{"query":"LLMs From Scratch","filters":{"category":null,"platform":null,"track":null,"safety":null,"include_blocked":false,"min_stars":0},"total":10,"skills":[{"rank":1,"match_score":99,"raw_match_score":855.5,"slug":"rasbt-llms-from-scratch","name":"LLMs From Scratch","description":"Implement a ChatGPT-like LLM in PyTorch from scratch, step by step","tagline":"Implement a ChatGPT-like LLM in PyTorch from scratch, step by step","category":"ml-automation","tags":["machine-learning","automation","ml-media","ai","artificial-intelligence","attention-mechanism","deep-learning","finetuning","from-scratch","generative-ai"],"author":{"name":"rasbt","verified":true,"url":"https://github.com/rasbt"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"rasbt/LLMs-from-scratch","creatorName":"rasbt","creatorUrl":"https://github.com/rasbt","sourceUrl":"https://github.com/rasbt/LLMs-from-scratch","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/rasbt-llms-from-scratch#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":97256,"forks":14876,"downloads":0,"rating":0,"review_count":0,"quality_score":78.12},"quality":{"score":100,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"97K","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Unknown","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":85,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":100,"weight":0.13,"status":"pass","detail":"97K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"97K stars, 15K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":42,"weight":0.09,"status":"warn","detail":"Unknown"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add rasbt/LLMs-from-scratch"},{"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/rasbt/LLMs-from-scratch"},{"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":"97K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"97K stars, 15K forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"warn","label":"License clarity","detail":"Unknown"},{"status":"warn","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add rasbt/LLMs-from-scratch"},{"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/rasbt/LLMs-from-scratch"},{"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":["License is unclear","Documentation summary is thin","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"97K GitHub stars","repoActivity":"97K stars, 15K forks","lastPushed":"2mo since push","license":"Unknown","repository":"https://github.com/rasbt/LLMs-from-scratch","install":"npx skills add rasbt/LLMs-from-scratch","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 rasbt/LLMs-from-scratch","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is unclear","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Jupyter Notebook","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["License is unclear","Documentation summary is thin","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["ml-automation","machine-learning","automation","ml-media","ai","artificial-intelligence"],"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","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":77,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["License is unclear","77/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["License is unclear"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["License is unclear","77/100 agent safety score"]},"supply_profile":{"track":{"slug":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Multimodal media","description":"I need my agent to process images, video, or audio and extract useful information.","useCases":[{"slug":"browser-automation","title":"Browser automation"},{"slug":"workflow-automation","title":"Workflow automation"},{"slug":"data-analysis","title":"Data analysis"}]},"applicableAgents":["OpenAI Agents","CLI","Codex","Claude Code","Cursor"],"install":{"ready":true,"command":"npx skills add rasbt/LLMs-from-scratch","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":97256,"starsLabel":"97K","forks":14876,"license":"Unknown","qualityScore":100,"trustScore":85,"auditScore":89},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":61,"lastPushedAt":"2026-06-02T14:14:19+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["License is unclear","Documentation summary is thin","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Needs review"]},"coverageTags":["Design","Multimodal media","ml-automation","machine-learning","automation","ml-media","ai","artificial-intelligence"]},"audit":{"audit_score":89,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Browser automation","role":"Primary pick","primary_fit":"Browser automation","best_for":["Browser automation workflows","OpenAI Agents teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Browser automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"rasbt-llms-from-scratch","name":"LLMs From Scratch","description":"Implement a ChatGPT-like LLM in PyTorch from scratch, step by step","category":"ml-automation","url":"https://www.openagentskill.com/skills/rasbt-llms-from-scratch","repository":"https://github.com/rasbt/LLMs-from-scratch","github_repo":"rasbt/LLMs-from-scratch"},"suited_tasks":["Browser automation workflows","OpenAI Agents teams","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Move data between tools","Transform files"],"suited_agents":["Jupyter Notebook","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add rasbt/LLMs-from-scratch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add rasbt/LLMs-from-scratch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"LLMs From Scratch\" agent skill from https://github.com/rasbt/LLMs-from-scratch. 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: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"LLMs From Scratch\" as a Claude Code skill from https://github.com/rasbt/LLMs-from-scratch. 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: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"LLMs From Scratch\" from https://github.com/rasbt/LLMs-from-scratch 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: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step"}],"handoff_url":"https://www.openagentskill.com/api/skills/rasbt-llms-from-scratch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/rasbt-llms-from-scratch"},"trust":{"score":85,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"97K GitHub stars","repoActivity":"97K stars, 15K forks","lastPushed":"2mo since push","license":"Unknown","repository":"https://github.com/rasbt/LLMs-from-scratch","install":"npx skills add rasbt/LLMs-from-scratch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["ml-automation","machine-learning","automation","ml-media","ai","artificial-intelligence"],"known_risks":["License is unclear","Documentation summary is thin","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":89,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","License clarity: Unknown","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 LLMs From Scratch in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 85/100 Strong shortlist","Audit: 89/100 Needs review","Safety: 77/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"rasbt-llms-from-scratch (LLMs From Scratch)","install_command":"npx skills add rasbt/LLMs-from-scratch","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":"rasbt-llms-from-scratch","task":"Use LLMs From Scratch in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/rasbt-llms-from-scratch","api":"https://www.openagentskill.com/api/agent/skills/rasbt-llms-from-scratch","audit":"https://www.openagentskill.com/skills/rasbt-llms-from-scratch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=rasbt-llms-from-scratch&task=Use%20LLMs%20From%20Scratch%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20LLMs%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20LLMs%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/rasbt-llms-from-scratch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/rasbt-llms-from-scratch"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"rasbt-llms-from-scratch","name":"LLMs From Scratch","description":"Implement a ChatGPT-like LLM in PyTorch from scratch, step by step","category":"ml-automation","url":"https://www.openagentskill.com/skills/rasbt-llms-from-scratch","repository":"https://github.com/rasbt/LLMs-from-scratch","github_repo":"rasbt/LLMs-from-scratch"},"suited_tasks":["Browser automation workflows","OpenAI Agents teams","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Move data between tools","Transform files"],"suited_agents":["Jupyter Notebook","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add rasbt/LLMs-from-scratch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add rasbt/LLMs-from-scratch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"LLMs From Scratch\" agent skill from https://github.com/rasbt/LLMs-from-scratch. 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: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"LLMs From Scratch\" as a Claude Code skill from https://github.com/rasbt/LLMs-from-scratch. 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: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"LLMs From Scratch\" from https://github.com/rasbt/LLMs-from-scratch 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: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step"}],"handoff_url":"https://www.openagentskill.com/api/skills/rasbt-llms-from-scratch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/rasbt-llms-from-scratch"},"trust":{"score":85,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"97K GitHub stars","repoActivity":"97K stars, 15K forks","lastPushed":"2mo since push","license":"Unknown","repository":"https://github.com/rasbt/LLMs-from-scratch","install":"npx skills add rasbt/LLMs-from-scratch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["ml-automation","machine-learning","automation","ml-media","ai","artificial-intelligence"],"known_risks":["License is unclear","Documentation summary is thin","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":89,"risk_level":"needs_review","risk_label":"Needs review","warnings":["License is unclear","Documentation summary is thin","License clarity: Unknown","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":100,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","License is unclear","Documentation summary is thin","License clarity: Unknown","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 LLMs From Scratch in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 85/100 Strong shortlist","Audit: 89/100 Needs review","Safety: 77/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"rasbt-llms-from-scratch (LLMs From Scratch)","install_command":"npx skills add rasbt/LLMs-from-scratch","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":"rasbt-llms-from-scratch","task":"Use LLMs From Scratch in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/rasbt-llms-from-scratch","api":"https://www.openagentskill.com/api/agent/skills/rasbt-llms-from-scratch","audit":"https://www.openagentskill.com/skills/rasbt-llms-from-scratch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=rasbt-llms-from-scratch&task=Use%20LLMs%20From%20Scratch%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20LLMs%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20LLMs%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/rasbt-llms-from-scratch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/rasbt-llms-from-scratch"}},"platforms":["Jupyter Notebook","Machine Learning","OpenAI Agents"],"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"slug":"data-analysis","title":"Data analysis","url":"https://www.openagentskill.com/use-cases/data-analysis"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"}],"install":"npx skills add rasbt/LLMs-from-scratch","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add rasbt/LLMs-from-scratch","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"LLMs From Scratch\" agent skill from https://github.com/rasbt/LLMs-from-scratch. 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: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step","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 \"LLMs From Scratch\" as a Claude Code skill from https://github.com/rasbt/LLMs-from-scratch. 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: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step","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 \"LLMs From Scratch\" from https://github.com/rasbt/LLMs-from-scratch 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: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/rasbt/LLMs-from-scratch","github_repo":"rasbt/LLMs-from-scratch","version":"1.0.0","license":"Unknown","updated_at":"2026-06-16T10:02:50.807705+00:00","canonical_key":"rasbt/llms-from-scratch","recommendation_reasons":["Matches task terms: llms, from, scratch","Strong GitHub adoption: 97,256 stars","Quality score 78/100","Install handoff is available","Repository freshness signal is available"],"urls":{"web":"https://www.openagentskill.com/skills/rasbt-llms-from-scratch","api":"https://www.openagentskill.com/api/agent/skills/rasbt-llms-from-scratch","install_api":"https://www.openagentskill.com/api/skills/rasbt-llms-from-scratch/install","audit":"https://www.openagentskill.com/skills/rasbt-llms-from-scratch/audit","repository":"https://github.com/rasbt/LLMs-from-scratch"}},{"rank":2,"match_score":25,"raw_match_score":218.9,"slug":"eriklindernoren-ml-from-scratch","name":"ML From Scratch","description":"Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.","tagline":"Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.","category":"ml-automation","tags":["machine-learning","automation","ml-media","data-mining","data-science","deep-learning","deep-reinforcement-learning","genetic-algorithm","machine-learning-from-scratch","python"],"author":{"name":"eriklindernoren","verified":true,"url":"https://github.com/eriklindernoren"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"eriklindernoren/ML-From-Scratch","creatorName":"eriklindernoren","creatorUrl":"https://github.com/eriklindernoren","sourceUrl":"https://github.com/eriklindernoren/ML-From-Scratch","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/eriklindernoren-ml-from-scratch#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":31915,"forks":5345,"downloads":0,"rating":0,"review_count":0,"quality_score":59.73},"quality":{"score":81,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"32K","tone":"positive"},{"label":"Freshness","value":"3y ago","tone":"warning"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":["Repository looks stale"]},"trust":{"version":"trust-score-v4","score":82,"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":100,"weight":0.13,"status":"pass","detail":"32K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":100,"weight":0.08,"status":"pass","detail":"32K stars, 5.3K forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":22,"weight":0.14,"status":"fail","detail":"3y since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add eriklindernoren/ML-From-Scratch"},{"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/eriklindernoren/ML-From-Scratch"},{"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":"32K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"32K stars, 5.3K forks; issue activity unavailable in current metadata"},{"status":"fail","label":"Recent maintenance","detail":"3y since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add eriklindernoren/ML-From-Scratch"},{"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/eriklindernoren/ML-From-Scratch"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Large GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Repository looks stale","Documentation summary is thin","Recent maintenance: 3y since push"],"evidence":{"stars":"32K GitHub stars","repoActivity":"32K stars, 5.3K forks","lastPushed":"3y since push","license":"MIT","repository":"https://github.com/eriklindernoren/ML-From-Scratch","install":"npx skills add eriklindernoren/ML-From-Scratch","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 eriklindernoren/ML-From-Scratch","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3y since push"]},"agentCompatibility":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Repository looks stale","Documentation summary is thin","Recent maintenance: 3y since push"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["ml-automation","machine-learning","automation","ml-media","data-mining","data-science"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Repository looks stale","Documentation summary is thin","Recent maintenance: 3y since push"]},"safety":{"score":63,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Repository appears stale","63/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Repository appears stale"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"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":["Repository appears stale","63/100 agent safety score"]},"supply_profile":{"track":{"slug":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Multimodal media","description":"I need my agent to process images, video, or audio and extract useful information.","useCases":[{"slug":"browser-automation","title":"Browser automation"},{"slug":"workflow-automation","title":"Workflow automation"},{"slug":"github-automation","title":"GitHub automation"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add eriklindernoren/ML-From-Scratch","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":31915,"starsLabel":"32K","forks":5345,"license":"MIT","qualityScore":81,"trustScore":82,"auditScore":75},"maintenance":{"status":"stale","label":"3y since push","daysSincePush":1022,"lastPushedAt":"2023-10-15T06:05:06+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Repository appears stale","Repository looks stale","Documentation summary is thin","Recent maintenance: 3y since push","Needs review"]},"coverageTags":["Design","Multimodal media","ml-automation","machine-learning","automation","ml-media","data-mining","data-science"]},"audit":{"audit_score":75,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Repository appears stale","Repository looks stale","Documentation summary is thin","Recent maintenance: 3y since push"]},"decision":{"readiness_score":83,"readiness_label":"Strong shortlist","headline":"Companion skill for Browser automation","role":"Companion skill","primary_fit":"Browser automation","best_for":["Browser automation workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["Repository looks stale","No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Browser automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"eriklindernoren-ml-from-scratch","name":"ML From Scratch","description":"Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.","category":"ml-automation","url":"https://www.openagentskill.com/skills/eriklindernoren-ml-from-scratch","repository":"https://github.com/eriklindernoren/ML-From-Scratch","github_repo":"eriklindernoren/ML-From-Scratch"},"suited_tasks":["Browser automation workflows","general agent builders","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Move data between tools","Transform files"],"suited_agents":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add eriklindernoren/ML-From-Scratch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add eriklindernoren/ML-From-Scratch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"ML From Scratch\" agent skill from https://github.com/eriklindernoren/ML-From-Scratch. 