code"]},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"175K","tone":"positive"},{"label":"Freshness","value":"5mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","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":"175K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"175K stars, 18K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"5mo 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 multica-ai/andrej-karpathy-skills"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":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/multica-ai/andrej-karpathy-skills"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":63,"weight":0.13,"status":"info","detail":"Early agent signal: 100% success from 5 agent outcomes"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"175K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"175K stars, 18K forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"5mo 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 multica-ai/andrej-karpathy-skills"},{"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/multica-ai/andrej-karpathy-skills"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"Early agent signal: 100% success from 5 agent outcomes"},{"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":"Early agent signal: 100% success from 5 agent outcomes"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Large GitHub adoption signal","Install command has no obvious high-risk pattern","Agent Proven evidence available: Early agent signal: 100% success from 5 agent outcomes"],"warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown"],"evidence":{"stars":"175K GitHub stars","repoActivity":"175K stars, 18K forks","lastPushed":"5mo since push","license":"Unknown","repository":"https://github.com/multica-ai/andrej-karpathy-skills","install":"npx skills add multica-ai/andrej-karpathy-skills","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"Early agent signal: 100% success from 5 agent outcomes"},"installReadiness":{"ready":true,"command":"npx skills add multica-ai/andrej-karpathy-skills","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","Early agent signal (63/100 Agent Proven)","5mo since push"]},"agentCompatibility":["Claude Code","Codex","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"outcomeEvidence":{"total":5,"successes":5,"failures":0,"notRelevant":0,"successRate":100,"installAttempts":5,"riskBlocked":0,"setupRequired":0,"installSuccessRate":100,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":100,"recentFailureRate":0,"uniqueAgents":1,"agentProvenScore":63,"agentProvenLabel":"Early agent signal","lastOutcomeAt":"2026-09-07T11:19:38.644233+00:00","label":"Early agent signal: 100% success from 5 agent outcomes"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["development","claude-code","agent-skills","developer-tools","github","Claude Code"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"trust_v5":{"version":"trust-score-v5","score":75,"base_score":88,"outcome_confidence":0.65,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["75/100 Trust Score v5","88/100 Trust Score v4 baseline","Early agent signal: 100% success from 5 agent outcomes; outcome confidence 65%","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"175K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"175K stars, 18K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"5mo 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 multica-ai/andrej-karpathy-skills"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":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/multica-ai/andrej-karpathy-skills"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":63,"weight":0.13,"status":"info","detail":"Early agent signal: 100% success from 5 agent outcomes"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"175K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"175K stars, 18K forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"5mo 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 multica-ai/andrej-karpathy-skills"},{"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/multica-ai/andrej-karpathy-skills"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"Early agent signal: 100% success from 5 agent outcomes"},{"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":"Early agent signal: 100% success from 5 agent outcomes"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Large GitHub adoption signal","Install command has no obvious high-risk pattern","Agent Proven evidence available: Early agent signal: 100% success from 5 agent outcomes","Outcome confidence 65% from 5 report(s)"],"warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown","Human review required before unattended installation"],"evidence":{"stars":"175K GitHub stars","repoActivity":"175K stars, 18K forks","lastPushed":"5mo since push","license":"Unknown","repository":"https://github.com/multica-ai/andrej-karpathy-skills","install":"npx skills add multica-ai/andrej-karpathy-skills","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"Early agent signal: 100% success from 5 agent outcomes","agentProvenScore":63,"outcomeConfidence":"65%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add multica-ai/andrej-karpathy-skills","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","Early agent signal (63/100 Agent Proven)","5mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Claude Code","Codex","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"outcomeEvidence":{"total":5,"successes":5,"failures":0,"notRelevant":0,"successRate":100,"installAttempts":5,"riskBlocked":0,"setupRequired":0,"installSuccessRate":100,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":100,"recentFailureRate":0,"uniqueAgents":1,"agentProvenScore":63,"agentProvenLabel":"Early agent signal","lastOutcomeAt":"2026-09-07T11:19:38.644233+00:00","label":"Early agent signal: 100% success from 5 agent outcomes"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["development","claude-code","agent-skills","developer-tools","github","Claude Code"],"suited_agents":["Claude Code","Codex","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add multica-ai/andrej-karpathy-skills","trust_score":75,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["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"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["development","claude-code","agent-skills","developer-tools","github","Claude Code"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace","Commercial reuse before clarifying license terms"],"knownRisks":["License is unclear","Documentation summary is thin","License clarity: Unknown"],"backward_compatible":{"trust_score_v4":{"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."}}},"agent_proven":{"version":"agent-proven-v1","score":63,"tier":"early","label":"Early agent signal","summary":"Early agent signal: 5 outcomes, 100% success, Agent Proven Score 63/100.","metrics":{"totalOutcomes":5,"successfulOutcomes":5,"failedOutcomes":0,"installAttempts":5,"installSuccessRate":100,"successRate":100,"recentSuccessRate":100,"recentFailureRate":0,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":1,"lastOutcomeAt":"2026-09-07T11:19:38.644233+00:00"},"signals":["100% all-time success","100% recent success","5 install attempts","1 agent surface"],"penalties":[]},"audit":{"audit_score":87,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"safety":{"score":71,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","71/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["License is unclear"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","71/100 agent safety score"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Coding agents","role":"Primary pick","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."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add multica-ai/andrej-karpathy-skills","value":"Install the \"Andrej Karpathy Skills\" agent skill from https://github.com/multica-ai/andrej-karpathy-skills. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"multica-ai-andrej-karpathy-skills\",\"task\":\"Install Andrej Karpathy Skills\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","kind":"agent-prompt","steps":["Review Andrej Karpathy Skills trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add multica-ai-andrej-karpathy-skills","description":"Resolve policy, run the source installer safely, and report a verified install receipt.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Andrej Karpathy Skills\" agent skill from https://github.com/multica-ai/andrej-karpathy-skills. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"multica-ai-andrej-karpathy-skills\",\"task\":\"Install Andrej Karpathy Skills\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"Andrej Karpathy Skills\" as a Claude Code skill from https://github.com/multica-ai/andrej-karpathy-skills. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"multica-ai-andrej-karpathy-skills\",\"task\":\"Install Andrej Karpathy Skills\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"Andrej Karpathy Skills\" from https://github.com/multica-ai/andrej-karpathy-skills into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"multica-ai-andrej-karpathy-skills\",\"task\":\"Install Andrej Karpathy Skills\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"multica-ai-andrej-karpathy-skills","name":"Andrej Karpathy Skills","description":"A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.","category":"development","url":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills","repository":"https://github.com/multica-ai/andrej-karpathy-skills","github_repo":"multica-ai/andrej-karpathy-skills"},"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":["Claude Code","Codex","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add multica-ai/andrej-karpathy-skills","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add multica-ai-andrej-karpathy-skills"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Andrej Karpathy Skills\" agent skill from https://github.com/multica-ai/andrej-karpathy-skills. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"multica-ai-andrej-karpathy-skills\",\"task\":\"Install Andrej Karpathy Skills\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Andrej Karpathy Skills\" as a Claude Code skill from https://github.com/multica-ai/andrej-karpathy-skills. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"multica-ai-andrej-karpathy-skills\",\"task\":\"Install Andrej Karpathy Skills\",\"agent\":\"claude-code\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Andrej Karpathy Skills\" from https://github.com/multica-ai/andrej-karpathy-skills into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"multica-ai-andrej-karpathy-skills\",\"task\":\"Install Andrej Karpathy Skills\",\"agent\":\"cursor\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes."}],"handoff_url":"https://www.openagentskill.com/api/skills/multica-ai-andrej-karpathy-skills/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/multica-ai-andrej-karpathy-skills"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"175K GitHub stars","repoActivity":"175K stars, 18K forks","lastPushed":"5mo since push","license":"Unknown","repository":"https://github.com/multica-ai/andrej-karpathy-skills","install":"npx skills add multica-ai/andrej-karpathy-skills","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"Early agent signal: 100% success from 5 agent outcomes"},"outcome_evidence":{"total":5,"successes":5,"failures":0,"not_relevant":0,"success_rate":100,"recent_success_rate":100,"recent_failure_rate":0,"install_attempts":5,"install_success_rate":100,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":"2026-09-07T11:19:38.644233+00:00","label":"Early agent signal: 100% success from 5 agent outcomes"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["development","claude-code","agent-skills","developer-tools","github","Claude Code"],"known_risks":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"agent_proven":{"version":"agent-proven-v1","score":63,"tier":"early","label":"Early agent signal","summary":"Early agent signal: 5 outcomes, 100% success, Agent Proven Score 63/100.","metrics":{"totalOutcomes":5,"successfulOutcomes":5,"failedOutcomes":0,"installAttempts":5,"installSuccessRate":100,"successRate":100,"recentSuccessRate":100,"recentFailureRate":0,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":1,"lastOutcomeAt":"2026-09-07T11:19:38.644233+00:00"},"signals":["100% all-time success","100% recent success","5 install attempts","1 agent surface"],"penalties":[]},"audit":{"score":87,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"5mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use karpathy","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: 87/100 Safe to try","Safety: 71/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"multica-ai-andrej-karpathy-skills (Andrej Karpathy Skills)","install_command":"npx skills add multica-ai/andrej-karpathy-skills","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":"multica-ai-andrej-karpathy-skills","task":"Use