{"adoption": {"forks": 21172, "observed_at": "2026-08-28T04:12:28.442511+00:00", "stars": 207708}, "canonical_url": "https://ross.abutalabs.com/products/andrej-karpathy-skills", "card": {"archived": false, "artifact_type": "learning-resource", "description": "A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.", "domain": ["developer-tools", "artificial-intelligence", "large-language-models", "tutorials"], "enriched": true, "function": ["prompt-engineering", "developer-tools", "configuration-management"], "health_score": 67, "homepage": null, "language": null, "license": null, "license_family": "other", "maturity": "active", "member_repos": ["multica-ai/andrej-karpathy-skills"], "name": "multica-ai/andrej-karpathy-skills", "platform": ["cli", "cross-platform"], "pushed_at": "2026-04-20T10:05:04+00:00", "repo": "multica-ai/andrej-karpathy-skills", "stars": 207708, "tags": ["claude-code", "claudemd", "llm-guidelines", "coding-agents", "prompting", "best-practices", "andrej-karpathy", "ai-assistants"], "topics": [], "urls": [], "use_cases": ["make Claude Code stop making silent assumptions and ask clarifying questions", "reduce overengineered and bloated code generated by AI coding agents", "prevent Claude Code from touching unrelated code or comments during edits", "set up behavioral guidelines for AI pair programming in a repository", "get simpler, minimal implementations from LLM coding assistants", "improve code review quality of AI-generated changes"], "what_it_is": "A single CLAUDE.md configuration file that improves Claude Code's coding behavior, based on Andrej Karpathy's observations about LLM coding pitfalls. It encodes four principles—Think Before Coding, Simplicity First, Surgical Changes, and Goal-Driven Execution—as instructions for the AI coding agent.", "when_to_avoid": ["you use coding agents other than Claude Code that don't read CLAUDE.md", "you need executable software or a tool rather than a prompt/configuration file", "you want guaranteed behavior changes rather than soft behavioral guidance"], "when_to_choose": ["you use Claude Code and want better default coding behavior without extra tooling", "your AI agent overcomplicates solutions or makes unverified assumptions", "you want a drop-in, single-file configuration to steer an LLM coding agent"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/andrej-karpathy-skills", "repo": "multica-ai/andrej-karpathy-skills", "role": "main", "score": 50}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:12:28.442511+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T16:10:29.892422+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c8e02b0b7517a44d9ed33e32eab318a4342c4110d10297582e2a722f56edfab8", "fetched_at": "2026-08-28T04:12:28.442511+00:00", "kind": "readme", "missing": false, "url": "https://github.com/multica-ai/andrej-karpathy-skills"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:12:28.442511+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T16:10:29.892422+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c8e02b0b7517a44d9ed33e32eab318a4342c4110d10297582e2a722f56edfab8", "fetched_at": "2026-08-28T04:12:28.442511+00:00", "kind": "readme", "missing": false, "url": "https://github.com/multica-ai/andrej-karpathy-skills"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T16:10:29.892422+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c8e02b0b7517a44d9ed33e32eab318a4342c4110d10297582e2a722f56edfab8", "fetched_at": "2026-08-28T04:12:28.442511+00:00", "kind": "readme", "missing": false, "url": "https://github.com/multica-ai/andrej-karpathy-skills"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:12:28.442511+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:12:28.442511+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:12:28.442511+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T16:10:29.892422+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c8e02b0b7517a44d9ed33e32eab318a4342c4110d10297582e2a722f56edfab8", "fetched_at": "2026-08-28T04:12:28.442511+00:00", "kind": "readme", "missing": false, "url": "https://github.com/multica-ai/andrej-karpathy-skills"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:12:28.442511+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:12:28.442511+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T16:10:29.892422+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c8e02b0b7517a44d9ed33e32eab318a4342c4110d10297582e2a722f56edfab8", "fetched_at": "2026-08-28T04:12:28.442511+00:00", "kind": "readme", "missing": false, "url": "https://github.com/multica-ai/andrej-karpathy-skills"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:12:28.442511+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:12:28.442511+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:12:28.442511+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T16:10:29.892422+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c8e02b0b7517a44d9ed33e32eab318a4342c4110d10297582e2a722f56edfab8", "fetched_at": "2026-08-28T04:12:28.442511+00:00", "kind": "readme", "missing": false, "url": "https://github.com/multica-ai/andrej-karpathy-skills"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:12:28.442511+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:12:28.442511+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T16:10:29.892422+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c8e02b0b7517a44d9ed33e32eab318a4342c4110d10297582e2a722f56edfab8", "fetched_at": "2026-08-28T04:12:28.442511+00:00", "kind": "readme", "missing": false, "url": "https://github.com/multica-ai/andrej-karpathy-skills"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T16:10:29.892422+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c8e02b0b7517a44d9ed33e32eab318a4342c4110d10297582e2a722f56edfab8", "fetched_at": "2026-08-28T04:12:28.442511+00:00", "kind": "readme", "missing": false, "url": "https://github.com/multica-ai/andrej-karpathy-skills"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T16:10:29.892422+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c8e02b0b7517a44d9ed33e32eab318a4342c4110d10297582e2a722f56edfab8", "fetched_at": "2026-08-28T04:12:28.442511+00:00", "kind": "readme", "missing": false, "url": "https://github.com/multica-ai/andrej-karpathy-skills"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T16:10:29.892422+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c8e02b0b7517a44d9ed33e32eab318a4342c4110d10297582e2a722f56edfab8", "fetched_at": "2026-08-28T04:12:28.442511+00:00", "kind": "readme", "missing": false, "url": "https://github.com/multica-ai/andrej-karpathy-skills"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 78, "longevity": 15, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 218, "days_push": 135, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 50, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}