andrej-karpathy-skills: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM

by multica-ai · AI Tool · ★ 234.4k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

How to install andrej-karpathy-skills

/plugin marketplace add forrestchang/andrej-karpathy-skills
/plugin install andrej-karpathy-skills@karpathy-skills

Taken from the project's README on GitHub. Check the security audit before running it.

Security audit verdict: SAFE · quality 63/100

None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

Quick Facts

Stars234,445
Forks23,303
CategoryAI Tool
Quality Score63/100
Open Issues138
Last Updated2026-04-20
Created2026-01-27
Platformsclaude-code
Est. Tokens~3k

About andrej-karpathy-skills

Karpathy-Inspired Claude Code Guidelines Check out my new project Multica — an open-source platform for running and managing coding agents with reusable skills. Follow me on X: https://x.com/jiayuanjy A single file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

More AI Tool Tools

Explore other popular ai tool tools:

View all AI Tool tools →

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse AI Tool tools