karpathy","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/multica-ai-andrej-karpathy-skills","api":"https://www.openagentskill.com/api/agent/skills/multica-ai-andrej-karpathy-skills","audit":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=multica-ai-andrej-karpathy-skills&task=Use%20karpathy&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20karpathy&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20karpathy&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/multica-ai-andrej-karpathy-skills/install","manifest":"https://www.openagentskill.com/api/registry/manifest/multica-ai-andrej-karpathy-skills"}},"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":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"urls":{"web":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills","api":"https://www.openagentskill.com/api/agent/skills/multica-ai-andrej-karpathy-skills","install_api":"https://www.openagentskill.com/api/skills/multica-ai-andrej-karpathy-skills/install","audit":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=multica-ai-andrej-karpathy-skills&task=Use%20karpathy&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/multica-ai-andrej-karpathy-skills?metric=audit","repository":"https://github.com/multica-ai/andrej-karpathy-skills"}},"alternatives":[{"rank":2,"match_score":30,"raw_match_score":126.2,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"astro-han-karpathy-llm-wiki","name":"Karpathy Llm Wiki","description":"Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting.","category":"agent-skills","github_stars":2139,"created_at":"2026-05-24T10:00:42.099578+00:00","updated_at":"2026-07-23T16:57:44+00:00","repository":"https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md","github_repo":"Astro-Han/karpathy-llm-wiki","source_version":{"version":"1.0.0","commit_sha":"eafcc77001e496cc43499e4923b663aec722c813","content_hash":"c154f62094738b65e91dbb1c706758137290c622e386b3204e87c60a78f75748","ref":"main","path":"SKILL.md","sync_status":"current"}},"recommendation_reasons":["Matches task terms: karpathy","Useful GitHub adoption: 2,139 stars","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"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":"rag-knowledge","title":"RAG and knowledge"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["Claude Code","OpenAI Agents","Cursor","CLI","Codex"],"install":{"ready":true,"command":"npx skills add Astro-Han/karpathy-llm-wiki","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":2139,"starsLabel":"2.1K","forks":254,"license":"MIT","qualityScore":93,"trustScore":88,"auditScore":90},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":46,"lastPushedAt":"2026-07-23T16:57:44+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Coding","Coding agents","agent-skills","agent-skill","skills","claude-code","codex","cursor"]},"quality":{"score":93,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"2.1K","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":88,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"2.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"2.1K stars, 254 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add Astro-Han/karpathy-llm-wiki"},{"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/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"2.1K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"2.1K stars, 254 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add Astro-Han/karpathy-llm-wiki"},{"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/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md"},{"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":"2.1K GitHub stars","repoActivity":"2.1K stars, 254 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md","install":"npx skills add Astro-Han/karpathy-llm-wiki","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 Astro-Han/karpathy-llm-wiki","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":["AI Agents","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":["agent-skills","agent-skill","skills","claude-code","codex","cursor"],"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"]},"trust_v5":{"version":"trust-score-v5","score":85,"base_score":88,"outcome_confidence":0,"tier":"strong","label":"Review then install","summary":"Good shortlist signal, but the agent should review audit notes, install policy, and outcome evidence before running it.","recommendedAction":"Use as the primary candidate after human or sandbox review.","decision":{"install_policy":"agent_install_candidate","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Ask for approval or run a sandbox-only trial before installing.","reasoning":["85/100 Trust Score v5","88/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Low metadata risk"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"2.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"2.1K stars, 254 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add Astro-Han/karpathy-llm-wiki"},{"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/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"2.1K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"2.1K stars, 254 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add Astro-Han/karpathy-llm-wiki"},{"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/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md"},{"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","Outcome loop is ready but needs first real agent run"],"warnings":["Documentation summary is thin","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"2.1K GitHub stars","repoActivity":"2.1K stars, 254 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md","install":"npx skills add Astro-Han/karpathy-llm-wiki","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","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"agent_install_candidate"},"installReadiness":{"ready":true,"command":"npx skills add Astro-Han/karpathy-llm-wiki","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","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["AI Agents","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":false,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Ask for approval or run a sandbox-only trial before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["agent-skills","agent-skill","skills","claude-code","codex","cursor"],"suited_agents":["AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add Astro-Han/karpathy-llm-wiki","trust_score":85,"trust_version":"trust-score-v5","risk_level":"low","do_not_use_when":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["agent-skills","agent-skill","skills","claude-code","codex","cursor"],"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"],"backward_compatible":{"trust_score_v4":{"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."}}},"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":{"audit_score":90,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety":{"score":78,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","78/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","78/100 agent safety score"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Coding agents","role":"Primary pick","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."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add Astro-Han/karpathy-llm-wiki","value":"Install the \"Karpathy Llm Wiki\" agent skill from https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md. 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: Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"astro-han-karpathy-llm-wiki\",\"task\":\"Install Karpathy Llm Wiki\",\"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.","kind":"agent-prompt","steps":["Review Karpathy Llm Wiki trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add astro-han-karpathy-llm-wiki","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 \"Karpathy Llm Wiki\" agent skill from https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md. 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: Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"astro-han-karpathy-llm-wiki\",\"task\":\"Install Karpathy Llm Wiki\",\"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 \"Karpathy Llm Wiki\" as a Claude Code skill from https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md. 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: Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"astro-han-karpathy-llm-wiki\",\"task\":\"Install Karpathy Llm Wiki\",\"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 \"Karpathy Llm Wiki\" from https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md 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: Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"astro-han-karpathy-llm-wiki\",\"task\":\"Install Karpathy Llm Wiki\",\"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"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"astro-han-karpathy-llm-wiki","name":"Karpathy Llm Wiki","description":"Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting.","category":"agent-skills","url":"https://www.openagentskill.com/skills/astro-han-karpathy-llm-wiki","repository":"https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md","github_repo":"Astro-Han/karpathy-llm-wiki"},"suited_tasks":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Chunk documents","Create embeddings"],"suited_agents":["AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add Astro-Han/karpathy-llm-wiki","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add astro-han-karpathy-llm-wiki"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Karpathy Llm Wiki\" agent skill from https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md. 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: Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"astro-han-karpathy-llm-wiki\",\"task\":\"Install Karpathy Llm Wiki\",\"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 \"Karpathy Llm Wiki\" as a Claude Code skill from https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md. 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: Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"astro-han-karpathy-llm-wiki\",\"task\":\"Install Karpathy Llm Wiki\",\"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 \"Karpathy Llm Wiki\" from https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md 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: Agent Skills-compatible LLM wiki for Claude Code, Cursor, and Codex. Build a Karpathy-style knowledge base from raw sources, citations, and linting. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"astro-han-karpathy-llm-wiki\",\"task\":\"Install Karpathy Llm Wiki\",\"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/astro-han-karpathy-llm-wiki/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/astro-han-karpathy-llm-wiki"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"2.1K GitHub stars","repoActivity":"2.1K stars, 254 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md","install":"npx skills add Astro-Han/karpathy-llm-wiki","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":["agent-skills","agent-skill","skills","claude-code","codex","cursor"],"known_risks":["Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":90,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":93,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","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 karpathy","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 88/100 Production candidate","Audit: 90/100 Safe to try","Safety: 78/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"astro-han-karpathy-llm-wiki (Karpathy Llm Wiki)","install_command":"npx skills add Astro-Han/karpathy-llm-wiki","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":"astro-han-karpathy-llm-wiki","task":"Use karpathy","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/astro-han-karpathy-llm-wiki","api":"https://www.openagentskill.com/api/agent/skills/astro-han-karpathy-llm-wiki","audit":"https://www.openagentskill.com/skills/astro-han-karpathy-llm-wiki/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=astro-han-karpathy-llm-wiki&task=Use%20karpathy&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20karpathy&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20karpathy&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/astro-han-karpathy-llm-wiki/install","manifest":"https://www.openagentskill.com/api/registry/manifest/astro-han-karpathy-llm-wiki"}},"use_cases":[{"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"}],"urls":{"web":"https://www.openagentskill.com/skills/astro-han-karpathy-llm-wiki","api":"https://www.openagentskill.com/api/agent/skills/astro-han-karpathy-llm-wiki","install_api":"https://www.openagentskill.com/api/skills/astro-han-karpathy-llm-wiki/install","audit":"https://www.openagentskill.com/skills/astro-han-karpathy-llm-wiki/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=astro-han-karpathy-llm-wiki&task=Use%20karpathy&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/astro-han-karpathy-llm-wiki?metric=audit","repository":"https://github.com/Astro-Han/karpathy-llm-wiki/blob/main/SKILL.md"}},{"rank":3,"match_score":30,"raw_match_score":84.6,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"kbwen-karpathy-principles","name":"karpathy-principles","description":"Behavioral guidelines to reduce common LLM coding mistakes — Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution.","category":"design-creative","github_stars":155,"created_at":"2026-09-04T07:25:40.479525+00:00","updated_at":"2026-09-01T13:45:57+00:00","repository":"https://github.com/KbWen/agentic-os/tree/main/.agents/skills/karpathy-principles","github_repo":"KbWen/agentic-os","source_version":{"version":"1.0.0","commit_sha":"93d054245273752e24798a725fe9753c8f3a7f57","content_hash":"d599b962a01c72ae2920ec92b3aa2d901274c72f5744c70014b784ea6e39b569","ref":"main","path":".agents/skills/karpathy-principles/SKILL.md","sync_status":"current"}},"recommendation_reasons":["Matches task terms: karpathy","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"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":"design-creative","title":"Design and creative"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add KbWen/agentic-os --skill karpathy-principles","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":155,"starsLabel":"155","forks":35,"license":"MIT","qualityScore":62,"trustScore":78,"auditScore":80},"maintenance":{"status":"fresh","label":"6d since push","daysSincePush":6,"lastPushedAt":"2026-09-01T13:45:57+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 155 stars, 35 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Needs review"]},"coverageTags":["Coding","Coding agents","design-creative","agent-skill"]},"quality":{"score":62,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"155","tone":"neutral"},{"label":"Freshness","value":"6d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":78,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"155 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"155 stars, 35 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"6d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"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 KbWen/agentic-os --skill karpathy-principles"},{"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/KbWen/agentic-os/tree/main/.agents/skills/karpathy-principles"},{"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":"155 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"155 stars, 35 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"6d 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 KbWen/agentic-os --skill karpathy-principles"},{"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/KbWen/agentic-os/tree/main/.agents/skills/karpathy-principles"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 155 stars, 35 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"155 GitHub stars","repoActivity":"155 stars, 35 forks","lastPushed":"6d since push","license":"MIT","repository":"https://github.com/KbWen/agentic-os/tree/main/.agents/skills/karpathy-principles","install":"npx skills add KbWen/agentic-os --skill karpathy-principles","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 KbWen/agentic-os --skill karpathy-principles","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","6d since push"]},"agentCompatibility":["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: 155 stars, 35 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["design-creative","agent-skill"],"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: 155 stars, 35 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":70,"base_score":78,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["70/100 Trust Score v5","78/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"155 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"155 stars, 35 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"6d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"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 KbWen/agentic-os --skill karpathy-principles"},{"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/KbWen/agentic-os/tree/main/.agents/skills/karpathy-principles"},{"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":"155 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"155 stars, 35 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"6d 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 KbWen/agentic-os --skill karpathy-principles"},{"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/KbWen/agentic-os/tree/main/.agents/skills/karpathy-principles"},{"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","Outcome loop is ready but needs first real agent run"],"warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 155 stars, 35 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"155 GitHub stars","repoActivity":"155 stars, 35 forks","lastPushed":"6d since push","license":"MIT","repository":"https://github.com/KbWen/agentic-os/tree/main/.agents/skills/karpathy-principles","install":"npx skills add KbWen/agentic-os --skill karpathy-principles","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","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add KbWen/agentic-os --skill karpathy-principles","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","6d since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["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: 155 stars, 35 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["design-creative","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add KbWen/agentic-os --skill karpathy-principles","trust_score":70,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["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"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["design-creative","agent-skill"],"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: 155 stars, 35 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":78,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"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":{"audit_score":80,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 155 stars, 35 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":68,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Quality score needs review","68/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Quality score needs review"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Quality score needs review","68/100 agent safety score"]},"decision":{"readiness_score":61,"readiness_label":"Prototype first","headline":"Fallback candidate for Design and creative","role":"Fallback candidate","best_for":["Design and creative workflows","Claude Code teams","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one 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."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add KbWen/agentic-os --skill karpathy-principles","value":"Install the \"karpathy-principles\" agent skill from https://github.com/KbWen/agentic-os/tree/main/.agents/skills/karpathy-principles. 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: Behavioral guidelines to reduce common LLM coding mistakes — Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"kbwen-karpathy-principles\",\"task\":\"Install karpathy-principles\",\"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.","kind":"agent-prompt","steps":["Review karpathy-principles trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add kbwen-karpathy-principles","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 \"karpathy-principles\" agent skill from https://github.com/KbWen/agentic-os/tree/main/.agents/skills/karpathy-principles. 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: Behavioral guidelines to reduce common LLM coding mistakes — Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"kbwen-karpathy-principles\",\"task\":\"Install karpathy-principles\",\"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 \"karpathy-principles\" as a Claude Code skill from https://github.com/KbWen/agentic-os/tree/main/.agents/skills/karpathy-principles. 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: Behavioral guidelines to reduce common LLM coding mistakes — Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"kbwen-karpathy-principles\",\"task\":\"Install karpathy-principles\",\"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 \"karpathy-principles\" from https://github.com/KbWen/agentic-os/tree/main/.agents/skills/karpathy-principles 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: Behavioral guidelines to reduce common LLM coding mistakes — Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"kbwen-karpathy-principles\",\"task\":\"Install karpathy-principles\",\"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"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"kbwen-karpathy-principles","name":"karpathy-principles","description":"Behavioral guidelines to reduce common LLM coding mistakes — Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution.","category":"design-creative","url":"https://www.openagentskill.com/skills/kbwen-karpathy-principles","repository":"https://github.com/KbWen/agentic-os/tree/main/.agents/skills/karpathy-principles","github_repo":"KbWen/agentic-os"},"suited_tasks":["Design and creative workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect visual requirements","Generate reusable assets","Package output for review","Inspect source files","Explain architecture"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add KbWen/agentic-os --skill karpathy-principles","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add kbwen-karpathy-principles"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"karpathy-principles\" agent skill from https://github.com/KbWen/agentic-os/tree/main/.agents/skills/karpathy-principles. 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: Behavioral guidelines to reduce common LLM coding mistakes — Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"kbwen-karpathy-principles\",\"task\":\"Install karpathy-principles\",\"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 \"karpathy-principles\" as a Claude Code skill from https://github.com/KbWen/agentic-os/tree/main/.agents/skills/karpathy-principles. 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: Behavioral guidelines to reduce common LLM coding mistakes — Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"kbwen-karpathy-principles\",\"task\":\"Install karpathy-principles\",\"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 \"karpathy-principles\" from https://github.com/KbWen/agentic-os/tree/main/.agents/skills/karpathy-principles 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: Behavioral guidelines to reduce common LLM coding mistakes — Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"kbwen-karpathy-principles\",\"task\":\"Install karpathy-principles\",\"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/kbwen-karpathy-principles/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/kbwen-karpathy-principles"},"trust":{"score":78,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"155 GitHub stars","repoActivity":"155 stars, 35 forks","lastPushed":"6d since push","license":"MIT","repository":"https://github.com/KbWen/agentic-os/tree/main/.agents/skills/karpathy-principles","install":"npx skills add KbWen/agentic-os --skill karpathy-principles","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":["design-creative","agent-skill"],"known_risks":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 155 stars, 35 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":80,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 155 stars, 35 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":62,"label":"Promising"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"6d since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Quality score needs review","Documentation summary is thin","Stars/forks activity: 155 stars, 35 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use karpathy","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 78/100 Strong shortlist","Audit: 80/100 Needs review","Safety: 68/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"kbwen-karpathy-principles (karpathy-principles)","install_command":"npx skills add KbWen/agentic-os --skill karpathy-principles","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":"kbwen-karpathy-principles","task":"Use karpathy","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/kbwen-karpathy-principles","api":"https://www.openagentskill.com/api/agent/skills/kbwen-karpathy-principles","audit":"https://www.openagentskill.com/skills/kbwen-karpathy-principles/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=kbwen-karpathy-principles&task=Use%20karpathy&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20karpathy&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20karpathy&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/kbwen-karpathy-principles/install","manifest":"https://www.openagentskill.com/api/registry/manifest/kbwen-karpathy-principles"}},"use_cases":[{"slug":"design-creative","title":"Design and creative","url":"https://www.openagentskill.com/use-cases/design-creative"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"}],"urls":{"web":"https://www.openagentskill.com/skills/kbwen-karpathy-principles","api":"https://www.openagentskill.com/api/agent/skills/kbwen-karpathy-principles","install_api":"https://www.openagentskill.com/api/skills/kbwen-karpathy-principles/install","audit":"https://www.openagentskill.com/skills/kbwen-karpathy-principles/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=kbwen-karpathy-principles&task=Use%20karpathy&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/kbwen-karpathy-principles?metric=audit","repository":"https://github.com/KbWen/agentic-os/tree/main/.agents/skills/karpathy-principles"}},{"rank":4,"match_score":30,"raw_match_score":84,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"gaasher-karpathy","name":"karpathy","description":"Use