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: Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"ML From Scratch\" as a Claude Code skill from https://github.com/eriklindernoren/ML-From-Scratch. 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: Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"ML From Scratch\" from https://github.com/eriklindernoren/ML-From-Scratch 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: Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning."}],"handoff_url":"https://www.openagentskill.com/api/skills/eriklindernoren-ml-from-scratch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/eriklindernoren-ml-from-scratch"},"trust":{"score":82,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"32K GitHub stars","repoActivity":"32K stars, 5.3K forks","lastPushed":"3y since push","license":"MIT","repository":"https://github.com/eriklindernoren/ML-From-Scratch","install":"npx skills add eriklindernoren/ML-From-Scratch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["ml-automation","machine-learning","automation","ml-media","data-mining","data-science"],"known_risks":["Repository looks stale","Documentation summary is thin","Recent maintenance: 3y since push"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":75,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Repository appears stale","Repository looks stale","Documentation summary is thin","Recent maintenance: 3y since push"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":81,"label":"Strong"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"3y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Repository appears stale","Documentation summary is thin","Recent maintenance: 3y since push","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use ML From Scratch in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 82/100 Strong shortlist","Audit: 75/100 Needs review","Safety: 63/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"eriklindernoren-ml-from-scratch (ML From Scratch)","install_command":"npx skills add eriklindernoren/ML-From-Scratch","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":"eriklindernoren-ml-from-scratch","task":"Use ML From Scratch in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/eriklindernoren-ml-from-scratch","api":"https://www.openagentskill.com/api/agent/skills/eriklindernoren-ml-from-scratch","audit":"https://www.openagentskill.com/skills/eriklindernoren-ml-from-scratch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=eriklindernoren-ml-from-scratch&task=Use%20ML%20From%20Scratch%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20ML%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20ML%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/eriklindernoren-ml-from-scratch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/eriklindernoren-ml-from-scratch"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"eriklindernoren-ml-from-scratch","name":"ML From Scratch","description":"Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.","category":"ml-automation","url":"https://www.openagentskill.com/skills/eriklindernoren-ml-from-scratch","repository":"https://github.com/eriklindernoren/ML-From-Scratch","github_repo":"eriklindernoren/ML-From-Scratch"},"suited_tasks":["Browser automation workflows","general agent builders","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Move data between tools","Transform files"],"suited_agents":["Python","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add eriklindernoren/ML-From-Scratch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add eriklindernoren/ML-From-Scratch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"ML From Scratch\" agent skill from https://github.com/eriklindernoren/ML-From-Scratch. 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: Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"ML From Scratch\" as a Claude Code skill from https://github.com/eriklindernoren/ML-From-Scratch. 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: Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"ML From Scratch\" from https://github.com/eriklindernoren/ML-From-Scratch 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: Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning."}],"handoff_url":"https://www.openagentskill.com/api/skills/eriklindernoren-ml-from-scratch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/eriklindernoren-ml-from-scratch"},"trust":{"score":82,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"32K GitHub stars","repoActivity":"32K stars, 5.3K forks","lastPushed":"3y since push","license":"MIT","repository":"https://github.com/eriklindernoren/ML-From-Scratch","install":"npx skills add eriklindernoren/ML-From-Scratch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["ml-automation","machine-learning","automation","ml-media","data-mining","data-science"],"known_risks":["Repository looks stale","Documentation summary is thin","Recent maintenance: 3y since push"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":75,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Repository appears stale","Repository looks stale","Documentation summary is thin","Recent maintenance: 3y since push"]},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace."},"quality":{"score":81,"label":"Strong"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"3y since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that require actively maintained dependencies","production agents without a repository review","Repository looks stale","No OpenAgentSkill engagement data yet","Repository appears stale","Documentation summary is thin","Recent maintenance: 3y since push","Production credentials, payments, or irreversible account changes without explicit human review"],"agent_contract":{"task_input":"Use ML From Scratch in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 82/100 Strong shortlist","Audit: 75/100 Needs review","Safety: 63/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"eriklindernoren-ml-from-scratch (ML From Scratch)","install_command":"npx skills add eriklindernoren/ML-From-Scratch","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":"eriklindernoren-ml-from-scratch","task":"Use ML From Scratch in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/eriklindernoren-ml-from-scratch","api":"https://www.openagentskill.com/api/agent/skills/eriklindernoren-ml-from-scratch","audit":"https://www.openagentskill.com/skills/eriklindernoren-ml-from-scratch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=eriklindernoren-ml-from-scratch&task=Use%20ML%20From%20Scratch%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20ML%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20ML%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/eriklindernoren-ml-from-scratch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/eriklindernoren-ml-from-scratch"}},"platforms":["Python","Machine Learning"],"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"testing-qa","title":"Testing and QA","url":"https://www.openagentskill.com/use-cases/testing-qa"}],"install":"npx skills add eriklindernoren/ML-From-Scratch","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add eriklindernoren/ML-From-Scratch","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"ML From Scratch\" agent skill from https://github.com/eriklindernoren/ML-From-Scratch. 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: Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.","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 \"ML From Scratch\" as a Claude Code skill from https://github.com/eriklindernoren/ML-From-Scratch. 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: Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.","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 \"ML From Scratch\" from https://github.com/eriklindernoren/ML-From-Scratch 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: Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/eriklindernoren/ML-From-Scratch","github_repo":"eriklindernoren/ML-From-Scratch","version":"1.0.0","license":"MIT","updated_at":"2026-06-16T10:02:52.475792+00:00","canonical_key":"eriklindernoren/ml-from-scratch","recommendation_reasons":["Matches task terms: from, scratch","Strong GitHub adoption: 31,915 stars","Install handoff is available","Repository freshness signal is available","Registry match score 25"],"urls":{"web":"https://www.openagentskill.com/skills/eriklindernoren-ml-from-scratch","api":"https://www.openagentskill.com/api/agent/skills/eriklindernoren-ml-from-scratch","install_api":"https://www.openagentskill.com/api/skills/eriklindernoren-ml-from-scratch/install","audit":"https://www.openagentskill.com/skills/eriklindernoren-ml-from-scratch/audit","repository":"https://github.com/eriklindernoren/ML-From-Scratch"}},{"rank":3,"match_score":25,"raw_match_score":215.3,"slug":"windy3f3f3f3f-claude-code-from-scratch","name":"Claude Code From Scratch","description":"Build your own Claude Code from scratch.  🔍 Claude Code 开源了 50 万行代码，读不动？用 ~4000 行 TypeScript / Python 从零复现核心架构，11 章分步教程带你理解 coding agent 精髓","tagline":"Build your own Claude Code from scratch.  🔍 Claude Code 开源了 50 万行代码，读不动？用 ~4000 行 TypeScript / Python 从零复现核心架构，11 章分步教程带你理解 coding agent 精髓","category":"agent-frameworks","tags":["agents","ai-agent","ai","anthropic","build-from-scratch","claude","claude-code","coding-agent","llm","tutorial"],"author":{"name":"Windy3f3f3f3f","verified":true,"url":"https://github.com/Windy3f3f3f3f"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"Windy3f3f3f3f/claude-code-from-scratch","creatorName":"Windy3f3f3f3f","creatorUrl":"https://github.com/Windy3f3f3f3f","sourceUrl":"https://github.com/Windy3f3f3f3f/claude-code-from-scratch","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/windy3f3f3f3f-claude-code-from-scratch#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":2482,"forks":514,"downloads":0,"rating":0,"review_count":0,"quality_score":65.46},"quality":{"score":99,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"2.5K","tone":"positive"},{"label":"Freshness","value":"24d ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":89,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"2.5K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"2.5K stars, 514 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":100,"weight":0.14,"status":"pass","detail":"24d since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add Windy3f3f3f3f/claude-code-from-scratch"},{"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/Windy3f3f3f3f/claude-code-from-scratch"},{"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":"2.5K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"2.5K stars, 514 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"24d since push"},{"status":"pass","label":"License clarity","detail":"MIT"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add Windy3f3f3f3f/claude-code-from-scratch"},{"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/Windy3f3f3f3f/claude-code-from-scratch"},{"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":"2.5K GitHub stars","repoActivity":"2.5K stars, 514 forks","lastPushed":"24d since push","license":"MIT","repository":"https://github.com/Windy3f3f3f3f/claude-code-from-scratch","install":"npx skills add Windy3f3f3f3f/claude-code-from-scratch","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 Windy3f3f3f3f/claude-code-from-scratch","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","24d since push"]},"agentCompatibility":["Python","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-frameworks","agents","ai-agent","ai","anthropic","build-from-scratch"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin"]},"safety":{"score":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"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"Coding agents","description":"I need a coding agent that can understand a repository, edit code, and review pull requests.","useCases":[{"slug":"coding-agents","title":"Coding agents"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"web-scraping","title":"Web scraping"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","Python"],"install":{"ready":true,"command":"npx skills add Windy3f3f3f3f/claude-code-from-scratch","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":2482,"starsLabel":"2.5K","forks":514,"license":"MIT","qualityScore":99,"trustScore":89,"auditScore":94},"maintenance":{"status":"fresh","label":"24d since push","daysSincePush":24,"lastPushedAt":"2026-07-09T09:34:10+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Coding","Coding agents","agent-frameworks","agents","ai-agent","ai","anthropic","build-from-scratch"]},"audit":{"audit_score":94,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Coding agents","role":"Primary pick","primary_fit":"Coding agents","best_for":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Coding agents task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"windy3f3f3f3f-claude-code-from-scratch","name":"Claude Code From Scratch","description":"Build your own Claude Code from scratch.  🔍 Claude Code 开源了 50 万行代码，读不动？用 ~4000 行 TypeScript / Python 从零复现核心架构，11 章分步教程带你理解 coding agent 精髓","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/windy3f3f3f3f-claude-code-from-scratch","repository":"https://github.com/Windy3f3f3f3f/claude-code-from-scratch","github_repo":"Windy3f3f3f3f/claude-code-from-scratch"},"suited_tasks":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Navigate pages","Click and type safely"],"suited_agents":["Python","AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add Windy3f3f3f3f/claude-code-from-scratch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add Windy3f3f3f3f/claude-code-from-scratch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Claude Code From Scratch\" agent skill from https://github.com/Windy3f3f3f3f/claude-code-from-scratch. 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: Build your own Claude Code from scratch. 🔍 Claude Code 开源了 50 万行代码，读不动？用 ~4000 行 TypeScript / Python 从零复现核心架构，11 章分步教程带你理解 coding agent 精髓"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Claude Code From Scratch\" as a Claude Code skill from https://github.com/Windy3f3f3f3f/claude-code-from-scratch. 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: Build your own Claude Code from scratch. 🔍 Claude Code 开源了 50 万行代码，读不动？用 ~4000 行 TypeScript / Python 从零复现核心架构，11 章分步教程带你理解 coding agent 精髓"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Claude Code From Scratch\" from https://github.com/Windy3f3f3f3f/claude-code-from-scratch 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: Build your own Claude Code from scratch. 🔍 Claude Code 开源了 50 万行代码，读不动？用 ~4000 行 TypeScript / Python 从零复现核心架构，11 章分步教程带你理解 coding agent 精髓"}],"handoff_url":"https://www.openagentskill.com/api/skills/windy3f3f3f3f-claude-code-from-scratch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/windy3f3f3f3f-claude-code-from-scratch"},"trust":{"score":89,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"2.5K GitHub stars","repoActivity":"2.5K stars, 514 forks","lastPushed":"24d since push","license":"MIT","repository":"https://github.com/Windy3f3f3f3f/claude-code-from-scratch","install":"npx skills add Windy3f3f3f3f/claude-code-from-scratch","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-frameworks","agents","ai-agent","ai","anthropic","build-from-scratch"],"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":99,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"24d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","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 Claude Code From Scratch in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 89/100 Production candidate","Audit: 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":"windy3f3f3f3f-claude-code-from-scratch (Claude Code From Scratch)","install_command":"npx skills add Windy3f3f3f3f/claude-code-from-scratch","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":"windy3f3f3f3f-claude-code-from-scratch","task":"Use Claude Code From Scratch in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/windy3f3f3f3f-claude-code-from-scratch","api":"https://www.openagentskill.com/api/agent/skills/windy3f3f3f3f-claude-code-from-scratch","audit":"https://www.openagentskill.com/skills/windy3f3f3f3f-claude-code-from-scratch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=windy3f3f3f3f-claude-code-from-scratch&task=Use%20Claude%20Code%20From%20Scratch%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Claude%20Code%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Claude%20Code%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/windy3f3f3f3f-claude-code-from-scratch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/windy3f3f3f3f-claude-code-from-scratch"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"windy3f3f3f3f-claude-code-from-scratch","name":"Claude Code From Scratch","description":"Build your own Claude Code from scratch.  🔍 Claude Code 开源了 50 万行代码，读不动？用 ~4000 行 TypeScript / Python 从零复现核心架构，11 章分步教程带你理解 coding agent 精髓","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/windy3f3f3f3f-claude-code-from-scratch","repository":"https://github.com/Windy3f3f3f3f/claude-code-from-scratch","github_repo":"Windy3f3f3f3f/claude-code-from-scratch"},"suited_tasks":["Coding agents workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect source files","Explain architecture","Patch bugs and verify changes","Navigate pages","Click and type safely"],"suited_agents":["Python","AI Agents","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add Windy3f3f3f3f/claude-code-from-scratch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add Windy3f3f3f3f/claude-code-from-scratch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Claude Code From Scratch\" agent skill from https://github.com/Windy3f3f3f3f/claude-code-from-scratch. 