Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Install
npx skills add multica-ai/andrej-karpathy-skills --skill karpathy-guidelinesnpx skills add multica-ai/andrej-karpathy-skills --skill karpathy-guidelines -a claude-code -gnpx skills add multica-ai/andrej-karpathy-skills --skill karpathy-guidelines -a codex -ggemini skills install https://github.com/multica-ai/andrej-karpathy-skills.git --path skills/karpathy-guidelinesgh skill install multica-ai/andrej-karpathy-skills karpathy-guidelinesgit clone --depth 1 https://github.com/multica-ai/andrej-karpathy-skills /tmp/multica-ai__andrej-karpathy-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/multica-ai__andrej-karpathy-skills/skills/karpathy-guidelines ~/.claude/skills/karpathy-guidelines # Claude Code
cp -R /tmp/multica-ai__andrej-karpathy-skills/skills/karpathy-guidelines ~/.agents/skills/karpathy-guidelines # Codex, Cursor, Gemini CLI, Copilot, OpenCode