when the user wants the LLM to do its own ML research: a fully-autonomous loop that hacks the training code, runs it, and keeps changes that lower a single scalar metric (e.g. val_bpb). One agent proposes one change at a time, runs training in the user's env, keeps it only if the metric improves (advancing a git branch) else reverts, and loops forever until the human interrupts. A faithful adaptation of Karpathy's autoresearch. Not for the analysis-first variant that profiles before editing (that is ml-autoresearch), and not for a budgeted, plateau-stopping refactor.","category":"research","github_stars":163,"created_at":"2026-09-04T05:03:51.713977+00:00","updated_at":"2026-06-30T04:03:49+00:00","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/karpathy","github_repo":"gaasher/Agent-Loop-Skills","source_version":{"version":"1.0.0","commit_sha":"f1169e6db0b0f8a83ced3a18562b7c57e14a748a","content_hash":"3a0fad621df1c7bf21aecbad47d7354d9ce766d4aff192bc22fe721b3811d62e","ref":"main","path":"loops/karpathy/SKILL.md","sync_status":"current"}},"recommendation_reasons":["Matches task terms: karpathy","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"Research agents","description":"I need my agent to research a topic, compare sources, and produce a concise report.","useCases":[{"slug":"research-agents","title":"Research agents"},{"slug":"github-automation","title":"GitHub automation"},{"slug":"coding-agents","title":"Coding agents"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add gaasher/Agent-Loop-Skills --skill karpathy","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":163,"starsLabel":"163","forks":19,"license":"MIT","qualityScore":63,"trustScore":73,"auditScore":76},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":70,"lastPushedAt":"2026-06-30T04:03:49+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Needs review"]},"coverageTags":["Research","Research agents","agent-skill"]},"quality":{"score":63,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"163","tone":"neutral"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":73,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"163 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"163 stars, 19 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":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"credential or environment access"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add gaasher/Agent-Loop-Skills --skill karpathy"},{"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":74,"weight":0.07,"status":"info","detail":"secrets or environment access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/karpathy"},{"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":"163 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"info","label":"Dependency/runtime risk","detail":"credential or environment access"},{"status":"pass","label":"Install availability","detail":"npx skills add gaasher/Agent-Loop-Skills --skill karpathy"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"secrets or environment access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/karpathy"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"warn","label":"Ownership","detail":"No approved owner claim yet"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/karpathy","install":"npx skills add gaasher/Agent-Loop-Skills --skill karpathy","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add gaasher/Agent-Loop-Skills --skill karpathy","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["research","agent-skill"],"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","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":65,"base_score":73,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["65/100 Trust Score v5","73/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"163 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"163 stars, 19 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":52,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":72,"weight":0.12,"status":"info","detail":"credential or environment access"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add gaasher/Agent-Loop-Skills --skill karpathy"},{"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":74,"weight":0.07,"status":"info","detail":"secrets or environment access"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/karpathy"},{"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":"163 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"163 stars, 19 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"info","label":"Dependency/runtime risk","detail":"credential or environment access"},{"status":"pass","label":"Install availability","detail":"npx skills add gaasher/Agent-Loop-Skills --skill karpathy"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"info","label":"Permission surface","detail":"secrets or environment access"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/karpathy"},{"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","Outcome loop is ready but needs first real agent run"],"warnings":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/karpathy","install":"npx skills add gaasher/Agent-Loop-Skills --skill karpathy","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add gaasher/Agent-Loop-Skills --skill karpathy","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["research","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add gaasher/Agent-Loop-Skills --skill karpathy","trust_score":65,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["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"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["research","agent-skill"],"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","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":73,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout."}}},"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":{"audit_score":76,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":52,"level":"avoid_auto_install","label":"Avoid automatic install","safety_tier":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","summary":"Sparse or mixed signals. Useful for discovery, but not for autonomous installation.","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","auto_install_policy":"review","reasons":["High-risk permission hints: Secrets or environment access","52/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"secrets","label":"Secrets or environment access","reason":"Skill metadata references credentials, tokens, environment variables, or secret-bearing workflows.","severity":"high"}],"policy_warnings":["High-risk permission hints: Secrets or environment access","Quality score needs review"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"experimental","label":"Experimental","badge":"EXPERIMENTAL","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","reasons":["High-risk permission hints: Secrets or environment access","52/100 agent safety score"]},"decision":{"readiness_score":62,"readiness_label":"Prototype first","headline":"Fallback candidate for Research agents","role":"Fallback candidate","best_for":["Research agents workflows","Claude Code teams","builders willing to evaluate younger projects"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Research agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add gaasher/Agent-Loop-Skills --skill karpathy","value":"Install the \"karpathy\" agent skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/karpathy. 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: Use when the user wants the LLM to do its own ML research: a fully-autonomous loop that hacks the training code, runs it, and keeps changes that lower a single scalar metric (e.g. val_bpb). One agent proposes one change at a time, runs training in the user's env, keeps it only if the metric improves (advancing a git branch) else reverts, and loops forever until the human interrupts. A faithful adaptation of Karpathy's autoresearch. Not for the analysis-first variant that profiles before editing (that is ml-autoresearch), and not for a budgeted, plateau-stopping refactor. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-karpathy\",\"task\":\"Install karpathy\",\"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.","kind":"agent-prompt","steps":["Review karpathy trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add gaasher-karpathy","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 \"karpathy\" agent skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/karpathy. 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: Use when the user wants the LLM to do its own ML research: a fully-autonomous loop that hacks the training code, runs it, and keeps changes that lower a single scalar metric (e.g. val_bpb). One agent proposes one change at a time, runs training in the user's env, keeps it only if the metric improves (advancing a git branch) else reverts, and loops forever until the human interrupts. A faithful adaptation of Karpathy's autoresearch. Not for the analysis-first variant that profiles before editing (that is ml-autoresearch), and not for a budgeted, plateau-stopping refactor. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-karpathy\",\"task\":\"Install karpathy\",\"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 \"karpathy\" as a Claude Code skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/karpathy. 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: Use when the user wants the LLM to do its own ML research: a fully-autonomous loop that hacks the training code, runs it, and keeps changes that lower a single scalar metric (e.g. val_bpb). One agent proposes one change at a time, runs training in the user's env, keeps it only if the metric improves (advancing a git branch) else reverts, and loops forever until the human interrupts. A faithful adaptation of Karpathy's autoresearch. Not for the analysis-first variant that profiles before editing (that is ml-autoresearch), and not for a budgeted, plateau-stopping refactor. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-karpathy\",\"task\":\"Install karpathy\",\"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 \"karpathy\" from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/karpathy 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: Use when the user wants the LLM to do its own ML research: a fully-autonomous loop that hacks the training code, runs it, and keeps changes that lower a single scalar metric (e.g. val_bpb). One agent proposes one change at a time, runs training in the user's env, keeps it only if the metric improves (advancing a git branch) else reverts, and loops forever until the human interrupts. A faithful adaptation of Karpathy's autoresearch. Not for the analysis-first variant that profiles before editing (that is ml-autoresearch), and not for a budgeted, plateau-stopping refactor. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-karpathy\",\"task\":\"Install karpathy\",\"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"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"gaasher-karpathy","name":"karpathy","description":"Use when the user wants the LLM to do its own ML research: a fully-autonomous loop that hacks the training code, runs it, and keeps changes that lower a single scalar metric (e.g. val_bpb). One agent proposes one change at a time, runs training in the user's env, keeps it only if the metric improves (advancing a git branch) else reverts, and loops forever until the human interrupts. A faithful adaptation of Karpathy's autoresearch. Not for the analysis-first variant that profiles before editing (that is ml-autoresearch), and not for a budgeted, plateau-stopping refactor.","category":"research","url":"https://www.openagentskill.com/skills/gaasher-karpathy","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/karpathy","github_repo":"gaasher/Agent-Loop-Skills"},"suited_tasks":["Research agents workflows","Claude Code teams","builders willing to evaluate younger projects","Search sources","Extract claims","Synthesize findings","Inspect repository metadata","Compare code changes"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add gaasher/Agent-Loop-Skills --skill karpathy","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add gaasher-karpathy"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"karpathy\" agent skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/karpathy. 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: Use when the user wants the LLM to do its own ML research: a fully-autonomous loop that hacks the training code, runs it, and keeps changes that lower a single scalar metric (e.g. val_bpb). One agent proposes one change at a time, runs training in the user's env, keeps it only if the metric improves (advancing a git branch) else reverts, and loops forever until the human interrupts. A faithful adaptation of Karpathy's autoresearch. Not for the analysis-first variant that profiles before editing (that is ml-autoresearch), and not for a budgeted, plateau-stopping refactor. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-karpathy\",\"task\":\"Install karpathy\",\"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 \"karpathy\" as a Claude Code skill from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/karpathy. 