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: Build your own Claude Code from scratch. 🔍 Claude Code 开源了 50 万行代码，读不动？用 ~4000 行 TypeScript / Python 从零复现核心架构，11 章分步教程带你理解 coding agent 精髓"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Claude Code From Scratch\" as a Claude Code skill from https://github.com/Windy3f3f3f3f/claude-code-from-scratch. 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: Build your own Claude Code from scratch. 🔍 Claude Code 开源了 50 万行代码，读不动？用 ~4000 行 TypeScript / Python 从零复现核心架构，11 章分步教程带你理解 coding agent 精髓"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Claude Code From Scratch\" from https://github.com/Windy3f3f3f3f/claude-code-from-scratch 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: Build your own Claude Code from scratch. 🔍 Claude Code 开源了 50 万行代码，读不动？用 ~4000 行 TypeScript / Python 从零复现核心架构，11 章分步教程带你理解 coding agent 精髓"}],"handoff_url":"https://www.openagentskill.com/api/skills/windy3f3f3f3f-claude-code-from-scratch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/windy3f3f3f3f-claude-code-from-scratch"},"trust":{"score":89,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"2.5K GitHub stars","repoActivity":"2.5K stars, 514 forks","lastPushed":"24d since push","license":"MIT","repository":"https://github.com/Windy3f3f3f3f/claude-code-from-scratch","install":"npx skills add Windy3f3f3f3f/claude-code-from-scratch","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-frameworks","agents","ai-agent","ai","anthropic","build-from-scratch"],"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":99,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"Coding agents","maintenance":"24d since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","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 Claude Code From Scratch in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 89/100 Production candidate","Audit: 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":"windy3f3f3f3f-claude-code-from-scratch (Claude Code From Scratch)","install_command":"npx skills add Windy3f3f3f3f/claude-code-from-scratch","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":"windy3f3f3f3f-claude-code-from-scratch","task":"Use Claude Code From Scratch in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/windy3f3f3f3f-claude-code-from-scratch","api":"https://www.openagentskill.com/api/agent/skills/windy3f3f3f3f-claude-code-from-scratch","audit":"https://www.openagentskill.com/skills/windy3f3f3f3f-claude-code-from-scratch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=windy3f3f3f3f-claude-code-from-scratch&task=Use%20Claude%20Code%20From%20Scratch%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Claude%20Code%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Claude%20Code%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/windy3f3f3f3f-claude-code-from-scratch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/windy3f3f3f3f-claude-code-from-scratch"}},"platforms":["Python","AI Agents","Claude Code"],"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":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"},{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"}],"install":"npx skills add Windy3f3f3f3f/claude-code-from-scratch","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add Windy3f3f3f3f/claude-code-from-scratch","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Claude Code From Scratch\" agent skill from https://github.com/Windy3f3f3f3f/claude-code-from-scratch. 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: Build your own Claude Code from scratch. 🔍 Claude Code 开源了 50 万行代码，读不动？用 ~4000 行 TypeScript / Python 从零复现核心架构，11 章分步教程带你理解 coding agent 精髓","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 \"Claude Code From Scratch\" as a Claude Code skill from https://github.com/Windy3f3f3f3f/claude-code-from-scratch. 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: Build your own Claude Code from scratch. 🔍 Claude Code 开源了 50 万行代码，读不动？用 ~4000 行 TypeScript / Python 从零复现核心架构，11 章分步教程带你理解 coding agent 精髓","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 \"Claude Code From Scratch\" from https://github.com/Windy3f3f3f3f/claude-code-from-scratch 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: Build your own Claude Code from scratch. 🔍 Claude Code 开源了 50 万行代码，读不动？用 ~4000 行 TypeScript / Python 从零复现核心架构，11 章分步教程带你理解 coding agent 精髓","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/Windy3f3f3f3f/claude-code-from-scratch","github_repo":"Windy3f3f3f3f/claude-code-from-scratch","version":"1.0.0","license":"MIT","updated_at":"2026-07-29T02:30:26.448869+00:00","canonical_key":"windy3f3f3f3f/claude-code-from-scratch","recommendation_reasons":["Matches task terms: from, scratch","Useful GitHub adoption: 2,482 stars","Install handoff is available","Repository freshness signal is available","Registry match score 25"],"urls":{"web":"https://www.openagentskill.com/skills/windy3f3f3f3f-claude-code-from-scratch","api":"https://www.openagentskill.com/api/agent/skills/windy3f3f3f3f-claude-code-from-scratch","install_api":"https://www.openagentskill.com/api/skills/windy3f3f3f3f-claude-code-from-scratch/install","audit":"https://www.openagentskill.com/skills/windy3f3f3f3f-claude-code-from-scratch/audit","repository":"https://github.com/Windy3f3f3f3f/claude-code-from-scratch"}},{"rank":4,"match_score":20,"raw_match_score":176.9,"slug":"pguso-ai-agents-from-scratch","name":"AI Agents From Scratch","description":"Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns.","tagline":"Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns.","category":"agent-frameworks","tags":["llm-agent","agents","ai-agents","educational","function-calling","llm","node-llama-cpp","react-agent","tutorial","javascript"],"author":{"name":"pguso","verified":true,"url":"https://github.com/pguso"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"pguso/ai-agents-from-scratch","creatorName":"pguso","creatorUrl":"https://github.com/pguso","sourceUrl":"https://github.com/pguso/ai-agents-from-scratch","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/pguso-ai-agents-from-scratch#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":4265,"forks":619,"downloads":0,"rating":0,"review_count":0,"quality_score":67.11},"quality":{"score":99,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"4.3K","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":88,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"4.3K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"4.3K stars, 619 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 pguso/ai-agents-from-scratch"},{"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/pguso/ai-agents-from-scratch"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"4.3K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"4.3K stars, 619 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 pguso/ai-agents-from-scratch"},{"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/pguso/ai-agents-from-scratch"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Recently maintained repository","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin"],"evidence":{"stars":"4.3K GitHub stars","repoActivity":"4.3K stars, 619 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/pguso/ai-agents-from-scratch","install":"npx skills add pguso/ai-agents-from-scratch","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 pguso/ai-agents-from-scratch","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":["JavaScript","LLM","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-frameworks","llm-agent","agents","ai-agents","educational","function-calling"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin"]},"safety":{"score":80,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","80/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","80/100 agent safety score"]},"supply_profile":{"track":{"slug":"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":"browser-automation","title":"Browser automation"},{"slug":"education-tutoring","title":"Education and tutoring"},{"slug":"local-desktop","title":"Local desktop"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","JavaScript"],"install":{"ready":true,"command":"npx skills add pguso/ai-agents-from-scratch","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":4265,"starsLabel":"4.3K","forks":619,"license":"MIT","qualityScore":99,"trustScore":88,"auditScore":92},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":63,"lastPushedAt":"2026-05-31T08:52:06+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Coding","Coding agents","agent-frameworks","llm-agent","agents","ai-agents","educational","function-calling"]},"audit":{"audit_score":92,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Browser automation","role":"Primary pick","primary_fit":"Browser automation","best_for":["Browser automation workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Browser automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"pguso-ai-agents-from-scratch","name":"AI Agents From Scratch","description":"Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns.","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/pguso-ai-agents-from-scratch","repository":"https://github.com/pguso/ai-agents-from-scratch","github_repo":"pguso/ai-agents-from-scratch"},"suited_tasks":["Browser automation workflows","general agent builders","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Break down concepts","Create practice material"],"suited_agents":["JavaScript","LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add pguso/ai-agents-from-scratch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add pguso/ai-agents-from-scratch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"AI Agents From Scratch\" agent skill from https://github.com/pguso/ai-agents-from-scratch. 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: Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"AI Agents From Scratch\" as a Claude Code skill from https://github.com/pguso/ai-agents-from-scratch. 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: Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"AI Agents From Scratch\" from https://github.com/pguso/ai-agents-from-scratch 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: Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns."}],"handoff_url":"https://www.openagentskill.com/api/skills/pguso-ai-agents-from-scratch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/pguso-ai-agents-from-scratch"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"4.3K GitHub stars","repoActivity":"4.3K stars, 619 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/pguso/ai-agents-from-scratch","install":"npx skills add pguso/ai-agents-from-scratch","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-frameworks","llm-agent","agents","ai-agents","educational","function-calling"],"known_risks":["Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":92,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":99,"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 AI Agents From Scratch in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 88/100 Production candidate","Audit: 92/100 Safe to try","Safety: 80/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"pguso-ai-agents-from-scratch (AI Agents From Scratch)","install_command":"npx skills add pguso/ai-agents-from-scratch","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":"pguso-ai-agents-from-scratch","task":"Use AI Agents From Scratch in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/pguso-ai-agents-from-scratch","api":"https://www.openagentskill.com/api/agent/skills/pguso-ai-agents-from-scratch","audit":"https://www.openagentskill.com/skills/pguso-ai-agents-from-scratch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=pguso-ai-agents-from-scratch&task=Use%20AI%20Agents%20From%20Scratch%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20AI%20Agents%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20AI%20Agents%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/pguso-ai-agents-from-scratch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/pguso-ai-agents-from-scratch"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"pguso-ai-agents-from-scratch","name":"AI Agents From Scratch","description":"Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns.","category":"agent-frameworks","url":"https://www.openagentskill.com/skills/pguso-ai-agents-from-scratch","repository":"https://github.com/pguso/ai-agents-from-scratch","github_repo":"pguso/ai-agents-from-scratch"},"suited_tasks":["Browser automation workflows","general agent builders","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Break down concepts","Create practice material"],"suited_agents":["JavaScript","LLM","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add pguso/ai-agents-from-scratch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add pguso/ai-agents-from-scratch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"AI Agents From Scratch\" agent skill from https://github.com/pguso/ai-agents-from-scratch. 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: Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"AI Agents From Scratch\" as a Claude Code skill from https://github.com/pguso/ai-agents-from-scratch. 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: Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"AI Agents From Scratch\" from https://github.com/pguso/ai-agents-from-scratch 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: Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns."}],"handoff_url":"https://www.openagentskill.com/api/skills/pguso-ai-agents-from-scratch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/pguso-ai-agents-from-scratch"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"4.3K GitHub stars","repoActivity":"4.3K stars, 619 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/pguso/ai-agents-from-scratch","install":"npx skills add pguso/ai-agents-from-scratch","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-frameworks","llm-agent","agents","ai-agents","educational","function-calling"],"known_risks":["Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":92,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":99,"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 AI Agents From Scratch in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 88/100 Production candidate","Audit: 92/100 Safe to try","Safety: 80/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"pguso-ai-agents-from-scratch (AI Agents From Scratch)","install_command":"npx skills add pguso/ai-agents-from-scratch","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":"pguso-ai-agents-from-scratch","task":"Use AI Agents From Scratch in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/pguso-ai-agents-from-scratch","api":"https://www.openagentskill.com/api/agent/skills/pguso-ai-agents-from-scratch","audit":"https://www.openagentskill.com/skills/pguso-ai-agents-from-scratch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=pguso-ai-agents-from-scratch&task=Use%20AI%20Agents%20From%20Scratch%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20AI%20Agents%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20AI%20Agents%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/pguso-ai-agents-from-scratch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/pguso-ai-agents-from-scratch"}},"platforms":["JavaScript","LLM"],"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"education-tutoring","title":"Education and tutoring","url":"https://www.openagentskill.com/use-cases/education-tutoring"},{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"},{"slug":"web-scraping","title":"Web scraping","url":"https://www.openagentskill.com/use-cases/web-scraping"}],"install":"npx skills add pguso/ai-agents-from-scratch","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add pguso/ai-agents-from-scratch","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"AI Agents From Scratch\" agent skill from https://github.com/pguso/ai-agents-from-scratch. 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: Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns.","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 \"AI Agents From Scratch\" as a Claude Code skill from https://github.com/pguso/ai-agents-from-scratch. 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: Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns.","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 \"AI Agents From Scratch\" from https://github.com/pguso/ai-agents-from-scratch 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: Demystify AI agents by building them yourself. Local LLMs, no black boxes, real understanding of function calling, memory, and ReAct patterns.