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: Use when the user wants the LLM to do its own ML research: a fully-autonomous loop that hacks the training code, runs it, and keeps changes that lower a single scalar metric (e.g. val_bpb). One agent proposes one change at a time, runs training in the user's env, keeps it only if the metric improves (advancing a git branch) else reverts, and loops forever until the human interrupts. A faithful adaptation of Karpathy's autoresearch. Not for the analysis-first variant that profiles before editing (that is ml-autoresearch), and not for a budgeted, plateau-stopping refactor. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-karpathy\",\"task\":\"Install karpathy\",\"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 \"karpathy\" from https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/karpathy 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: Use when the user wants the LLM to do its own ML research: a fully-autonomous loop that hacks the training code, runs it, and keeps changes that lower a single scalar metric (e.g. val_bpb). One agent proposes one change at a time, runs training in the user's env, keeps it only if the metric improves (advancing a git branch) else reverts, and loops forever until the human interrupts. A faithful adaptation of Karpathy's autoresearch. Not for the analysis-first variant that profiles before editing (that is ml-autoresearch), and not for a budgeted, plateau-stopping refactor. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"gaasher-karpathy\",\"task\":\"Install karpathy\",\"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/gaasher-karpathy/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/gaasher-karpathy"},"trust":{"score":73,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"163 GitHub stars","repoActivity":"163 stars, 19 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/karpathy","install":"npx skills add gaasher/Agent-Loop-Skills --skill karpathy","installSafety":"standard package or runtime install path","permissionSurface":"secrets or environment access","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":["research","agent-skill"],"known_risks":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":76,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"experimental","label":"Experimental","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Test manually in an isolated workspace and compare against safer alternatives."},"quality":{"score":63,"label":"Promising"},"supply":{"track":"Research and knowledge work","scenario":"Research agents","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","High-risk permission hints: Secrets or environment access","Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use karpathy","recommended_action":"Test manually in an isolated workspace and compare against safer alternatives.","install_policy":"review","minimum_review_before_use":["Trust: 73/100 Strong shortlist","Audit: 76/100 Needs review","Safety: 52/100 Avoid automatic install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"gaasher-karpathy (karpathy)","install_command":"npx skills add gaasher/Agent-Loop-Skills --skill karpathy","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":"gaasher-karpathy","task":"Use karpathy","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/gaasher-karpathy","api":"https://www.openagentskill.com/api/agent/skills/gaasher-karpathy","audit":"https://www.openagentskill.com/skills/gaasher-karpathy/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=gaasher-karpathy&task=Use%20karpathy&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20karpathy&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20karpathy&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/gaasher-karpathy/install","manifest":"https://www.openagentskill.com/api/registry/manifest/gaasher-karpathy"}},"use_cases":[{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"}],"urls":{"web":"https://www.openagentskill.com/skills/gaasher-karpathy","api":"https://www.openagentskill.com/api/agent/skills/gaasher-karpathy","install_api":"https://www.openagentskill.com/api/skills/gaasher-karpathy/install","audit":"https://www.openagentskill.com/skills/gaasher-karpathy/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=gaasher-karpathy&task=Use%20karpathy&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/gaasher-karpathy?metric=audit","repository":"https://github.com/gaasher/Agent-Loop-Skills/tree/main/loops/karpathy"}},{"rank":5,"match_score":30,"raw_match_score":83.8,"semantic_relevance":30,"registry_source":{"kind":"live_registry","live":true,"auto_install_eligible":true,"warning":null},"skill":{"slug":"k-dense-ai-andrej-karpathy","name":"andrej-karpathy","description":"Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs). Use this skill whenever you are helping the user build neural networks from scratch, debug deep learning pipelines, evaluate AI agent workflows, design LLM apps, or navigate the transition to Software 3.0 (vibe coding). It is highly relevant for pedagogy (untangling complex knowledge), assessing AI capabilities vs. limitations (jagged intelligence, tokenization limits), and architectural decisions (end-to-end optimization vs. complex pipelines). Reach for this whenever discussing LLM training, autonomous systems, or AI-assisted coding.","category":"design-creative","github_stars":122,"created_at":"2026-09-06T23:10:36.590761+00:00","updated_at":"2026-08-18T22:59:08+00:00","repository":"https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy","github_repo":"K-Dense-AI/mimeographs","source_version":{"version":"1.0.0","commit_sha":"a38f5fcad0853be3e98a6cd95d8e6bf8c66f7c7b","content_hash":"64a25ee376be2594548b1ac44446911ecbc346d1cf907fabcd01754e580ca018","ref":"main","path":"mimeographs/andrej-karpathy/SKILL.md","sync_status":"current"}},"recommendation_reasons":["Matches task terms: karpathy","Install handoff is available","Repository freshness signal is available","Registry match score 30"],"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":"coding-agents","title":"Coding agents"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"testing-qa","title":"Testing and QA"}]},"applicableAgents":["Claude Code","OpenAI Agents","CLI","Codex","Cursor"],"install":{"ready":true,"command":"npx skills add K-Dense-AI/mimeographs --skill andrej-karpathy","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":122,"starsLabel":"122","forks":18,"license":"MIT","qualityScore":67,"trustScore":69,"auditScore":78},"maintenance":{"status":"fresh","label":"20d since push","daysSincePush":20,"lastPushedAt":"2026-08-18T22:59:08+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","The skill does not document explicit limitations or safe operating boundaries, though it is a mental-model/persona skill rather than a tool-executing workflow.","The submission includes internal `_workspace` artifacts (critique files, generated JSON) that are not part of the skill itself and add clutter.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata"]},"coverageTags":["Design","Design and creative","design-creative","agent-skill"]},"quality":{"score":67,"tier":"promising","label":"Promising","summary":"Useful candidate, but compare it with alternatives before adopting.","signals":[{"label":"GitHub stars","value":"122","tone":"neutral"},{"label":"Freshness","value":"20d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory."]},"trust":{"version":"trust-score-v4","score":69,"tier":"review","label":"Manual review","summary":"Potentially useful, but at least one trust signal needs human inspection.","recommendedAction":"Inspect the repository, license, and recent activity before connecting it to agent workflows.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"122 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"122 stars, 18 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"20d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"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 K-Dense-AI/mimeographs --skill andrej-karpathy"},{"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/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","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":"122 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"122 stars, 18 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"20d 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 K-Dense-AI/mimeographs --skill andrej-karpathy"},{"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/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy"},{"status":"info","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":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"122 GitHub stars","repoActivity":"122 stars, 18 forks","lastPushed":"20d since push","license":"MIT","repository":"https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy","install":"npx skills add K-Dense-AI/mimeographs --skill andrej-karpathy","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 K-Dense-AI/mimeographs --skill andrej-karpathy","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","20d since push"]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["design-creative","agent-skill"],"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":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"trust_v5":{"version":"trust-score-v5","score":61,"base_score":69,"outcome_confidence":0,"tier":"review","label":"Sandbox only","summary":"Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.","recommendedAction":"Run only in a sandbox and compare close alternatives before using it for real work.","decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["61/100 Trust Score v5","69/100 Trust Score v4 baseline","Needs more real agent outcomes before unattended install","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":62,"weight":0.13,"status":"info","detail":"122 GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":57,"weight":0.08,"status":"warn","detail":"122 stars, 18 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"20d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":52,"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 K-Dense-AI/mimeographs --skill andrej-karpathy"},{"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/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy"},{"id":"review_status","label":"Review status","score":66,"weight":0.05,"status":"info","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":"122 GitHub stars"},{"status":"warn","label":"Stars/forks activity","detail":"122 stars, 18 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"20d 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 K-Dense-AI/mimeographs --skill andrej-karpathy"},{"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/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy"},{"status":"info","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","Outcome loop is ready but needs first real agent run"],"warnings":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","No real agent outcome reports yet","Human review required before unattended installation"],"evidence":{"stars":"122 GitHub stars","repoActivity":"122 stars, 18 forks","lastPushed":"20d since push","license":"MIT","repository":"https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy","install":"npx skills add K-Dense-AI/mimeographs --skill andrej-karpathy","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","agentProvenScore":0,"outcomeConfidence":"0%","installPolicy":"human_review_before_install"},"installReadiness":{"ready":true,"command":"npx skills add K-Dense-AI/mimeographs --skill andrej-karpathy","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","20d since push","Trust Score v5 requires review or sandbox-only use before install."]},"agentCompatibility":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Compare alternatives before installing."},"outcome_loop":{"version":"openagentskill-agent-outcome-v4","required_after_install":true,"endpoint":"/api/agent/outcome","method":"POST","event_id_source":"feedback.event_id, install_receipt.resolve_event_id, or decision_packet.outcome_feedback.event_id","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"required_fields":["event_id","skill_slug","task"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url","time_to_useful_ms","source_version"],"ranking_inputs_updated":["Trust Score v5 outcome confidence","Agent Proven Score","Resolve ranking task-fit evidence","Skill detail machine-readable metadata","Outcome leaderboard"]},"agent_contract":{"suited_tasks":["design-creative","agent-skill"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"install_command":"npx skills add K-Dense-AI/mimeographs --skill andrej-karpathy","trust_score":61,"trust_version":"trust-score-v5","risk_level":"medium","do_not_use_when":["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"],"before_install":["Read the audit page and machine-readable metadata.","Confirm the install command, license, and permission surface fit the workspace.","Get explicit human approval or choose an alternative before installing."],"after_run":["Report the outcome to /api/agent/outcome using the resolve event id.","Include output_quality, workspace, human_review_required, and evidence_url when available.","Re-resolve before broad production rollout."]},"bestFor":["design-creative","agent-skill"],"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":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"backward_compatible":{"trust_score_v4":{"version":"trust-score-v4","score":69,"tier":"review","label":"Manual review","summary":"Potentially useful, but at least one trust signal needs human inspection."}}},"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":{"audit_score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","The skill does not document explicit limitations or safe operating boundaries, though it is a mental-model/persona skill rather than a tool-executing workflow.","The submission includes internal `_workspace` artifacts (critique files, generated JSON) that are not part of the skill itself and add clutter.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata"]},"safety":{"score":66,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","66/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory."],"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":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","66/100 agent safety score"]},"decision":{"readiness_score":66,"readiness_label":"Prototype first","headline":"Fallback candidate for Coding agents","role":"Fallback candidate","best_for":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects"],"risks":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","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."]},"install_plan":{"target":"codex","label":"Codex install prompt","command":"npx skills add K-Dense-AI/mimeographs --skill andrej-karpathy","value":"Install the \"andrej-karpathy\" agent skill from https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy. 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: Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs). Use this skill whenever you are helping the user build neural networks from scratch, debug deep learning pipelines, evaluate AI agent workflows, design LLM apps, or navigate the transition to Software 3.0 (vibe coding). It is highly relevant for pedagogy (untangling complex knowledge), assessing AI capabilities vs. limitations (jagged intelligence, tokenization limits), and architectural decisions (end-to-end optimization vs. complex pipelines). Reach for this whenever discussing LLM training, autonomous systems, or AI-assisted coding. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"k-dense-ai-andrej-karpathy\",\"task\":\"Install andrej-karpathy\",\"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.","kind":"agent-prompt","steps":["Review andrej-karpathy trust and audit signals before installing.","Send the install prompt to the target agent.","Install in a sandbox or low-risk workspace first.","Pin the repository source and re-check the audit before production use."],"targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add k-dense-ai-andrej-karpathy","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 \"andrej-karpathy\" agent skill from https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy. 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: Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs). Use this skill whenever you are helping the user build neural networks from scratch, debug deep learning pipelines, evaluate AI agent workflows, design LLM apps, or navigate the transition to Software 3.0 (vibe coding). It is highly relevant for pedagogy (untangling complex knowledge), assessing AI capabilities vs. limitations (jagged intelligence, tokenization limits), and architectural decisions (end-to-end optimization vs. complex pipelines). Reach for this whenever discussing LLM training, autonomous systems, or AI-assisted coding. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"k-dense-ai-andrej-karpathy\",\"task\":\"Install andrej-karpathy\",\"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 \"andrej-karpathy\" as a Claude Code skill from https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy. 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: Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs). Use this skill whenever you are helping the user build neural networks from scratch, debug deep learning pipelines, evaluate AI agent workflows, design LLM apps, or navigate the transition to Software 3.0 (vibe coding). It is highly relevant for pedagogy (untangling complex knowledge), assessing AI capabilities vs. limitations (jagged intelligence, tokenization limits), and architectural decisions (end-to-end optimization vs. complex pipelines). Reach for this whenever discussing LLM training, autonomous systems, or AI-assisted coding. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"k-dense-ai-andrej-karpathy\",\"task\":\"Install andrej-karpathy\",\"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 \"andrej-karpathy\" from https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy 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: Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs). Use this skill whenever you are helping the user build neural networks from scratch, debug deep learning pipelines, evaluate AI agent workflows, design LLM apps, or navigate the transition to Software 3.0 (vibe coding). It is highly relevant for pedagogy (untangling complex knowledge), assessing AI capabilities vs. limitations (jagged intelligence, tokenization limits), and architectural decisions (end-to-end optimization vs. complex pipelines). Reach for this whenever discussing LLM training, autonomous systems, or AI-assisted coding. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"k-dense-ai-andrej-karpathy\",\"task\":\"Install andrej-karpathy\",\"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"}]},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"k-dense-ai-andrej-karpathy","name":"andrej-karpathy","description":"Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs). Use this skill whenever you are helping the user build neural networks from scratch, debug deep learning pipelines, evaluate AI agent workflows, design LLM apps, or navigate the transition to Software 3.0 (vibe coding). It is highly relevant for pedagogy (untangling complex knowledge), assessing AI capabilities vs. limitations (jagged intelligence, tokenization limits), and architectural decisions (end-to-end optimization vs. complex pipelines). Reach for this whenever discussing LLM training, autonomous systems, or AI-assisted coding.","category":"design-creative","url":"https://www.openagentskill.com/skills/k-dense-ai-andrej-karpathy","repository":"https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy","github_repo":"K-Dense-AI/mimeographs"},"suited_tasks":["Coding agents workflows","Claude Code teams","builders willing to evaluate younger projects","Inspect source files","Explain architecture","Patch bugs and verify changes","Navigate pages","Click and type safely"],"suited_agents":["Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add K-Dense-AI/mimeographs --skill andrej-karpathy","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz add k-dense-ai-andrej-karpathy"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"andrej-karpathy\" agent skill from https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy. 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: Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs). Use this skill whenever you are helping the user build neural networks from scratch, debug deep learning pipelines, evaluate AI agent workflows, design LLM apps, or navigate the transition to Software 3.0 (vibe coding). It is highly relevant for pedagogy (untangling complex knowledge), assessing AI capabilities vs. limitations (jagged intelligence, tokenization limits), and architectural decisions (end-to-end optimization vs. complex pipelines). Reach for this whenever discussing LLM training, autonomous systems, or AI-assisted coding. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"k-dense-ai-andrej-karpathy\",\"task\":\"Install andrej-karpathy\",\"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 \"andrej-karpathy\" as a Claude Code skill from https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy. 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: Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs). Use this skill whenever you are helping the user build neural networks from scratch, debug deep learning pipelines, evaluate AI agent workflows, design LLM apps, or navigate the transition to Software 3.0 (vibe coding). It is highly relevant for pedagogy (untangling complex knowledge), assessing AI capabilities vs. limitations (jagged intelligence, tokenization limits), and architectural decisions (end-to-end optimization vs. complex pipelines). Reach for this whenever discussing LLM training, autonomous systems, or AI-assisted coding. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"k-dense-ai-andrej-karpathy\",\"task\":\"Install andrej-karpathy\",\"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 \"andrej-karpathy\" from https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy 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: Applies the mental models and frameworks of Andrej Karpathy (deep learning, former Director of AI at Tesla, founding member of OpenAI, Eureka Labs). Use this skill whenever you are helping the user build neural networks from scratch, debug deep learning pipelines, evaluate AI agent workflows, design LLM apps, or navigate the transition to Software 3.0 (vibe coding). It is highly relevant for pedagogy (untangling complex knowledge), assessing AI capabilities vs. limitations (jagged intelligence, tokenization limits), and architectural decisions (end-to-end optimization vs. complex pipelines). Reach for this whenever discussing LLM training, autonomous systems, or AI-assisted coding. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"k-dense-ai-andrej-karpathy\",\"task\":\"Install andrej-karpathy\",\"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/k-dense-ai-andrej-karpathy/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/k-dense-ai-andrej-karpathy"},"trust":{"score":69,"label":"Manual review","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"122 GitHub stars","repoActivity":"122 stars, 18 forks","lastPushed":"20d since push","license":"MIT","repository":"https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy","install":"npx skills add K-Dense-AI/mimeographs --skill andrej-karpathy","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":["design-creative","agent-skill"],"known_risks":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":78,"risk_level":"needs_review","risk_label":"Needs review","warnings":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","The skill does not document explicit limitations or safe operating boundaries, though it is a mental-model/persona skill rather than a tool-executing workflow.","The submission includes internal `_workspace` artifacts (critique files, generated JSON) that are not part of the skill itself and add clutter.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":67,"label":"Promising"},"supply":{"track":"Design and creative production","scenario":"Design and creative","maintenance":"20d since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","production agents without a repository review","SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","No OpenAgentSkill engagement data yet","The skill does not document explicit limitations or safe operating boundaries, though it is a mental-model/persona skill rather than a tool-executing workflow.","The submission includes internal `_workspace` artifacts (critique files, generated JSON) that are not part of the skill itself and add clutter.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata"],"agent_contract":{"task_input":"Use karpathy","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 69/100 Manual review","Audit: 78/100 Needs review","Safety: 66/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"k-dense-ai-andrej-karpathy (andrej-karpathy)","install_command":"npx skills add K-Dense-AI/mimeographs --skill andrej-karpathy","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":"k-dense-ai-andrej-karpathy","task":"Use karpathy","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/k-dense-ai-andrej-karpathy","api":"https://www.openagentskill.com/api/agent/skills/k-dense-ai-andrej-karpathy","audit":"https://www.openagentskill.com/skills/k-dense-ai-andrej-karpathy/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=k-dense-ai-andrej-karpathy&task=Use%20karpathy&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20karpathy&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20karpathy&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/k-dense-ai-andrej-karpathy/install","manifest":"https://www.openagentskill.com/api/registry/manifest/k-dense-ai-andrej-karpathy"}},"use_cases":[{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"testing-qa","title":"Testing and QA","url":"https://www.openagentskill.com/use-cases/testing-qa"}],"urls":{"web":"https://www.openagentskill.com/skills/k-dense-ai-andrej-karpathy","api":"https://www.openagentskill.com/api/agent/skills/k-dense-ai-andrej-karpathy","install_api":"https://www.openagentskill.com/api/skills/k-dense-ai-andrej-karpathy/install","audit":"https://www.openagentskill.com/skills/k-dense-ai-andrej-karpathy/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=k-dense-ai-andrej-karpathy&task=Use%20karpathy&max_risk=medium","badge":"https://www.openagentskill.com/api/badge/k-dense-ai-andrej-karpathy?metric=audit","repository":"https://github.com/K-Dense-AI/mimeographs/tree/main/mimeographs/andrej-karpathy"}}],"blocked_candidates":[],"agent_workflow":{"mode":"resolve_review_install","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","selected_skill":{"slug":"multica-ai-andrej-karpathy-skills","name":"Andrej Karpathy Skills","url":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills","repository":"https://github.com/multica-ai/andrej-karpathy-skills"},"install":{"target":"codex","label":"Codex install prompt","kind":"agent-prompt","command":"npx skills add multica-ai/andrej-karpathy-skills","value":"Install the \"Andrej Karpathy Skills\" agent skill from https://github.com/multica-ai/andrej-karpathy-skills. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"multica-ai-andrej-karpathy-skills\",\"task\":\"Install Andrej Karpathy Skills\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","api":"https://www.openagentskill.com/api/skills/multica-ai-andrej-karpathy-skills/install"},"copy_paste_prompt":"Task: Use karpathy\nUse Andrej Karpathy Skills from https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills.\nReview the audit first: https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills/audit\nReview the eval first: https://www.openagentskill.com/api/agent/evals?slug=multica-ai-andrej-karpathy-skills&task=Use%20karpathy&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/multica-ai-andrej-karpathy-skills/install\nInstall command: npx skills add multica-ai/andrej-karpathy-skills\nIf audit or policy warnings look unsafe for this workspace, use one of the alternatives instead.","api_sequence":[{"step":1,"label":"Resolve task","method":"GET","url":"https://www.openagentskill.com/api/agent/resolve?task=Use%20karpathy&agent=codex&max_risk=medium"},{"step":2,"label":"Fetch pre-install eval","method":"GET","url":"https://www.openagentskill.com/api/agent/evals?slug=multica-ai-andrej-karpathy-skills&task=Use%20karpathy&max_risk=medium"},{"step":3,"label":"Fetch selected skill profile","method":"GET","url":"https://www.openagentskill.com/api/agent/skills/multica-ai-andrej-karpathy-skills"},{"step":4,"label":"Fetch install handoff","method":"GET","url":"https://www.openagentskill.com/api/skills/multica-ai-andrej-karpathy-skills/install"},{"step":5,"label":"Review audit","method":"GET","url":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills/audit"},{"step":6,"label":"Report outcome","method":"POST","url":"https://www.openagentskill.com/api/agent/outcome","body":{"event_id":"resolve_013e884c-6dad-4779-beeb-bf280901a319","skill_slug":"multica-ai-andrej-karpathy-skills","task":"Use karpathy","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":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}}}],"review_checklist":["Safety tier: Reviewed","Safety score: 71/100 Review before install","Audit score: 87/100 Safe to try","Trust score: 75/100 Sandbox only","Readiness: 100/100 Production-ready","License is unclear","License is unclear","Documentation summary is thin","License clarity: Unknown"],"fallback_strategy":[{"slug":"astro-han-karpathy-llm-wiki","name":"Karpathy Llm Wiki","reason":"Matches task terms: karpathy","url":"https://www.openagentskill.com/skills/astro-han-karpathy-llm-wiki","install_api":"https://www.openagentskill.com/api/skills/astro-han-karpathy-llm-wiki/install"},{"slug":"kbwen-karpathy-principles","name":"karpathy-principles","reason":"Matches task terms: karpathy","url":"https://www.openagentskill.com/skills/kbwen-karpathy-principles","install_api":"https://www.openagentskill.com/api/skills/kbwen-karpathy-principles/install"},{"slug":"gaasher-karpathy","name":"karpathy","reason":"Matches task terms: karpathy","url":"https://www.openagentskill.com/skills/gaasher-karpathy","install_api":"https://www.openagentskill.com/api/skills/gaasher-karpathy/install"}],"expected_agent_output":{"selected_skill":"slug and name","install_command":"command or agent prompt used","risk_summary":"audit, trust, and policy notes","next_step":"what the agent will do after install","outcome_event_id":"resolve_013e884c-6dad-4779-beeb-bf280901a319"}},"agent_handoff":{"version":"openagentskill-agent-handoff-v1","mode":"resolve_compare_review_install","task":"Use karpathy","agent":"codex","selected_skill":{"slug":"multica-ai-andrej-karpathy-skills","name":"Andrej Karpathy Skills","url":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills","api_url":"https://www.openagentskill.com/api/agent/skills/multica-ai-andrej-karpathy-skills","audit_url":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills/audit","eval_url":"https://www.openagentskill.com/api/agent/evals?slug=multica-ai-andrej-karpathy-skills&task=Use%20karpathy&max_risk=medium","repository":"https://github.com/multica-ai/andrej-karpathy-skills"},"install_plan":{"command":"npx skills add multica-ai/andrej-karpathy-skills","target":"codex","label":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Andrej Karpathy Skills\" agent skill from https://github.com/multica-ai/andrej-karpathy-skills. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. After the install attempt, report the result to https://www.openagentskill.com/api/agent/outcome with POST JSON {\"event_id\":\"install_<unique-id>\",\"skill_slug\":\"multica-ai-andrej-karpathy-skills\",\"task\":\"Install Andrej Karpathy Skills\",\"agent\":\"codex\",\"outcome\":\"success\",\"install_used\":true}. Replace event_id with a unique value and outcome with success or failed. Report success only after the skill is installed and a minimal verification passes.","install_api":"https://www.openagentskill.com/api/skills/multica-ai-andrej-karpathy-skills/install","auto_install_allowed":false,"human_review_required":true,"policy":"review"},"api_sequence":[{"step":1,"label":"Resolve task","method":"GET","url":"https://www.openagentskill.com/api/agent/resolve?task=Use%20karpathy&agent=codex&max_risk=medium"},{"step":2,"label":"Fetch pre-install eval","method":"GET","url":"https://www.openagentskill.com/api/agent/evals?slug=multica-ai-andrej-karpathy-skills&task=Use%20karpathy&max_risk=medium"},{"step":3,"label":"Fetch selected skill profile","method":"GET","url":"https://www.openagentskill.com/api/agent/skills/multica-ai-andrej-karpathy-skills"},{"step":4,"label":"Fetch install handoff","method":"GET","url":"https://www.openagentskill.com/api/skills/multica-ai-andrej-karpathy-skills/install"},{"step":5,"label":"Review audit","method":"GET","url":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills/audit"},{"step":6,"label":"Report outcome","method":"POST","url":"https://www.openagentskill.com/api/agent/outcome","body":{"event_id":"resolve_013e884c-6dad-4779-beeb-bf280901a319","skill_slug":"multica-ai-andrej-karpathy-skills","task":"Use karpathy","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":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}}}],"platform_templates":[{"id":"codex","name":"Codex","surface":"Coding agent / local workspace","copy_prompt":"Task: Use karpathy\nSelected skill: Andrej Karpathy Skills (multica-ai-andrej-karpathy-skills)\nSkill URL: https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills\nAudit URL: https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills/audit\nEval URL: https://www.openagentskill.com/api/agent/evals?slug=multica-ai-andrej-karpathy-skills&task=Use%20karpathy&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/multica-ai-andrej-karpathy-skills/install\nInstall command: npx skills add multica-ai/andrej-karpathy-skills\nInstall policy: Human review is required before install.\nOutcome feedback: use install_receipt.outcome_feedback.event_id or feedback.event_id from the Resolve API and report the result to /api/agent/outcome after one narrow run. Include outcome, install_used, task_success, output_quality, workspace, error_type, and human_review_required when known.\n\nBefore installing:\n1. Read the audit and eval result.\n2. Report risk notes and files or commands that will be touched.\n3. Install only in a sandbox or low-risk workspace first.\n4. If risk is unacceptable, use an alternative.\n\nAlternatives:\n- Karpathy Llm Wiki (astro-han-karpathy-llm-wiki): https://www.openagentskill.com/skills/astro-han-karpathy-llm-wiki\n- karpathy-principles (kbwen-karpathy-principles): https://www.openagentskill.com/skills/kbwen-karpathy-principles\n- karpathy (gaasher-karpathy): https://www.openagentskill.com/skills/gaasher-karpathy\n\nExpected Codex output:\n- selected_skill\n- install_command\n- risk_summary\n- outcome_event_id\n- alternatives\n- files_or_commands_to_touch\n- next_action"},{"id":"claude-code","name":"Claude Code","surface":"Claude Code skill workflow","copy_prompt":"Task: Use karpathy\nSelected skill: Andrej Karpathy Skills (multica-ai-andrej-karpathy-skills)\nSkill URL: https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills\nAudit URL: https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills/audit\nEval URL: https://www.openagentskill.com/api/agent/evals?slug=multica-ai-andrej-karpathy-skills&task=Use%20karpathy&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/multica-ai-andrej-karpathy-skills/install\nInstall command: npx skills add multica-ai/andrej-karpathy-skills\nInstall policy: Human review is required before install.\nOutcome feedback: use install_receipt.outcome_feedback.event_id or feedback.event_id from the Resolve API and report the result to /api/agent/outcome after one narrow run. Include outcome, install_used, task_success, output_quality, workspace, error_type, and human_review_required when known.\n\nBefore installing:\n1. Read the audit and eval result.\n2. Report risk notes and files or commands that will be touched.\n3. Install only in a sandbox or low-risk workspace first.\n4. If risk is unacceptable, use an alternative.\n\nAlternatives:\n- Karpathy Llm Wiki (astro-han-karpathy-llm-wiki): https://www.openagentskill.com/skills/astro-han-karpathy-llm-wiki\n- karpathy-principles (kbwen-karpathy-principles): https://www.openagentskill.com/skills/kbwen-karpathy-principles\n- karpathy (gaasher-karpathy): https://www.openagentskill.com/skills/gaasher-karpathy\n\nExpected Claude Code output:\n- selected_skill\n- skill_files_or_instructions\n- install_prompt\n- risk_summary\n- outcome_event_id\n- activation_steps\n- fallback_skill"},{"id":"cursor","name":"Cursor","surface":"Cursor rules / agent instructions","copy_prompt":"Task: Use karpathy\nSelected skill: Andrej Karpathy Skills (multica-ai-andrej-karpathy-skills)\nSkill URL: https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills\nAudit URL: https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills/audit\nEval URL: https://www.openagentskill.com/api/agent/evals?slug=multica-ai-andrej-karpathy-skills&task=Use%20karpathy&max_risk=medium\nInstall handoff: https://www.openagentskill.com/api/skills/multica-ai-andrej-karpathy-skills/install\nInstall command: npx skills add multica-ai/andrej-karpathy-skills\nInstall policy: Human review is required before install.\nOutcome feedback: use install_receipt.outcome_feedback.event_id or feedback.event_id from the Resolve API and report the result to /api/agent/outcome after one narrow run. Include outcome, install_used, task_success, output_quality, workspace, error_type, and human_review_required when known.\n\nBefore installing:\n1. Read the audit and eval result.\n2. Report risk notes and files or commands that will be touched.\n3. Install only in a sandbox or low-risk workspace first.\n4. If risk is unacceptable, use an alternative.\n\nAlternatives:\n- Karpathy Llm Wiki (astro-han-karpathy-llm-wiki): https://www.openagentskill.com/skills/astro-han-karpathy-llm-wiki\n- karpathy-principles (kbwen-karpathy-principles): https://www.openagentskill.com/skills/kbwen-karpathy-principles\n- karpathy (gaasher-karpathy): https://www.openagentskill.com/skills/gaasher-karpathy\n\nExpected Cursor output:\n- selected_skill\n- cursor_rule_or_prompt\n- install_command\n- risk_summary\n- outcome_event_id\n- when_to_use\n- when_not_to_use"}],"review_checklist":["Safety tier: Reviewed","Safety score: 71/100 Review before install","Audit score: 87/100 Safe to try","Trust score: 75/100 Sandbox only","Readiness: 100/100 Production-ready","License is unclear","License is unclear","Documentation summary is thin","License clarity: Unknown"],"expected_output":{"selected_skill":"slug and name","install_command":"command or agent prompt used","risk_summary":"audit, trust, and policy notes","next_step":"what the agent will do after install","outcome_event_id":"resolve_013e884c-6dad-4779-beeb-bf280901a319"},"feedback":{"event_id":"resolve_013e884c-6dad-4779-beeb-bf280901a319","outcome_api":"https://www.openagentskill.com/api/agent/outcome","cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_013e884c-6dad-4779-beeb-bf280901a319\" --skill \"multica-ai-andrej-karpathy-skills\" --task \"Use karpathy\" --agent \"codex\" --outcome success","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"]},"blocked_actions":["Do not install when safety_gate.blocked is true.","Do not install when the audit or eval reports unacceptable workspace risk.","Do not execute shell commands, access secrets, or call external services without user approval.","Do not keep the skill as an always-on instruction if it only fits a narrow task."]