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/pguso/ai-agents-from-scratch","github_repo":"pguso/ai-agents-from-scratch","version":"1.0.0","license":"MIT","updated_at":"2026-06-14T03:01:31.419442+00:00","canonical_key":"pguso/ai-agents-from-scratch","recommendation_reasons":["Matches task terms: llms, from, scratch","Useful GitHub adoption: 4,265 stars","Install handoff is available","Repository freshness signal is available","Registry match score 20"],"urls":{"web":"https://www.openagentskill.com/skills/pguso-ai-agents-from-scratch","api":"https://www.openagentskill.com/api/agent/skills/pguso-ai-agents-from-scratch","install_api":"https://www.openagentskill.com/api/skills/pguso-ai-agents-from-scratch/install","audit":"https://www.openagentskill.com/skills/pguso-ai-agents-from-scratch/audit","repository":"https://github.com/pguso/ai-agents-from-scratch"}},{"rank":5,"match_score":20,"raw_match_score":172,"slug":"pguso-rag-from-scratch","name":"RAG From Scratch","description":"Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.","tagline":"Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.","category":"rag-knowledge","tags":["rag","retrieval","knowledge","agents","ai-agents","educational","llm","node-llama-cpp","nodejs","rag-chatbot"],"author":{"name":"pguso","verified":true,"url":"https://github.com/pguso"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"pguso/rag-from-scratch","creatorName":"pguso","creatorUrl":"https://github.com/pguso","sourceUrl":"https://github.com/pguso/rag-from-scratch","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/pguso-rag-from-scratch#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":1456,"forks":173,"downloads":0,"rating":0,"review_count":0,"quality_score":56.84},"quality":{"score":87,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"1.5K","tone":"positive"},{"label":"Freshness","value":"5mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":86,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"1.5K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":77,"weight":0.08,"status":"info","detail":"1.5K stars, 173 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":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 pguso/rag-from-scratch"},{"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/pguso/rag-from-scratch"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"1.5K GitHub stars"},{"status":"info","label":"Stars/forks activity","detail":"1.5K stars, 173 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"5mo 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 pguso/rag-from-scratch"},{"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/pguso/rag-from-scratch"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin"],"evidence":{"stars":"1.5K GitHub stars","repoActivity":"1.5K stars, 173 forks","lastPushed":"5mo since push","license":"MIT","repository":"https://github.com/pguso/rag-from-scratch","install":"npx skills add pguso/rag-from-scratch","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 pguso/rag-from-scratch","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","5mo since push"]},"agentCompatibility":["JavaScript","RAG","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":["rag-knowledge","rag","retrieval","knowledge","agents","ai-agents"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin"]},"safety":{"score":74,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","74/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["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","74/100 agent safety score"]},"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"RAG and knowledge","description":"I need my agent to build a RAG workflow over documents and retrieve reliable context.","useCases":[{"slug":"rag-knowledge","title":"RAG and knowledge"},{"slug":"browser-automation","title":"Browser automation"},{"slug":"research-agents","title":"Research agents"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","JavaScript"],"install":{"ready":true,"command":"npx skills add pguso/rag-from-scratch","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":1456,"starsLabel":"1.5K","forks":173,"license":"MIT","qualityScore":87,"trustScore":86,"auditScore":86},"maintenance":{"status":"active","label":"5mo since push","daysSincePush":144,"lastPushedAt":"2026-03-11T11:44:33+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Research","RAG and knowledge","rag-knowledge","rag","retrieval","knowledge","agents","ai-agents"]},"audit":{"audit_score":86,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"decision":{"readiness_score":98,"readiness_label":"Production-ready","headline":"Primary pick for RAG and knowledge","role":"Primary pick","primary_fit":"RAG and knowledge","best_for":["RAG and knowledge workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one RAG and knowledge task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"pguso-rag-from-scratch","name":"RAG From Scratch","description":"Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.","category":"rag-knowledge","url":"https://www.openagentskill.com/skills/pguso-rag-from-scratch","repository":"https://github.com/pguso/rag-from-scratch","github_repo":"pguso/rag-from-scratch"},"suited_tasks":["RAG and knowledge workflows","general agent builders","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Navigate pages","Click and type safely"],"suited_agents":["JavaScript","RAG","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add pguso/rag-from-scratch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add pguso/rag-from-scratch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"RAG From Scratch\" agent skill from https://github.com/pguso/rag-from-scratch. 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: Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"RAG From Scratch\" as a Claude Code skill from https://github.com/pguso/rag-from-scratch. 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: Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"RAG From Scratch\" from https://github.com/pguso/rag-from-scratch 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: Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation."}],"handoff_url":"https://www.openagentskill.com/api/skills/pguso-rag-from-scratch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/pguso-rag-from-scratch"},"trust":{"score":86,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"1.5K GitHub stars","repoActivity":"1.5K stars, 173 forks","lastPushed":"5mo since push","license":"MIT","repository":"https://github.com/pguso/rag-from-scratch","install":"npx skills add pguso/rag-from-scratch","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":["rag-knowledge","rag","retrieval","knowledge","agents","ai-agents"],"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":86,"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":87,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","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","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 RAG From Scratch in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 86/100 Production candidate","Audit: 86/100 Safe to try","Safety: 74/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"pguso-rag-from-scratch (RAG From Scratch)","install_command":"npx skills add pguso/rag-from-scratch","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":"pguso-rag-from-scratch","task":"Use RAG From Scratch in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/pguso-rag-from-scratch","api":"https://www.openagentskill.com/api/agent/skills/pguso-rag-from-scratch","audit":"https://www.openagentskill.com/skills/pguso-rag-from-scratch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=pguso-rag-from-scratch&task=Use%20RAG%20From%20Scratch%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20RAG%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20RAG%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/pguso-rag-from-scratch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/pguso-rag-from-scratch"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"pguso-rag-from-scratch","name":"RAG From Scratch","description":"Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.","category":"rag-knowledge","url":"https://www.openagentskill.com/skills/pguso-rag-from-scratch","repository":"https://github.com/pguso/rag-from-scratch","github_repo":"pguso/rag-from-scratch"},"suited_tasks":["RAG and knowledge workflows","general agent builders","teams that value GitHub adoption signals","Chunk documents","Create embeddings","Retrieve and cite relevant passages","Navigate pages","Click and type safely"],"suited_agents":["JavaScript","RAG","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add pguso/rag-from-scratch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add pguso/rag-from-scratch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"RAG From Scratch\" agent skill from https://github.com/pguso/rag-from-scratch. 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: Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"RAG From Scratch\" as a Claude Code skill from https://github.com/pguso/rag-from-scratch. 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: Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"RAG From Scratch\" from https://github.com/pguso/rag-from-scratch 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: Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation."}],"handoff_url":"https://www.openagentskill.com/api/skills/pguso-rag-from-scratch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/pguso-rag-from-scratch"},"trust":{"score":86,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"1.5K GitHub stars","repoActivity":"1.5K stars, 173 forks","lastPushed":"5mo since push","license":"MIT","repository":"https://github.com/pguso/rag-from-scratch","install":"npx skills add pguso/rag-from-scratch","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":["rag-knowledge","rag","retrieval","knowledge","agents","ai-agents"],"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":86,"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":87,"label":"Excellent"},"supply":{"track":"Research and knowledge work","scenario":"RAG and knowledge","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","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 RAG From Scratch in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 86/100 Production candidate","Audit: 86/100 Safe to try","Safety: 74/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"pguso-rag-from-scratch (RAG From Scratch)","install_command":"npx skills add pguso/rag-from-scratch","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":"pguso-rag-from-scratch","task":"Use RAG From Scratch in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/pguso-rag-from-scratch","api":"https://www.openagentskill.com/api/agent/skills/pguso-rag-from-scratch","audit":"https://www.openagentskill.com/skills/pguso-rag-from-scratch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=pguso-rag-from-scratch&task=Use%20RAG%20From%20Scratch%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20RAG%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20RAG%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/pguso-rag-from-scratch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/pguso-rag-from-scratch"}},"platforms":["JavaScript","RAG"],"use_cases":[{"slug":"rag-knowledge","title":"RAG and knowledge","url":"https://www.openagentskill.com/use-cases/rag-knowledge"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"research-agents","title":"Research agents","url":"https://www.openagentskill.com/use-cases/research-agents"},{"slug":"education-tutoring","title":"Education and tutoring","url":"https://www.openagentskill.com/use-cases/education-tutoring"}],"install":"npx skills add pguso/rag-from-scratch","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add pguso/rag-from-scratch","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"RAG From Scratch\" agent skill from https://github.com/pguso/rag-from-scratch. 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: Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.","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 \"RAG From Scratch\" as a Claude Code skill from https://github.com/pguso/rag-from-scratch. 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: Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.","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 \"RAG From Scratch\" from https://github.com/pguso/rag-from-scratch 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: Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/pguso/rag-from-scratch","github_repo":"pguso/rag-from-scratch","version":"1.0.0","license":"MIT","updated_at":"2026-06-13T00:01:21.613225+00:00","canonical_key":"pguso/rag-from-scratch","recommendation_reasons":["Matches task terms: llms, from, scratch","Useful GitHub adoption: 1,456 stars","Install handoff is available","Repository freshness signal is available","Registry match score 20"],"urls":{"web":"https://www.openagentskill.com/skills/pguso-rag-from-scratch","api":"https://www.openagentskill.com/api/agent/skills/pguso-rag-from-scratch","install_api":"https://www.openagentskill.com/api/skills/pguso-rag-from-scratch/install","audit":"https://www.openagentskill.com/skills/pguso-rag-from-scratch/audit","repository":"https://github.com/pguso/rag-from-scratch"}},{"rank":6,"match_score":20,"raw_match_score":169.1,"slug":"rasbt-reasoning-from-scratch","name":"Reasoning From Scratch","description":"Implement a reasoning LLM in PyTorch from scratch, step by step","tagline":"Implement a reasoning LLM in PyTorch from scratch, step by step","category":"ml-automation","tags":["machine-learning","automation","ml-media","ai","artificial-intelligence","chain-of-thought","deep-learning","distillation","grpo","inference-time-scaling"],"author":{"name":"rasbt","verified":true,"url":"https://github.com/rasbt"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"rasbt/reasoning-from-scratch","creatorName":"rasbt","creatorUrl":"https://github.com/rasbt","sourceUrl":"https://github.com/rasbt/reasoning-from-scratch","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/rasbt-reasoning-from-scratch#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":4516,"forks":664,"downloads":0,"rating":0,"review_count":0,"quality_score":67.28},"quality":{"score":99,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"4.5K","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":86,"tier":"production","label":"Production candidate","summary":"Strong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/runtime risk, install safety, permission surface, and install availability.","recommendedAction":"Shortlist for production use, then run a normal repository and dependency review.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"4.5K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"4.5K stars, 664 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add rasbt/reasoning-from-scratch"},{"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/rasbt/reasoning-from-scratch"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"4.5K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"4.5K stars, 664 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"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 rasbt/reasoning-from-scratch"},{"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/rasbt/reasoning-from-scratch"},{"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","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"4.5K GitHub stars","repoActivity":"4.5K stars, 664 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/rasbt/reasoning-from-scratch","install":"npx skills add rasbt/reasoning-from-scratch","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 rasbt/reasoning-from-scratch","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Jupyter Notebook","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["ml-automation","machine-learning","automation","ml-media","ai","artificial-intelligence"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":78,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","78/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","78/100 agent safety score"]},"supply_profile":{"track":{"slug":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Multimodal media","description":"I need my agent to process images, video, or audio and extract useful information.","useCases":[{"slug":"browser-automation","title":"Browser automation"},{"slug":"workflow-automation","title":"Workflow automation"},{"slug":"data-analysis","title":"Data analysis"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Jupyter Notebook"],"install":{"ready":true,"command":"npx skills add rasbt/reasoning-from-scratch","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":4516,"starsLabel":"4.5K","forks":664,"license":"Apache-2.0","qualityScore":99,"trustScore":86,"auditScore":90},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":52,"lastPushedAt":"2026-06-12T01:02:45+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"coverageTags":["Design","Multimodal media","ml-automation","machine-learning","automation","ml-media","ai","artificial-intelligence"]},"audit":{"audit_score":90,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Browser automation","role":"Primary pick","primary_fit":"Browser automation","best_for":["Browser automation workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Browser automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"rasbt-reasoning-from-scratch","name":"Reasoning From Scratch","description":"Implement a reasoning LLM in PyTorch from scratch, step by step","category":"ml-automation","url":"https://www.openagentskill.com/skills/rasbt-reasoning-from-scratch","repository":"https://github.com/rasbt/reasoning-from-scratch","github_repo":"rasbt/reasoning-from-scratch"},"suited_tasks":["Browser automation workflows","general agent builders","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Move data between tools","Transform files"],"suited_agents":["Jupyter Notebook","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add rasbt/reasoning-from-scratch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add rasbt/reasoning-from-scratch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Reasoning From Scratch\" agent skill from https://github.com/rasbt/reasoning-from-scratch. 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: Implement a reasoning LLM in PyTorch from scratch, step by step"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Reasoning From Scratch\" as a Claude Code skill from https://github.com/rasbt/reasoning-from-scratch. 