},"policy_decision":{"status":"human_review_required","summary":"Review the audit page, then allow agent install in a sandboxed workflow."},"agent_decision":{"input_task":"Use karpathy","recommended_skill":{"slug":"multica-ai-andrej-karpathy-skills","name":"Andrej Karpathy Skills","url":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills","audit_url":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills/audit","repository":"https://github.com/multica-ai/andrej-karpathy-skills","safety_tier":"Reviewed","auto_install_policy":"review"},"alternative_skills":[{"slug":"astro-han-karpathy-llm-wiki","name":"Karpathy Llm Wiki","url":"https://www.openagentskill.com/skills/astro-han-karpathy-llm-wiki","install_command":"npx skills add Astro-Han/karpathy-llm-wiki","why_consider":"Matches task terms: karpathy","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"78/100 Review before install","trust":"88/100 Production candidate","notes":["Documentation summary is thin"]}},{"slug":"kbwen-karpathy-principles","name":"karpathy-principles","url":"https://www.openagentskill.com/skills/kbwen-karpathy-principles","install_command":"npx skills add KbWen/agentic-os --skill karpathy-principles","why_consider":"Matches task terms: karpathy","risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"68/100 Review before install","trust":"78/100 Strong shortlist","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 155 stars, 35 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},{"slug":"gaasher-karpathy","name":"karpathy","url":"https://www.openagentskill.com/skills/gaasher-karpathy","install_command":"npx skills add gaasher/Agent-Loop-Skills --skill karpathy","why_consider":"Matches task terms: karpathy","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"52/100 Avoid automatic install","trust":"73/100 Strong shortlist","notes":["High-risk permission hints: Secrets or environment access","Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}}],"install_command":"npx skills add multica-ai/andrej-karpathy-skills","install_target":"Codex install prompt","why_recommended":["Matches task terms: karpathy","Strong GitHub adoption: 175,191 stars","Quality score 83/100","Install handoff is available","Repository freshness signal is available","Primary pick for Coding agents"],"risk_summary":{"level":"Safe to try","safety_tier":"Reviewed","safety":"71/100 Review before install","trust":"88/100 Production candidate","notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","action":"Review the audit page, then allow agent install in a sandboxed workflow."},"feedback":{"event_id":"resolve_013e884c-6dad-4779-beeb-bf280901a319","outcome_api":"https://www.openagentskill.com/api/agent/outcome","cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_013e884c-6dad-4779-beeb-bf280901a319\" --skill \"multica-ai-andrej-karpathy-skills\" --task \"Use karpathy\" --agent \"codex\" --outcome success","contract":{"version":"openagentskill-agent-feedback-loop-v3","status":"active","purpose":"Report the result of one resolved skill run so Trust Score v5 and future Resolve rankings learn from real use.","event_id":"resolve_013e884c-6dad-4779-beeb-bf280901a319","selected_skill_slug":"multica-ai-andrej-karpathy-skills","selected_skill_name":"Andrej Karpathy Skills","endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","idempotency":"Retrying the same event_id updates the previous outcome.","dry_run":{"supported":true,"instruction":"Set dry_run=true to validate a payload before wiring a new agent integration."},"expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"error_types":["install_failed","runtime_error","not_relevant","permission_blocked","risk_blocked","setup_required","low_quality_output","missing_dependency","timeout","other"],"workspaces":["sandbox","local","ci","production","unknown"],"quality_fields":["task_success","output_quality","error_type","human_review_required","used_in_production","workspace","evidence_url"],"payload_template":{"event_id":"resolve_013e884c-6dad-4779-beeb-bf280901a319","skill_slug":"multica-ai-andrej-karpathy-skills","task":"Use karpathy","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":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_013e884c-6dad-4779-beeb-bf280901a319\" --skill \"multica-ai-andrej-karpathy-skills\" --task \"Use karpathy\" --agent \"codex\" --outcome success","ranking_inputs_updated":["Trust Score v5 outcome confidence","Resolve ranking outcome evidence","Skill detail outcome signal block","Outcome leaderboard"]}},"agent_next_steps":["Read the audit URL before installing.","Ask for human approval before installing.","Use install command: npx skills add multica-ai/andrej-karpathy-skills","After one narrow task, report the outcome with: npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_013e884c-6dad-4779-beeb-bf280901a319\" --skill \"multica-ai-andrej-karpathy-skills\" --task \"Use karpathy\" --agent \"codex\" --outcome success","Summarize output, warnings, files touched, and whether setup or human review was required."]},"decision_packet":{"version":"openagentskill-agent-decision-packet-v1","task":"Use karpathy","agent":"codex","selected_skill":{"slug":"multica-ai-andrej-karpathy-skills","name":"Andrej Karpathy Skills","url":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills","api_url":"https://www.openagentskill.com/api/agent/skills/multica-ai-andrej-karpathy-skills","audit_url":"https://www.openagentskill.com/skills/multica-ai-andrej-karpathy-skills/audit","repository":"https://github.com/multica-ai/andrej-karpathy-skills","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"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":["Claude Code","Codex","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add multica-ai/andrej-karpathy-skills","target":"codex","label":"Codex install prompt","policy":"review","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true},"trust":{"score":75,"label":"Sandbox only","version":"trust-score-v5","base_score":88,"outcome_confidence":0.65,"decision":{"install_policy":"human_review_before_install","auto_install_allowed":false,"human_review_required":true,"sandbox_first":true,"agent_action":"Compare alternatives before installing.","reasoning":["75/100 Trust Score v5","88/100 Trust Score v4 baseline","Early agent signal: 100% success from 5 agent outcomes; outcome confidence 65%","Install path is available","Review before production"],"review_required_when":["The workspace contains production secrets, payments, private customer data, or irreversible actions.","The install command requests shell, network, credential, database, or broad filesystem access.","Outcome evidence is missing, recently failed, or required human review.","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"]},"dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"status":"pass","detail":"175K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"status":"pass","detail":"175K stars, 18K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"status":"info","detail":"5mo since push"},{"id":"license","label":"License clarity","score":42,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"status":"pass","detail":"npx skills add multica-ai/andrej-karpathy-skills"},{"id":"install_safety","label":"Install command safety","score":92,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":86,"status":"pass","detail":"filesystem or document access"},{"id":"repository","label":"Repository evidence","score":86,"status":"pass","detail":"https://github.com/multica-ai/andrej-karpathy-skills"},{"id":"review_status","label":"Review status","score":88,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":63,"status":"info","detail":"Early agent signal: 100% success from 5 agent outcomes"}]},"risk":{"level":"Safe to try","audit_label":"Safe to try","safety":"71/100 Review before install","trust":"88/100 Production candidate","safety_tier":"Reviewed","notes":["License is unclear","Documentation summary is thin","License clarity: Unknown"],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","License clarity: Unknown","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"minimum_review_before_use":["Trust: 88/100 Production candidate","Audit: 87/100 Safe to try","Safety: 71/100 Review before install","Review repository, license, install command, and permission surface before production use."]},"alternatives":[{"slug":"astro-han-karpathy-llm-wiki","name":"Karpathy Llm Wiki","url":"https://www.openagentskill.com/skills/astro-han-karpathy-llm-wiki","install_command":"npx skills add Astro-Han/karpathy-llm-wiki","trust_score":88,"audit_score":90,"safety_score":78,"why_consider":"Matches task terms: karpathy","risk":{"level":"Safe to try","safety_tier":"Reviewed","safety":"78/100 Review before install","trust":"88/100 Production candidate","notes":["Documentation summary is thin"]}},{"slug":"kbwen-karpathy-principles","name":"karpathy-principles","url":"https://www.openagentskill.com/skills/kbwen-karpathy-principles","install_command":"npx skills add KbWen/agentic-os --skill karpathy-principles","trust_score":78,"audit_score":80,"safety_score":68,"why_consider":"Matches task terms: karpathy","risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"68/100 Review before install","trust":"78/100 Strong shortlist","notes":["Quality score needs review","Documentation summary is thin","Stars/forks activity: 155 stars, 35 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},{"slug":"gaasher-karpathy","name":"karpathy","url":"https://www.openagentskill.com/skills/gaasher-karpathy","install_command":"npx skills add gaasher/Agent-Loop-Skills --skill karpathy","trust_score":73,"audit_score":76,"safety_score":52,"why_consider":"Matches task terms: karpathy","risk":{"level":"Needs review","safety_tier":"Experimental","safety":"52/100 Avoid automatic install","trust":"73/100 Strong shortlist","notes":["High-risk permission hints: Secrets or environment access","Quality score needs review","Stars/forks activity: 163 stars, 19 forks; issue activity unavailable in current metadata","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]}},{"slug":"k-dense-ai-andrej-karpathy","name":"andrej-karpathy","url":"https://www.openagentskill.com/skills/k-dense-ai-andrej-karpathy","install_command":"npx skills add K-Dense-AI/mimeographs --skill andrej-karpathy","trust_score":69,"audit_score":78,"safety_score":66,"why_consider":"Matches task terms: karpathy","risk":{"level":"Needs review","safety_tier":"Reviewed with permission notes","safety":"66/100 Review before install","trust":"69/100 Manual review","notes":["SKILL.md references `references/principles.md` and `references/mental-models.md`, but these files are not present in the submitted skill directory.","The skill does not document explicit limitations or safe operating boundaries, though it is a mental-model/persona skill rather than a tool-executing workflow.","The submission includes internal `_workspace` artifacts (critique files, generated JSON) that are not part of the skill itself and add clutter.","Quality score needs review","Stars/forks activity: 122 stars, 18 forks; issue activity unavailable in current metadata"]}}],"outcome_feedback":{"event_id":"resolve_013e884c-6dad-4779-beeb-bf280901a319","endpoint":"https://www.openagentskill.com/api/agent/outcome","method":"POST","expected_outcomes":["success","failed","not_relevant","blocked_by_risk","setup_required"],"payload_template":{"event_id":"resolve_013e884c-6dad-4779-beeb-bf280901a319","skill_slug":"multica-ai-andrej-karpathy-skills","task":"Use karpathy","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":"Solved the task in a sandbox workflow.","source_version":{"version":"1.0.0","commit_sha":null,"content_hash":null,"ref":null,"path":null,"sync_status":"untracked"}},"cli_example":"npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.3.0/openagentskill-0.3.0.tgz outcome \"resolve_013e884c-6dad-4779-beeb-bf280901a319\" --skill \"multica-ai-andrej-karpathy-skills\" --task \"Use karpathy\" --agent \"codex\" --outcome success"},"next_agent_action":"Ask for human approval or choose a safer alternative before installing.","stable_fields":["decision_packet.selected_skill","decision_packet.install","decision_packet.risk.do_not_use_when","decision_packet.alternatives","decision_packet.outcome_feedback","decision_packet.trust.decision"]},"benchmark":{"endpoint":"https://www.openagentskill.com/api/agent/evals","note":"Use the evals endpoint to regression-test recommendation quality before changing ranking logic."},"meta":{"endpoint":"/api/agent/resolve","api_version":"2.0","generated_at":"2026-09-08T13:11:02.632Z","total_skills_searched":789,"total_candidates":15,"candidate_pool":{"sort":"quality","size":789,"note":"Resolver searches the highest-quality candidate pool for low-latency agent use. Browse /skills for the full public index."},"contract":{"best_skill":"recommendation.best_skill","install":"recommendation.install","why":"recommendation.why_recommended","risk":"recommendation.risk","alternatives":"recommendation.alternatives","agent_handoff":"agent_handoff.platform_templates + agent_handoff.review_checklist","decision_packet":"decision_packet","install_receipt":"install_receipt","recommendation_lanes":"recommendation_lanes"}}}