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: Implement a reasoning LLM in PyTorch from scratch, step by step"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Reasoning From Scratch\" from https://github.com/rasbt/reasoning-from-scratch 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: Implement a reasoning LLM in PyTorch from scratch, step by step"}],"handoff_url":"https://www.openagentskill.com/api/skills/rasbt-reasoning-from-scratch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/rasbt-reasoning-from-scratch"},"trust":{"score":86,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"4.5K GitHub stars","repoActivity":"4.5K stars, 664 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/rasbt/reasoning-from-scratch","install":"npx skills add rasbt/reasoning-from-scratch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["ml-automation","machine-learning","automation","ml-media","ai","artificial-intelligence"],"known_risks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":90,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":99,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Reasoning From Scratch in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 86/100 Production candidate","Audit: 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":"rasbt-reasoning-from-scratch (Reasoning From Scratch)","install_command":"npx skills add rasbt/reasoning-from-scratch","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":"rasbt-reasoning-from-scratch","task":"Use Reasoning From Scratch in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/rasbt-reasoning-from-scratch","api":"https://www.openagentskill.com/api/agent/skills/rasbt-reasoning-from-scratch","audit":"https://www.openagentskill.com/skills/rasbt-reasoning-from-scratch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=rasbt-reasoning-from-scratch&task=Use%20Reasoning%20From%20Scratch%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Reasoning%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Reasoning%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/rasbt-reasoning-from-scratch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/rasbt-reasoning-from-scratch"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"rasbt-reasoning-from-scratch","name":"Reasoning From Scratch","description":"Implement a reasoning LLM in PyTorch from scratch, step by step","category":"ml-automation","url":"https://www.openagentskill.com/skills/rasbt-reasoning-from-scratch","repository":"https://github.com/rasbt/reasoning-from-scratch","github_repo":"rasbt/reasoning-from-scratch"},"suited_tasks":["Browser automation workflows","general agent builders","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Move data between tools","Transform files"],"suited_agents":["Jupyter Notebook","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add rasbt/reasoning-from-scratch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add rasbt/reasoning-from-scratch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"Reasoning From Scratch\" agent skill from https://github.com/rasbt/reasoning-from-scratch. 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: Implement a reasoning LLM in PyTorch from scratch, step by step"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"Reasoning From Scratch\" as a Claude Code skill from https://github.com/rasbt/reasoning-from-scratch. 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: Implement a reasoning LLM in PyTorch from scratch, step by step"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"Reasoning From Scratch\" from https://github.com/rasbt/reasoning-from-scratch 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: Implement a reasoning LLM in PyTorch from scratch, step by step"}],"handoff_url":"https://www.openagentskill.com/api/skills/rasbt-reasoning-from-scratch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/rasbt-reasoning-from-scratch"},"trust":{"score":86,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"4.5K GitHub stars","repoActivity":"4.5K stars, 664 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/rasbt/reasoning-from-scratch","install":"npx skills add rasbt/reasoning-from-scratch","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["ml-automation","machine-learning","automation","ml-media","ai","artificial-intelligence"],"known_risks":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":90,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":99,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use Reasoning From Scratch in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 86/100 Production candidate","Audit: 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":"rasbt-reasoning-from-scratch (Reasoning From Scratch)","install_command":"npx skills add rasbt/reasoning-from-scratch","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":"rasbt-reasoning-from-scratch","task":"Use Reasoning From Scratch in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/rasbt-reasoning-from-scratch","api":"https://www.openagentskill.com/api/agent/skills/rasbt-reasoning-from-scratch","audit":"https://www.openagentskill.com/skills/rasbt-reasoning-from-scratch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=rasbt-reasoning-from-scratch&task=Use%20Reasoning%20From%20Scratch%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20Reasoning%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20Reasoning%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/rasbt-reasoning-from-scratch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/rasbt-reasoning-from-scratch"}},"platforms":["Jupyter Notebook","Machine Learning"],"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"slug":"data-analysis","title":"Data analysis","url":"https://www.openagentskill.com/use-cases/data-analysis"},{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"}],"install":"npx skills add rasbt/reasoning-from-scratch","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add rasbt/reasoning-from-scratch","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"Reasoning From Scratch\" agent skill from https://github.com/rasbt/reasoning-from-scratch. 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: Implement a reasoning LLM in PyTorch from scratch, step by step","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 \"Reasoning From Scratch\" as a Claude Code skill from https://github.com/rasbt/reasoning-from-scratch. 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: Implement a reasoning LLM in PyTorch from scratch, step by step","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 \"Reasoning From Scratch\" from https://github.com/rasbt/reasoning-from-scratch 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: Implement a reasoning LLM in PyTorch from scratch, step by step","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/rasbt/reasoning-from-scratch","github_repo":"rasbt/reasoning-from-scratch","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-06-16T09:27:03.37947+00:00","canonical_key":"rasbt/reasoning-from-scratch","recommendation_reasons":["Matches task terms: from, scratch","Useful GitHub adoption: 4,516 stars","Install handoff is available","Repository freshness signal is available","Registry match score 20"],"urls":{"web":"https://www.openagentskill.com/skills/rasbt-reasoning-from-scratch","api":"https://www.openagentskill.com/api/agent/skills/rasbt-reasoning-from-scratch","install_api":"https://www.openagentskill.com/api/skills/rasbt-reasoning-from-scratch/install","audit":"https://www.openagentskill.com/skills/rasbt-reasoning-from-scratch/audit","repository":"https://github.com/rasbt/reasoning-from-scratch"}},{"rank":7,"match_score":19,"raw_match_score":167.8,"slug":"aadi1011-ai-ml-roadmap-from-scratch","name":"AI ML Roadmap From Scratch","description":"Become skilled in Artificial Intelligence, Machine Learning, Generative AI, Deep Learning, Data Science, Natural Language Processing, Reinforcement Learning and more with this complete 0 to 100 repository.","tagline":"Become skilled in Artificial Intelligence, Machine Learning, Generative AI, Deep Learning, Data Science, Natural Language Processing, Reinforcement Learning and more with this complete 0 to 100 repository.","category":"ml-automation","tags":["machine-learning","automation","ml-media","ai","aiml","artificial-intelligence","data-science","deep-learning","hacktoberfest","hacktoberfest2025"],"author":{"name":"aadi1011","verified":true,"url":"https://github.com/aadi1011"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"aadi1011/AI-ML-Roadmap-from-scratch","creatorName":"aadi1011","creatorUrl":"https://github.com/aadi1011","sourceUrl":"https://github.com/aadi1011/AI-ML-Roadmap-from-scratch","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/aadi1011-ai-ml-roadmap-from-scratch#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":3738,"forks":706,"downloads":0,"rating":0,"review_count":0,"quality_score":63.71},"quality":{"score":95,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"3.7K","tone":"positive"},{"label":"Freshness","value":"3mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":85,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"3.7K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"3.7K stars, 706 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":76,"weight":0.14,"status":"info","detail":"3mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"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 aadi1011/AI-ML-Roadmap-from-scratch"},{"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/aadi1011/AI-ML-Roadmap-from-scratch"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"3.7K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"3.7K stars, 706 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"3mo 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 aadi1011/AI-ML-Roadmap-from-scratch"},{"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/aadi1011/AI-ML-Roadmap-from-scratch"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Documentation summary is thin"],"evidence":{"stars":"3.7K GitHub stars","repoActivity":"3.7K stars, 706 forks","lastPushed":"3mo since push","license":"MIT","repository":"https://github.com/aadi1011/AI-ML-Roadmap-from-scratch","install":"npx skills add aadi1011/AI-ML-Roadmap-from-scratch","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add aadi1011/AI-ML-Roadmap-from-scratch","policy":"human_review_before_install","label":"Human review before install","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","3mo since push"]},"agentCompatibility":["Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["ml-automation","machine-learning","automation","ml-media","ai","aiml"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Documentation summary is thin"]},"safety":{"score":72,"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","72/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","72/100 agent safety score"]},"supply_profile":{"track":{"slug":"coding","label":"Coding and developer agents","shortLabel":"Coding","description":"Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills."},"scenario":{"label":"GitHub automation","description":"I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.","useCases":[{"slug":"github-automation","title":"GitHub automation"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"browser-automation","title":"Browser automation"}]},"applicableAgents":["Claude Code","CLI","Codex","Cursor","Machine Learning"],"install":{"ready":true,"command":"npx skills add aadi1011/AI-ML-Roadmap-from-scratch","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":3738,"starsLabel":"3.7K","forks":706,"license":"MIT","qualityScore":95,"trustScore":85,"auditScore":88},"maintenance":{"status":"active","label":"3mo since push","daysSincePush":91,"lastPushedAt":"2026-05-03T11:16:20+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Coding","GitHub automation","ml-automation","machine-learning","automation","ml-media","ai","aiml"]},"audit":{"audit_score":88,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for GitHub automation","role":"Primary pick","primary_fit":"GitHub automation","best_for":["GitHub automation 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 GitHub automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"aadi1011-ai-ml-roadmap-from-scratch","name":"AI ML Roadmap From Scratch","description":"Become skilled in Artificial Intelligence, Machine Learning, Generative AI, Deep Learning, Data Science, Natural Language Processing, Reinforcement Learning and more with this complete 0 to 100 repository.","category":"ml-automation","url":"https://www.openagentskill.com/skills/aadi1011-ai-ml-roadmap-from-scratch","repository":"https://github.com/aadi1011/AI-ML-Roadmap-from-scratch","github_repo":"aadi1011/AI-ML-Roadmap-from-scratch"},"suited_tasks":["GitHub automation workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add aadi1011/AI-ML-Roadmap-from-scratch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add aadi1011/AI-ML-Roadmap-from-scratch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"AI ML Roadmap From Scratch\" agent skill from https://github.com/aadi1011/AI-ML-Roadmap-from-scratch. 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: Become skilled in Artificial Intelligence, Machine Learning, Generative AI, Deep Learning, Data Science, Natural Language Processing, Reinforcement Learning and more with this complete 0 to 100 repository."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"AI ML Roadmap From Scratch\" as a Claude Code skill from https://github.com/aadi1011/AI-ML-Roadmap-from-scratch. 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: Become skilled in Artificial Intelligence, Machine Learning, Generative AI, Deep Learning, Data Science, Natural Language Processing, Reinforcement Learning and more with this complete 0 to 100 repository."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"AI ML Roadmap From Scratch\" from https://github.com/aadi1011/AI-ML-Roadmap-from-scratch 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: Become skilled in Artificial Intelligence, Machine Learning, Generative AI, Deep Learning, Data Science, Natural Language Processing, Reinforcement Learning and more with this complete 0 to 100 repository."}],"handoff_url":"https://www.openagentskill.com/api/skills/aadi1011-ai-ml-roadmap-from-scratch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/aadi1011-ai-ml-roadmap-from-scratch"},"trust":{"score":85,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"3.7K GitHub stars","repoActivity":"3.7K stars, 706 forks","lastPushed":"3mo since push","license":"MIT","repository":"https://github.com/aadi1011/AI-ML-Roadmap-from-scratch","install":"npx skills add aadi1011/AI-ML-Roadmap-from-scratch","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["ml-automation","machine-learning","automation","ml-media","ai","aiml"],"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":88,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":95,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"3mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use AI ML Roadmap From Scratch in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 85/100 Strong shortlist","Audit: 88/100 Safe to try","Safety: 72/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"aadi1011-ai-ml-roadmap-from-scratch (AI ML Roadmap From Scratch)","install_command":"npx skills add aadi1011/AI-ML-Roadmap-from-scratch","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":"aadi1011-ai-ml-roadmap-from-scratch","task":"Use AI ML Roadmap From Scratch in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/aadi1011-ai-ml-roadmap-from-scratch","api":"https://www.openagentskill.com/api/agent/skills/aadi1011-ai-ml-roadmap-from-scratch","audit":"https://www.openagentskill.com/skills/aadi1011-ai-ml-roadmap-from-scratch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=aadi1011-ai-ml-roadmap-from-scratch&task=Use%20AI%20ML%20Roadmap%20From%20Scratch%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20AI%20ML%20Roadmap%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20AI%20ML%20Roadmap%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/aadi1011-ai-ml-roadmap-from-scratch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/aadi1011-ai-ml-roadmap-from-scratch"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"aadi1011-ai-ml-roadmap-from-scratch","name":"AI ML Roadmap From Scratch","description":"Become skilled in Artificial Intelligence, Machine Learning, Generative AI, Deep Learning, Data Science, Natural Language Processing, Reinforcement Learning and more with this complete 0 to 100 repository.","category":"ml-automation","url":"https://www.openagentskill.com/skills/aadi1011-ai-ml-roadmap-from-scratch","repository":"https://github.com/aadi1011/AI-ML-Roadmap-from-scratch","github_repo":"aadi1011/AI-ML-Roadmap-from-scratch"},"suited_tasks":["GitHub automation workflows","Claude Code teams","teams that value GitHub adoption signals","Inspect repository metadata","Compare code changes","Write concise engineering summaries","Inspect source files","Explain architecture"],"suited_agents":["Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add aadi1011/AI-ML-Roadmap-from-scratch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add aadi1011/AI-ML-Roadmap-from-scratch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"AI ML Roadmap From Scratch\" agent skill from https://github.com/aadi1011/AI-ML-Roadmap-from-scratch. 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: Become skilled in Artificial Intelligence, Machine Learning, Generative AI, Deep Learning, Data Science, Natural Language Processing, Reinforcement Learning and more with this complete 0 to 100 repository."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"AI ML Roadmap From Scratch\" as a Claude Code skill from https://github.com/aadi1011/AI-ML-Roadmap-from-scratch. 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: Become skilled in Artificial Intelligence, Machine Learning, Generative AI, Deep Learning, Data Science, Natural Language Processing, Reinforcement Learning and more with this complete 0 to 100 repository."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"AI ML Roadmap From Scratch\" from https://github.com/aadi1011/AI-ML-Roadmap-from-scratch 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: Become skilled in Artificial Intelligence, Machine Learning, Generative AI, Deep Learning, Data Science, Natural Language Processing, Reinforcement Learning and more with this complete 0 to 100 repository."}],"handoff_url":"https://www.openagentskill.com/api/skills/aadi1011-ai-ml-roadmap-from-scratch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/aadi1011-ai-ml-roadmap-from-scratch"},"trust":{"score":85,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"3.7K GitHub stars","repoActivity":"3.7K stars, 706 forks","lastPushed":"3mo since push","license":"MIT","repository":"https://github.com/aadi1011/AI-ML-Roadmap-from-scratch","install":"npx skills add aadi1011/AI-ML-Roadmap-from-scratch","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":false,"sandbox_required":true,"reason":"Human review or sandbox validation is required before automatic installation."},"best_for":["ml-automation","machine-learning","automation","ml-media","ai","aiml"],"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":88,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":95,"label":"Excellent"},"supply":{"track":"Coding and developer agents","scenario":"GitHub automation","maintenance":"3mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"agent_contract":{"task_input":"Use AI ML Roadmap From Scratch in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 85/100 Strong shortlist","Audit: 88/100 Safe to try","Safety: 72/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"aadi1011-ai-ml-roadmap-from-scratch (AI ML Roadmap From Scratch)","install_command":"npx skills add aadi1011/AI-ML-Roadmap-from-scratch","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":"aadi1011-ai-ml-roadmap-from-scratch","task":"Use AI ML Roadmap From Scratch in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/aadi1011-ai-ml-roadmap-from-scratch","api":"https://www.openagentskill.com/api/agent/skills/aadi1011-ai-ml-roadmap-from-scratch","audit":"https://www.openagentskill.com/skills/aadi1011-ai-ml-roadmap-from-scratch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=aadi1011-ai-ml-roadmap-from-scratch&task=Use%20AI%20ML%20Roadmap%20From%20Scratch%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20AI%20ML%20Roadmap%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20AI%20ML%20Roadmap%20From%20Scratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/aadi1011-ai-ml-roadmap-from-scratch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/aadi1011-ai-ml-roadmap-from-scratch"}},"platforms":["Machine Learning","Claude Code"],"use_cases":[{"slug":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"},{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"}],"install":"npx skills add aadi1011/AI-ML-Roadmap-from-scratch","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add aadi1011/AI-ML-Roadmap-from-scratch","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"AI ML Roadmap From Scratch\" agent skill from https://github.com/aadi1011/AI-ML-Roadmap-from-scratch. 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: Become skilled in Artificial Intelligence, Machine Learning, Generative AI, Deep Learning, Data Science, Natural Language Processing, Reinforcement Learning and more with this complete 0 to 100 repository.","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 \"AI ML Roadmap From Scratch\" as a Claude Code skill from https://github.com/aadi1011/AI-ML-Roadmap-from-scratch. 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: Become skilled in Artificial Intelligence, Machine Learning, Generative AI, Deep Learning, Data Science, Natural Language Processing, Reinforcement Learning and more with this complete 0 to 100 repository.","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 \"AI ML Roadmap From Scratch\" from https://github.com/aadi1011/AI-ML-Roadmap-from-scratch 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: Become skilled in Artificial Intelligence, Machine Learning, Generative AI, Deep Learning, Data Science, Natural Language Processing, Reinforcement Learning and more with this complete 0 to 100 repository.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/aadi1011/AI-ML-Roadmap-from-scratch","github_repo":"aadi1011/AI-ML-Roadmap-from-scratch","version":"1.0.0","license":"MIT","updated_at":"2026-06-16T09:35:49.197341+00:00","canonical_key":"aadi1011/ai-ml-roadmap-from-scratch","recommendation_reasons":["Matches task terms: from, scratch","Useful GitHub adoption: 3,738 stars","Install handoff is available","Repository freshness signal is available","Registry match score 19"],"urls":{"web":"https://www.openagentskill.com/skills/aadi1011-ai-ml-roadmap-from-scratch","api":"https://www.openagentskill.com/api/agent/skills/aadi1011-ai-ml-roadmap-from-scratch","install_api":"https://www.openagentskill.com/api/skills/aadi1011-ai-ml-roadmap-from-scratch/install","audit":"https://www.openagentskill.com/skills/aadi1011-ai-ml-roadmap-from-scratch/audit","repository":"https://github.com/aadi1011/AI-ML-Roadmap-from-scratch"}},{"rank":8,"match_score":19,"raw_match_score":162.3,"slug":"qiaohaoforever-deeplearningfromscratch","name":"DeepLearningFromScratch","description":"《深度学习入门：基于Python的理论与实现》电子版及配套代码​。​","tagline":"《深度学习入门：基于Python的理论与实现》电子版及配套代码​。​","category":"document-processing","tags":["pdf","documents","extraction","code","machine-learning","python","github"],"author":{"name":"qiaohaoforever","verified":true,"url":"https://github.com/qiaohaoforever"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"qiaohaoforever/DeepLearningFromScratch","creatorName":"qiaohaoforever","creatorUrl":"https://github.com/qiaohaoforever","sourceUrl":"https://github.com/qiaohaoforever/DeepLearningFromScratch","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/qiaohaoforever-deeplearningfromscratch#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":1133,"forks":271,"downloads":0,"rating":0,"review_count":0,"quality_score":52.08},"quality":{"score":78,"tier":"strong","label":"Strong","summary":"Solid option that is likely worth shortlisting for production workflows.","signals":[{"label":"GitHub stars","value":"1.1K","tone":"positive"},{"label":"Freshness","value":"8mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"MIT","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":82,"tier":"strong","label":"Strong shortlist","summary":"Good trust signals with a few areas worth checking before rollout.","recommendedAction":"Test in a sandbox workflow and compare its install path with close alternatives.","dimensions":[{"id":"github_adoption","label":"GitHub adoption","score":86,"weight":0.13,"status":"pass","detail":"1.1K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"1.1K stars, 271 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":62,"weight":0.14,"status":"info","detail":"8mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"MIT"},{"id":"documentation","label":"README/SKILL.md completeness","score":50,"weight":0.14,"status":"warn","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add qiaohaoforever/DeepLearningFromScratch"},{"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/qiaohaoforever/DeepLearningFromScratch"},{"id":"review_status","label":"Review status","score":88,"weight":0.05,"status":"pass","detail":"AI review data available"},{"id":"agent_outcomes","label":"Agent Proven outcomes","score":54,"weight":0.13,"status":"info","detail":"No agent outcome data yet"}],"checks":[{"status":"pass","label":"GitHub adoption","detail":"1.1K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"1.1K stars, 271 forks; issue activity unavailable in current metadata"},{"status":"info","label":"Recent maintenance","detail":"8mo 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 qiaohaoforever/DeepLearningFromScratch"},{"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/qiaohaoforever/DeepLearningFromScratch"},{"status":"pass","label":"Review status","detail":"AI review data available"},{"status":"info","label":"Agent Proven outcomes","detail":"No agent outcome data yet"},{"status":"pass","label":"Ownership","detail":"Listing manually verified"},{"status":"info","label":"OpenAgentSkill usage","detail":"No local usage activity yet"},{"status":"info","label":"Agent outcomes","detail":"No agent outcome data yet"}],"strengths":["Manually verified listing","AI review approved","Install path is available","Repository evidence is available","Meaningful GitHub adoption signal","Install command has no obvious high-risk pattern"],"warnings":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"],"evidence":{"stars":"1.1K GitHub stars","repoActivity":"1.1K stars, 271 forks","lastPushed":"8mo since push","license":"MIT","repository":"https://github.com/qiaohaoforever/DeepLearningFromScratch","install":"npx skills add qiaohaoforever/DeepLearningFromScratch","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document access","documentation":"Thin public metadata","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add qiaohaoforever/DeepLearningFromScratch","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","8mo since push"]},"agentCompatibility":["Python","PDF","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"medium","label":"Review before production","notes":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":false,"sandboxRequired":true,"policy":"human_review_before_install","reason":"Human review or sandbox validation is required before automatic installation."},"bestFor":["document-processing","pdf","documents","extraction","code","machine-learning"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface","Automatic installation in a production workspace"],"knownRisks":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"safety":{"score":63,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","summary":"Usable candidate, but the agent should surface permission and audit notes before installation.","recommended_action":"Require human approval before installing into a real workspace.","auto_install_policy":"review","reasons":["Documentation summary is thin","63/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"needs_review","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"},{"id":"filesystem","label":"Filesystem access","reason":"Skill may read or write project files, documents, generated artifacts, or local workspace state.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed with permission notes","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Require human approval before installing into a real workspace.","reasons":["Documentation summary is thin","63/100 agent safety score"]},"supply_profile":{"track":{"slug":"research","label":"Research and knowledge work","shortLabel":"Research","description":"Deep research, source comparison, literature review, RAG, knowledge search, and reports."},"scenario":{"label":"Document processing","description":"I need my agent to read PDFs, extract tables, and turn documents into structured data.","useCases":[{"slug":"document-processing","title":"Document processing"},{"slug":"coding-agents","title":"Coding agents"},{"slug":"rag-knowledge","title":"RAG and knowledge"}]},"applicableAgents":["CLI","Codex","Claude Code","Cursor","Python"],"install":{"ready":true,"command":"npx skills add qiaohaoforever/DeepLearningFromScratch","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":1133,"starsLabel":"1.1K","forks":271,"license":"MIT","qualityScore":78,"trustScore":82,"auditScore":79},"maintenance":{"status":"stable","label":"8mo since push","daysSincePush":246,"lastPushedAt":"2025-11-29T06:46:10+00:00"},"risk":{"level":"needs_review","label":"Needs review","requiresReview":true,"notes":["Documentation summary is thin","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Needs review"]},"coverageTags":["Research","Document processing","document-processing","pdf","documents","extraction","code","machine-learning"]},"audit":{"audit_score":79,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"decision":{"readiness_score":80,"readiness_label":"Strong shortlist","headline":"Companion skill for Document processing","role":"Companion skill","primary_fit":"Document processing","best_for":["Document processing workflows","general agent builders","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Document processing task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"qiaohaoforever-deeplearningfromscratch","name":"DeepLearningFromScratch","description":"《深度学习入门：基于Python的理论与实现》电子版及配套代码​。​","category":"document-processing","url":"https://www.openagentskill.com/skills/qiaohaoforever-deeplearningfromscratch","repository":"https://github.com/qiaohaoforever/DeepLearningFromScratch","github_repo":"qiaohaoforever/DeepLearningFromScratch"},"suited_tasks":["Document processing workflows","general agent builders","teams that value GitHub adoption signals","Read uploaded files","Extract structured fields","Prepare clean context for downstream agents","Inspect source files","Explain architecture"],"suited_agents":["Python","PDF","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add qiaohaoforever/DeepLearningFromScratch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add qiaohaoforever/DeepLearningFromScratch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"DeepLearningFromScratch\" agent skill from https://github.com/qiaohaoforever/DeepLearningFromScratch. 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: 《深度学习入门：基于Python的理论与实现》电子版及配套代码​。​"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"DeepLearningFromScratch\" as a Claude Code skill from https://github.com/qiaohaoforever/DeepLearningFromScratch. 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: 《深度学习入门：基于Python的理论与实现》电子版及配套代码​。​"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"DeepLearningFromScratch\" from https://github.com/qiaohaoforever/DeepLearningFromScratch 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: 《深度学习入门：基于Python的理论与实现》电子版及配套代码​。​"}],"handoff_url":"https://www.openagentskill.com/api/skills/qiaohaoforever-deeplearningfromscratch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/qiaohaoforever-deeplearningfromscratch"},"trust":{"score":82,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"1.1K GitHub stars","repoActivity":"1.1K stars, 271 forks","lastPushed":"8mo since push","license":"MIT","repository":"https://github.com/qiaohaoforever/DeepLearningFromScratch","install":"npx skills add qiaohaoforever/DeepLearningFromScratch","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document 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":["document-processing","pdf","documents","extraction","code","machine-learning"],"known_risks":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":79,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","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":78,"label":"Strong"},"supply":{"track":"Research and knowledge work","scenario":"Document processing","maintenance":"8mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use DeepLearningFromScratch in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 82/100 Strong shortlist","Audit: 79/100 Needs review","Safety: 63/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"qiaohaoforever-deeplearningfromscratch (DeepLearningFromScratch)","install_command":"npx skills add qiaohaoforever/DeepLearningFromScratch","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":"qiaohaoforever-deeplearningfromscratch","task":"Use DeepLearningFromScratch in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/qiaohaoforever-deeplearningfromscratch","api":"https://www.openagentskill.com/api/agent/skills/qiaohaoforever-deeplearningfromscratch","audit":"https://www.openagentskill.com/skills/qiaohaoforever-deeplearningfromscratch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=qiaohaoforever-deeplearningfromscratch&task=Use%20DeepLearningFromScratch%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20DeepLearningFromScratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20DeepLearningFromScratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/qiaohaoforever-deeplearningfromscratch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/qiaohaoforever-deeplearningfromscratch"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"qiaohaoforever-deeplearningfromscratch","name":"DeepLearningFromScratch","description":"《深度学习入门：基于Python的理论与实现》电子版及配套代码​。​","category":"document-processing","url":"https://www.openagentskill.com/skills/qiaohaoforever-deeplearningfromscratch","repository":"https://github.com/qiaohaoforever/DeepLearningFromScratch","github_repo":"qiaohaoforever/DeepLearningFromScratch"},"suited_tasks":["Document processing workflows","general agent builders","teams that value GitHub adoption signals","Read uploaded files","Extract structured fields","Prepare clean context for downstream agents","Inspect source files","Explain architecture"],"suited_agents":["Python","PDF","Codex","Claude Code","Cursor","OpenAgentSkill CLI","CLI"],"install":{"command":"npx skills add qiaohaoforever/DeepLearningFromScratch","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add qiaohaoforever/DeepLearningFromScratch"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"DeepLearningFromScratch\" agent skill from https://github.com/qiaohaoforever/DeepLearningFromScratch. 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: 《深度学习入门：基于Python的理论与实现》电子版及配套代码​。​"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"DeepLearningFromScratch\" as a Claude Code skill from https://github.com/qiaohaoforever/DeepLearningFromScratch. 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: 《深度学习入门：基于Python的理论与实现》电子版及配套代码​。​"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"DeepLearningFromScratch\" from https://github.com/qiaohaoforever/DeepLearningFromScratch 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: 《深度学习入门：基于Python的理论与实现》电子版及配套代码​。​"}],"handoff_url":"https://www.openagentskill.com/api/skills/qiaohaoforever-deeplearningfromscratch/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/qiaohaoforever-deeplearningfromscratch"},"trust":{"score":82,"label":"Strong shortlist","version":"trust-score-v4","install_policy":"human_review_before_install","evidence":{"stars":"1.1K GitHub stars","repoActivity":"1.1K stars, 271 forks","lastPushed":"8mo since push","license":"MIT","repository":"https://github.com/qiaohaoforever/DeepLearningFromScratch","install":"npx skills add qiaohaoforever/DeepLearningFromScratch","installSafety":"standard package or runtime install path","permissionSurface":"filesystem or document 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":["document-processing","pdf","documents","extraction","code","machine-learning"],"known_risks":["Quality score needs review","Documentation summary is thin","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":79,"risk_level":"needs_review","risk_label":"Needs review","warnings":["Documentation summary is thin","Quality score needs review","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":78,"label":"Strong"},"supply":{"track":"Research and knowledge work","scenario":"Document processing","maintenance":"8mo since push","risk":"Needs review"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Quality score needs review","README/SKILL.md completeness: Public metadata needs stronger README/SKILL.md context","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use DeepLearningFromScratch in an agent workflow","recommended_action":"Require human approval before installing into a real workspace.","install_policy":"review","minimum_review_before_use":["Trust: 82/100 Strong shortlist","Audit: 79/100 Needs review","Safety: 63/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"qiaohaoforever-deeplearningfromscratch (DeepLearningFromScratch)","install_command":"npx skills add qiaohaoforever/DeepLearningFromScratch","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":"qiaohaoforever-deeplearningfromscratch","task":"Use DeepLearningFromScratch in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/qiaohaoforever-deeplearningfromscratch","api":"https://www.openagentskill.com/api/agent/skills/qiaohaoforever-deeplearningfromscratch","audit":"https://www.openagentskill.com/skills/qiaohaoforever-deeplearningfromscratch/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=qiaohaoforever-deeplearningfromscratch&task=Use%20DeepLearningFromScratch%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20DeepLearningFromScratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20DeepLearningFromScratch%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/qiaohaoforever-deeplearningfromscratch/install","manifest":"https://www.openagentskill.com/api/registry/manifest/qiaohaoforever-deeplearningfromscratch"}},"platforms":["Python","PDF"],"use_cases":[{"slug":"document-processing","title":"Document processing","url":"https://www.openagentskill.com/use-cases/document-processing"},{"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":"github-automation","title":"GitHub automation","url":"https://www.openagentskill.com/use-cases/github-automation"}],"install":"npx skills add qiaohaoforever/DeepLearningFromScratch","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add qiaohaoforever/DeepLearningFromScratch","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"DeepLearningFromScratch\" agent skill from https://github.com/qiaohaoforever/DeepLearningFromScratch. 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: 《深度学习入门：基于Python的理论与实现》电子版及配套代码​。​","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 \"DeepLearningFromScratch\" as a Claude Code skill from https://github.com/qiaohaoforever/DeepLearningFromScratch. 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: 《深度学习入门：基于Python的理论与实现》电子版及配套代码​。​","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 \"DeepLearningFromScratch\" from https://github.com/qiaohaoforever/DeepLearningFromScratch 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: 《深度学习入门：基于Python的理论与实现》电子版及配套代码​。​","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/qiaohaoforever/DeepLearningFromScratch","github_repo":"qiaohaoforever/DeepLearningFromScratch","version":"1.0.0","license":"MIT","updated_at":"2026-06-25T03:02:28.510609+00:00","canonical_key":"qiaohaoforever/deeplearningfromscratch","recommendation_reasons":["Matches task terms: from, scratch","Useful GitHub adoption: 1,133 stars","Install handoff is available","Repository freshness signal is available","Registry match score 19"],"urls":{"web":"https://www.openagentskill.com/skills/qiaohaoforever-deeplearningfromscratch","api":"https://www.openagentskill.com/api/agent/skills/qiaohaoforever-deeplearningfromscratch","install_api":"https://www.openagentskill.com/api/skills/qiaohaoforever-deeplearningfromscratch/install","audit":"https://www.openagentskill.com/skills/qiaohaoforever-deeplearningfromscratch/audit","repository":"https://github.com/qiaohaoforever/DeepLearningFromScratch"}},{"rank":9,"match_score":12,"raw_match_score":105.4,"slug":"h2oai-h2o-llmstudio","name":"H2o Llmstudio","description":"H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/","tagline":"H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/","category":"support-automation","tags":["chatbot","support","automation","customer-support","ai","chatgpt","fedramp","fine-tuning","finetuning","generative"],"author":{"name":"h2oai","verified":true,"url":"https://github.com/h2oai"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"h2oai/h2o-llmstudio","creatorName":"h2oai","creatorUrl":"https://github.com/h2oai","sourceUrl":"https://github.com/h2oai/h2o-llmstudio","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/h2oai-h2o-llmstudio#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":4977,"forks":530,"downloads":0,"rating":0,"review_count":0,"quality_score":67.58},"quality":{"score":99,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"5.0K","tone":"positive"},{"label":"Freshness","value":"2mo ago","tone":"positive"},{"label":"Install ready","value":"Yes","tone":"positive"},{"label":"License","value":"Apache-2.0","tone":"neutral"}],"warnings":[]},"trust":{"version":"trust-score-v4","score":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":"5.0K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"5.0K stars, 530 forks; issue activity unavailable in current metadata"},{"id":"maintenance","label":"Recent maintenance","score":88,"weight":0.14,"status":"pass","detail":"2mo since push"},{"id":"license","label":"License clarity","score":86,"weight":0.09,"status":"pass","detail":"Apache-2.0"},{"id":"documentation","label":"README/SKILL.md completeness","score":66,"weight":0.14,"status":"info","detail":"Public metadata needs stronger README/SKILL.md context"},{"id":"dependency_risk","label":"Dependency/runtime risk","score":90,"weight":0.12,"status":"pass","detail":"no major dependency risk hints in public metadata"},{"id":"installability","label":"Install availability","score":92,"weight":0.1,"status":"pass","detail":"npx skills add h2oai/h2o-llmstudio"},{"id":"install_safety","label":"Install command safety","score":92,"weight":0.1,"status":"pass","detail":"standard package or runtime install path"},{"id":"permission_surface","label":"Permission surface","score":100,"weight":0.07,"status":"pass","detail":"no high-risk permission surface in public metadata"},{"id":"repository","label":"Repository evidence","score":86,"weight":0.04,"status":"pass","detail":"https://github.com/h2oai/h2o-llmstudio"},{"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":"5.0K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"5.0K stars, 530 forks; issue activity unavailable in current metadata"},{"status":"pass","label":"Recent maintenance","detail":"2mo since push"},{"status":"pass","label":"License clarity","detail":"Apache-2.0"},{"status":"info","label":"README/SKILL.md completeness","detail":"Public metadata needs stronger README/SKILL.md context"},{"status":"pass","label":"Dependency/runtime risk","detail":"no major dependency risk hints in public metadata"},{"status":"pass","label":"Install availability","detail":"npx skills add h2oai/h2o-llmstudio"},{"status":"pass","label":"Install command safety","detail":"standard package or runtime install path"},{"status":"pass","label":"Permission surface","detail":"no high-risk permission surface in public metadata"},{"status":"pass","label":"Repository evidence","detail":"https://github.com/h2oai/h2o-llmstudio"},{"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":"5.0K GitHub stars","repoActivity":"5.0K stars, 530 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/h2oai/h2o-llmstudio","install":"npx skills add h2oai/h2o-llmstudio","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"installReadiness":{"ready":true,"command":"npx skills add h2oai/h2o-llmstudio","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Python","Chatbot","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":["support-automation","chatbot","support","automation","customer-support","ai"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin"]},"safety":{"score":79,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","79/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","79/100 agent safety score"]},"supply_profile":{"track":{"slug":"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":"browser-automation","title":"Browser automation"},{"slug":"customer-support","title":"Customer support"},{"slug":"local-desktop","title":"Local desktop"}]},"applicableAgents":["OpenAI Agents","CLI","Codex","Claude Code","Cursor"],"install":{"ready":true,"command":"npx skills add h2oai/h2o-llmstudio","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":4977,"starsLabel":"5.0K","forks":530,"license":"Apache-2.0","qualityScore":99,"trustScore":88,"auditScore":91},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":57,"lastPushedAt":"2026-06-06T08:16:34+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Coding","Coding agents","support-automation","chatbot","support","automation","customer-support","ai"]},"audit":{"audit_score":91,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Browser automation","role":"Primary pick","primary_fit":"Browser automation","best_for":["Browser automation workflows","OpenAI Agents teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Browser automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"h2oai-h2o-llmstudio","name":"H2o Llmstudio","description":"H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/","category":"support-automation","url":"https://www.openagentskill.com/skills/h2oai-h2o-llmstudio","repository":"https://github.com/h2oai/h2o-llmstudio","github_repo":"h2oai/h2o-llmstudio"},"suited_tasks":["Browser automation workflows","OpenAI Agents teams","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Read user messages","Find relevant knowledge"],"suited_agents":["Python","Chatbot","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add h2oai/h2o-llmstudio","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add h2oai/h2o-llmstudio"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"H2o Llmstudio\" agent skill from https://github.com/h2oai/h2o-llmstudio. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"H2o Llmstudio\" as a Claude Code skill from https://github.com/h2oai/h2o-llmstudio. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"H2o Llmstudio\" from https://github.com/h2oai/h2o-llmstudio into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/"}],"handoff_url":"https://www.openagentskill.com/api/skills/h2oai-h2o-llmstudio/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/h2oai-h2o-llmstudio"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"5.0K GitHub stars","repoActivity":"5.0K stars, 530 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/h2oai/h2o-llmstudio","install":"npx skills add h2oai/h2o-llmstudio","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":["support-automation","chatbot","support","automation","customer-support","ai"],"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":91,"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":99,"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 H2o Llmstudio in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 88/100 Production candidate","Audit: 91/100 Safe to try","Safety: 79/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"h2oai-h2o-llmstudio (H2o Llmstudio)","install_command":"npx skills add h2oai/h2o-llmstudio","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":"h2oai-h2o-llmstudio","task":"Use H2o Llmstudio in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/h2oai-h2o-llmstudio","api":"https://www.openagentskill.com/api/agent/skills/h2oai-h2o-llmstudio","audit":"https://www.openagentskill.com/skills/h2oai-h2o-llmstudio/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=h2oai-h2o-llmstudio&task=Use%20H2o%20Llmstudio%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20H2o%20Llmstudio%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20H2o%20Llmstudio%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/h2oai-h2o-llmstudio/install","manifest":"https://www.openagentskill.com/api/registry/manifest/h2oai-h2o-llmstudio"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"h2oai-h2o-llmstudio","name":"H2o Llmstudio","description":"H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/","category":"support-automation","url":"https://www.openagentskill.com/skills/h2oai-h2o-llmstudio","repository":"https://github.com/h2oai/h2o-llmstudio","github_repo":"h2oai/h2o-llmstudio"},"suited_tasks":["Browser automation workflows","OpenAI Agents teams","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Read user messages","Find relevant knowledge"],"suited_agents":["Python","Chatbot","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add h2oai/h2o-llmstudio","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add h2oai/h2o-llmstudio"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"H2o Llmstudio\" agent skill from https://github.com/h2oai/h2o-llmstudio. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/"},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"H2o Llmstudio\" as a Claude Code skill from https://github.com/h2oai/h2o-llmstudio. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/"},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"H2o Llmstudio\" from https://github.com/h2oai/h2o-llmstudio into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/"}],"handoff_url":"https://www.openagentskill.com/api/skills/h2oai-h2o-llmstudio/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/h2oai-h2o-llmstudio"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"5.0K GitHub stars","repoActivity":"5.0K stars, 530 forks","lastPushed":"2mo since push","license":"Apache-2.0","repository":"https://github.com/h2oai/h2o-llmstudio","install":"npx skills add h2oai/h2o-llmstudio","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":["support-automation","chatbot","support","automation","customer-support","ai"],"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":91,"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":99,"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 H2o Llmstudio in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 88/100 Production candidate","Audit: 91/100 Safe to try","Safety: 79/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"h2oai-h2o-llmstudio (H2o Llmstudio)","install_command":"npx skills add h2oai/h2o-llmstudio","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":"h2oai-h2o-llmstudio","task":"Use H2o Llmstudio in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/h2oai-h2o-llmstudio","api":"https://www.openagentskill.com/api/agent/skills/h2oai-h2o-llmstudio","audit":"https://www.openagentskill.com/skills/h2oai-h2o-llmstudio/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=h2oai-h2o-llmstudio&task=Use%20H2o%20Llmstudio%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20H2o%20Llmstudio%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20H2o%20Llmstudio%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/h2oai-h2o-llmstudio/install","manifest":"https://www.openagentskill.com/api/registry/manifest/h2oai-h2o-llmstudio"}},"platforms":["Python","Chatbot","OpenAI Agents"],"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"customer-support","title":"Customer support","url":"https://www.openagentskill.com/use-cases/customer-support"},{"slug":"local-desktop","title":"Local desktop","url":"https://www.openagentskill.com/use-cases/local-desktop"},{"slug":"coding-agents","title":"Coding agents","url":"https://www.openagentskill.com/use-cases/coding-agents"}],"install":"npx skills add h2oai/h2o-llmstudio","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add h2oai/h2o-llmstudio","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"H2o Llmstudio\" agent skill from https://github.com/h2oai/h2o-llmstudio. Read its SKILL.md or equivalent instructions first, install only the files needed for this workspace, and summarize any required setup before using it. Skill purpose: H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/","description":"Give Codex a repo-aware install prompt when the skill is not available through a local CLI.","copyLabel":"Copy prompt"},{"id":"claude-code","label":"Claude Code","title":"Claude Code skill prompt","kind":"agent-prompt","value":"Add \"H2o Llmstudio\" as a Claude Code skill from https://github.com/h2oai/h2o-llmstudio. Inspect the skill instructions, place the reusable skill files in the appropriate local skills location for this project, and report the activation steps. Skill purpose: H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/","description":"Use this prompt to ask Claude Code to add the skill and explain the local activation steps.","copyLabel":"Copy prompt"},{"id":"cursor","label":"Cursor","title":"Cursor rule prompt","kind":"agent-prompt","value":"Turn \"H2o Llmstudio\" from https://github.com/h2oai/h2o-llmstudio into a reusable Cursor project rule or agent instruction. Preserve the core workflow, adapt paths to this repo, and keep the rule scoped to tasks where it is relevant. Skill purpose: H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/h2oai/h2o-llmstudio","github_repo":"h2oai/h2o-llmstudio","version":"1.0.0","license":"Apache-2.0","updated_at":"2026-06-16T10:06:42.987333+00:00","canonical_key":"h2oai/h2o-llmstudio","recommendation_reasons":["Matches task terms: llms","Useful GitHub adoption: 4,977 stars","Install handoff is available","Repository freshness signal is available","Registry match score 12"],"urls":{"web":"https://www.openagentskill.com/skills/h2oai-h2o-llmstudio","api":"https://www.openagentskill.com/api/agent/skills/h2oai-h2o-llmstudio","install_api":"https://www.openagentskill.com/api/skills/h2oai-h2o-llmstudio/install","audit":"https://www.openagentskill.com/skills/h2oai-h2o-llmstudio/audit","repository":"https://github.com/h2oai/h2o-llmstudio"}},{"rank":10,"match_score":12,"raw_match_score":103.1,"slug":"raiyanyahya-how-to-train-your-gpt","name":"How To Train Your Gpt","description":"Build a modern LLM from scratch. Every line commented. Explained like we are five.","tagline":"Build a modern LLM from scratch. Every line commented. Explained like we are five.","category":"ml-automation","tags":["machine-learning","automation","ml-media","attention-mechanism","deep-learning","educational","from-scratch","gpt","language-model","llama"],"author":{"name":"raiyanyahya","verified":true,"url":"https://github.com/raiyanyahya"},"attribution":{"status":"community_indexed","statusLabel":"Community indexed","shortLabel":"COMMUNITY INDEXED","sourceLabel":"GitHub star discovery","sourceDetail":"raiyanyahya/how-to-train-your-gpt","creatorName":"raiyanyahya","creatorUrl":"https://github.com/raiyanyahya","sourceUrl":"https://github.com/raiyanyahya/how-to-train-your-gpt","indexedBy":"OpenAgentSkill community index","claimUrl":"https://www.openagentskill.com/skills/raiyanyahya-how-to-train-your-gpt#claim-this-skill","claimCta":"Claim this skill","trustNote":"This listing was indexed from public sources and is not marked official until a maintainer claim is approved.","publicNote":"Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals."},"stats":{"stars":2250,"forks":300,"downloads":0,"rating":0,"review_count":0,"quality_score":65.17},"quality":{"score":96,"tier":"excellent","label":"Excellent","summary":"High-confidence pick with strong adoption and healthy maintenance signals.","signals":[{"label":"GitHub stars","value":"2.3K","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":"2.3K GitHub stars"},{"id":"repo_activity","label":"Stars/forks activity","score":83,"weight":0.08,"status":"pass","detail":"2.3K stars, 300 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 raiyanyahya/how-to-train-your-gpt"},{"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/raiyanyahya/how-to-train-your-gpt"},{"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":"2.3K GitHub stars"},{"status":"pass","label":"Stars/forks activity","detail":"2.3K stars, 300 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 raiyanyahya/how-to-train-your-gpt"},{"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/raiyanyahya/how-to-train-your-gpt"},{"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":"2.3K GitHub stars","repoActivity":"2.3K stars, 300 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/raiyanyahya/how-to-train-your-gpt","install":"npx skills add raiyanyahya/how-to-train-your-gpt","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 raiyanyahya/how-to-train-your-gpt","policy":"agent_install_candidate","label":"Agent install candidate","notes":["Install path is available","Repository evidence is available","License is declared","No Agent Proven outcome evidence yet","2mo since push"]},"agentCompatibility":["Jupyter Notebook","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI"],"riskSummary":{"level":"low","label":"Low metadata risk","notes":["Documentation summary is thin"]},"outcomeEvidence":{"total":0,"successes":0,"failures":0,"notRelevant":0,"successRate":null,"installAttempts":0,"riskBlocked":0,"setupRequired":0,"installSuccessRate":null,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"recentSuccessRate":null,"recentFailureRate":null,"uniqueAgents":0,"agentProvenScore":0,"agentProvenLabel":"Needs first agent run","lastOutcomeAt":null,"label":"No agent outcome data yet"},"autoInstall":{"allowed":true,"sandboxRequired":true,"policy":"agent_install_candidate","reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"bestFor":["ml-automation","machine-learning","automation","ml-media","attention-mechanism","deep-learning"],"doNotUseFor":["Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"knownRisks":["Documentation summary is thin"]},"safety":{"score":78,"level":"review_before_install","label":"Review before install","safety_tier":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","summary":"Good audit and safety signals with no high-risk permission hints in public metadata.","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","auto_install_policy":"review","reasons":["Safe-to-try audit","78/100 agent safety score"]},"auto_install_allowed":false,"human_review_required":true,"blocked":false,"audit_risk":"safe_to_try","permission_hints":[{"id":"network","label":"Network access","reason":"Skill likely fetches remote pages, APIs, repositories, or external services.","severity":"medium"}],"policy_warnings":["Documentation summary is thin"],"constraints_applied":{"max_risk":"medium","needs_install_command":true,"min_stars":0}},"safety_gate":{"tier":"reviewed","label":"Reviewed","badge":"REVIEWED","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","reasons":["Safe-to-try audit","78/100 agent safety score"]},"supply_profile":{"track":{"slug":"design","label":"Design and creative production","shortLabel":"Design","description":"Design assets, images, video, audio, multimodal media, presentation, and creative production skills."},"scenario":{"label":"Multimodal media","description":"I need my agent to process images, video, or audio and extract useful information.","useCases":[{"slug":"browser-automation","title":"Browser automation"},{"slug":"workflow-automation","title":"Workflow automation"},{"slug":"data-analysis","title":"Data analysis"}]},"applicableAgents":["OpenAI Agents","CLI","Codex","Claude Code","Cursor"],"install":{"ready":true,"command":"npx skills add raiyanyahya/how-to-train-your-gpt","primaryTarget":"CLI","targetCount":4},"githubQuality":{"stars":2250,"starsLabel":"2.3K","forks":300,"license":"MIT","qualityScore":96,"trustScore":88,"auditScore":90},"maintenance":{"status":"active","label":"2mo since push","daysSincePush":50,"lastPushedAt":"2026-06-13T19:26:21+00:00"},"risk":{"level":"safe_to_try","label":"Safe to try","requiresReview":true,"notes":["Documentation summary is thin"]},"coverageTags":["Design","Multimodal media","ml-automation","machine-learning","automation","ml-media","attention-mechanism","deep-learning"]},"audit":{"audit_score":90,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"decision":{"readiness_score":100,"readiness_label":"Production-ready","headline":"Primary pick for Browser automation","role":"Primary pick","primary_fit":"Browser automation","best_for":["Browser automation workflows","OpenAI Agents teams","teams that value GitHub adoption signals"],"risks":["No OpenAgentSkill engagement data yet"],"next_steps":["Install it in a sandbox agent and run one Browser automation task end to end.","Compare output quality, latency, and failure behavior against at least one alternative.","Promote it into production only after reviewing repository permissions, license, and maintenance signals."]},"agent_readable_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"raiyanyahya-how-to-train-your-gpt","name":"How To Train Your Gpt","description":"Build a modern LLM from scratch. Every line commented. Explained like we are five.","category":"ml-automation","url":"https://www.openagentskill.com/skills/raiyanyahya-how-to-train-your-gpt","repository":"https://github.com/raiyanyahya/how-to-train-your-gpt","github_repo":"raiyanyahya/how-to-train-your-gpt"},"suited_tasks":["Browser automation workflows","OpenAI Agents teams","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Move data between tools","Transform files"],"suited_agents":["Jupyter Notebook","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add raiyanyahya/how-to-train-your-gpt","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add raiyanyahya/how-to-train-your-gpt"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"How To Train Your Gpt\" agent skill from https://github.com/raiyanyahya/how-to-train-your-gpt. 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: Build a modern LLM from scratch. Every line commented. Explained like we are five."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"How To Train Your Gpt\" as a Claude Code skill from https://github.com/raiyanyahya/how-to-train-your-gpt. 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: Build a modern LLM from scratch. Every line commented. Explained like we are five."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"How To Train Your Gpt\" from https://github.com/raiyanyahya/how-to-train-your-gpt 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: Build a modern LLM from scratch. Every line commented. Explained like we are five."}],"handoff_url":"https://www.openagentskill.com/api/skills/raiyanyahya-how-to-train-your-gpt/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/raiyanyahya-how-to-train-your-gpt"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"2.3K GitHub stars","repoActivity":"2.3K stars, 300 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/raiyanyahya/how-to-train-your-gpt","install":"npx skills add raiyanyahya/how-to-train-your-gpt","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["ml-automation","machine-learning","automation","ml-media","attention-mechanism","deep-learning"],"known_risks":["Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":90,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":96,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use How To Train Your Gpt in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 88/100 Production candidate","Audit: 90/100 Safe to try","Safety: 78/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"raiyanyahya-how-to-train-your-gpt (How To Train Your Gpt)","install_command":"npx skills add raiyanyahya/how-to-train-your-gpt","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":"raiyanyahya-how-to-train-your-gpt","task":"Use How To Train Your Gpt in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/raiyanyahya-how-to-train-your-gpt","api":"https://www.openagentskill.com/api/agent/skills/raiyanyahya-how-to-train-your-gpt","audit":"https://www.openagentskill.com/skills/raiyanyahya-how-to-train-your-gpt/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=raiyanyahya-how-to-train-your-gpt&task=Use%20How%20To%20Train%20Your%20Gpt%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20How%20To%20Train%20Your%20Gpt%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20How%20To%20Train%20Your%20Gpt%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/raiyanyahya-how-to-train-your-gpt/install","manifest":"https://www.openagentskill.com/api/registry/manifest/raiyanyahya-how-to-train-your-gpt"}},"machine_metadata":{"version":"openagentskill-agent-metadata-v2","skill":{"slug":"raiyanyahya-how-to-train-your-gpt","name":"How To Train Your Gpt","description":"Build a modern LLM from scratch. Every line commented. Explained like we are five.","category":"ml-automation","url":"https://www.openagentskill.com/skills/raiyanyahya-how-to-train-your-gpt","repository":"https://github.com/raiyanyahya/how-to-train-your-gpt","github_repo":"raiyanyahya/how-to-train-your-gpt"},"suited_tasks":["Browser automation workflows","OpenAI Agents teams","teams that value GitHub adoption signals","Navigate pages","Click and type safely","Check visual and DOM state","Move data between tools","Transform files"],"suited_agents":["Jupyter Notebook","Machine Learning","Codex","Claude Code","Cursor","OpenAgentSkill CLI","OpenAI Agents","CLI"],"install":{"command":"npx skills add raiyanyahya/how-to-train-your-gpt","ready":true,"targets":[{"id":"openagentskill-cli","label":"CLI","kind":"command","value":"npx skills add raiyanyahya/how-to-train-your-gpt"},{"id":"codex","label":"Codex","kind":"agent-prompt","value":"Install the \"How To Train Your Gpt\" agent skill from https://github.com/raiyanyahya/how-to-train-your-gpt. 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: Build a modern LLM from scratch. Every line commented. Explained like we are five."},{"id":"claude-code","label":"Claude Code","kind":"agent-prompt","value":"Add \"How To Train Your Gpt\" as a Claude Code skill from https://github.com/raiyanyahya/how-to-train-your-gpt. 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: Build a modern LLM from scratch. Every line commented. Explained like we are five."},{"id":"cursor","label":"Cursor","kind":"agent-prompt","value":"Turn \"How To Train Your Gpt\" from https://github.com/raiyanyahya/how-to-train-your-gpt 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: Build a modern LLM from scratch. Every line commented. Explained like we are five."}],"handoff_url":"https://www.openagentskill.com/api/skills/raiyanyahya-how-to-train-your-gpt/install","manifest_url":"https://www.openagentskill.com/api/registry/manifest/raiyanyahya-how-to-train-your-gpt"},"trust":{"score":88,"label":"Production candidate","version":"trust-score-v4","install_policy":"agent_install_candidate","evidence":{"stars":"2.3K GitHub stars","repoActivity":"2.3K stars, 300 forks","lastPushed":"2mo since push","license":"MIT","repository":"https://github.com/raiyanyahya/how-to-train-your-gpt","install":"npx skills add raiyanyahya/how-to-train-your-gpt","installSafety":"standard package or runtime install path","permissionSurface":"no high-risk permission surface in public metadata","documentation":"Usable metadata, review docs","agentOutcomes":"No agent outcome data yet"},"outcome_evidence":{"total":0,"successes":0,"failures":0,"not_relevant":0,"success_rate":null,"recent_success_rate":null,"recent_failure_rate":null,"install_attempts":0,"install_success_rate":null,"risk_blocked":0,"setup_required":0,"avg_output_quality":null,"production_outcomes":0,"last_outcome_at":null,"label":"No agent outcome data yet"},"auto_install":{"allowed":true,"sandbox_required":true,"reason":"Trust Score v4 allows sandbox-first agent installation after normal workspace review."},"best_for":["ml-automation","machine-learning","automation","ml-media","attention-mechanism","deep-learning"],"known_risks":["Documentation summary is thin"]},"agent_proven":{"version":"agent-proven-v1","score":0,"tier":"unproven","label":"Needs first agent run","summary":"No agent outcome reports yet. Use Resolve, run one narrow sandbox task, then report the result.","metrics":{"totalOutcomes":0,"successfulOutcomes":0,"failedOutcomes":0,"installAttempts":0,"installSuccessRate":null,"successRate":null,"recentSuccessRate":null,"recentFailureRate":null,"riskBlocked":0,"setupRequired":0,"notRelevant":0,"avgOutputQuality":null,"avgTimeToUsefulMs":null,"productionOutcomes":0,"humanReviewRequired":0,"uniqueAgents":0,"lastOutcomeAt":null},"signals":[],"penalties":["No real agent outcome evidence yet"]},"audit":{"score":90,"risk_level":"safe_to_try","risk_label":"Safe to try","warnings":["Documentation summary is thin"]},"safety_gate":{"tier":"reviewed","label":"Reviewed","auto_install_policy":"review","auto_install_allowed":false,"human_review_required":true,"blocked":false,"recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow."},"quality":{"score":96,"label":"Excellent"},"supply":{"track":"Design and creative production","scenario":"Multimodal media","maintenance":"2mo since push","risk":"Safe to try"},"alternative_skills":[],"do_not_use_when":["teams that need a vendor-supported SLA","high-compliance environments without internal security review","No OpenAgentSkill engagement data yet","Documentation summary is thin","Production credentials, payments, or irreversible account changes without explicit human review","Sensitive private data before reviewing repository code, license, and permission surface"],"agent_contract":{"task_input":"Use How To Train Your Gpt in an agent workflow","recommended_action":"Review the audit page, then allow agent install in a sandboxed workflow.","install_policy":"review","minimum_review_before_use":["Trust: 88/100 Production candidate","Audit: 90/100 Safe to try","Safety: 78/100 Review before install","Review repository, license, install command, and permission surface before production use."],"expected_agent_output":{"selected_skill":"raiyanyahya-how-to-train-your-gpt (How To Train Your Gpt)","install_command":"npx skills add raiyanyahya/how-to-train-your-gpt","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":"raiyanyahya-how-to-train-your-gpt","task":"Use How To Train Your Gpt in an agent workflow","agent":"codex","outcome":"success","install_used":true,"risk_blocked":false,"setup_required":false,"task_success":true,"output_quality":4,"error_type":null,"human_review_required":false,"workspace":"sandbox","time_to_useful_ms":120000,"notes":"Report the smallest successful task, setup friction, files touched, and risk notes."}},"endpoints":{"web":"https://www.openagentskill.com/skills/raiyanyahya-how-to-train-your-gpt","api":"https://www.openagentskill.com/api/agent/skills/raiyanyahya-how-to-train-your-gpt","audit":"https://www.openagentskill.com/skills/raiyanyahya-how-to-train-your-gpt/audit","eval":"https://www.openagentskill.com/api/agent/evals?slug=raiyanyahya-how-to-train-your-gpt&task=Use%20How%20To%20Train%20Your%20Gpt%20in%20an%20agent%20workflow&max_risk=medium","resolve":"https://www.openagentskill.com/api/agent/resolve?task=Use%20How%20To%20Train%20Your%20Gpt%20in%20an%20agent%20workflow&agent=codex&max_risk=medium","receipt":"https://www.openagentskill.com/api/agent/receipt?task=Use%20How%20To%20Train%20Your%20Gpt%20in%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text","install":"https://www.openagentskill.com/api/skills/raiyanyahya-how-to-train-your-gpt/install","manifest":"https://www.openagentskill.com/api/registry/manifest/raiyanyahya-how-to-train-your-gpt"}},"platforms":["Jupyter Notebook","Machine Learning","OpenAI Agents"],"use_cases":[{"slug":"browser-automation","title":"Browser automation","url":"https://www.openagentskill.com/use-cases/browser-automation"},{"slug":"workflow-automation","title":"Workflow automation","url":"https://www.openagentskill.com/use-cases/workflow-automation"},{"slug":"data-analysis","title":"Data analysis","url":"https://www.openagentskill.com/use-cases/data-analysis"},{"slug":"education-tutoring","title":"Education and tutoring","url":"https://www.openagentskill.com/use-cases/education-tutoring"}],"install":"npx skills add raiyanyahya/how-to-train-your-gpt","install_targets":[{"id":"openagentskill-cli","label":"CLI","title":"OpenAgentSkill CLI","kind":"command","value":"npx skills add raiyanyahya/how-to-train-your-gpt","description":"Use the registry command when your workflow supports the OpenAgentSkill installer.","copyLabel":"Copy command"},{"id":"codex","label":"Codex","title":"Codex install prompt","kind":"agent-prompt","value":"Install the \"How To Train Your Gpt\" agent skill from https://github.com/raiyanyahya/how-to-train-your-gpt. 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: Build a modern LLM from scratch. Every line commented. Explained like we are five.","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 \"How To Train Your Gpt\" as a Claude Code skill from https://github.com/raiyanyahya/how-to-train-your-gpt. 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: Build a modern LLM from scratch. Every line commented. Explained like we are five.","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 \"How To Train Your Gpt\" from https://github.com/raiyanyahya/how-to-train-your-gpt 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: Build a modern LLM from scratch. Every line commented. Explained like we are five.","description":"Use this when installing as Cursor project rules or reusable agent instructions.","copyLabel":"Copy prompt"}],"repository":"https://github.com/raiyanyahya/how-to-train-your-gpt","github_repo":"raiyanyahya/how-to-train-your-gpt","version":"1.0.0","license":"MIT","updated_at":"2026-06-20T21:55:45.828214+00:00","canonical_key":"raiyanyahya/how-to-train-your-gpt","recommendation_reasons":["Matches task terms: from, scratch","Useful GitHub adoption: 2,250 stars","Install handoff is available","Repository freshness signal is available","Registry match score 12"],"urls":{"web":"https://www.openagentskill.com/skills/raiyanyahya-how-to-train-your-gpt","api":"https://www.openagentskill.com/api/agent/skills/raiyanyahya-how-to-train-your-gpt","install_api":"https://www.openagentskill.com/api/skills/raiyanyahya-how-to-train-your-gpt/install","audit":"https://www.openagentskill.com/skills/raiyanyahya-how-to-train-your-gpt/audit","repository":"https://github.com/raiyanyahya/how-to-train-your-gpt"}}],"meta":{"endpoint":"/api/skills/search","canonical_agent_endpoint":"/api/agent/resolve","safety_policy":"Blocked candidates are excluded by default. Pass include_blocked=true only for manual audit workflows.","agent_friendly":true,"api_version":"1.0","generated_at":"2026-08-03T02:51:41.625Z"}}