/karpathy-guidelines
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.
shell
$ npx -y skills add 0xwilliamortiz/andrej-karpathy-skills --skill karpathy-guidelines --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/karpathy-guidelines
Context preview
The summary Claude sees to decide when to auto-load this skill.
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.
Ships withandrej-karpathy-skills
Andrej Karpathy named the specific ways LLMs screw up code. This repo turns each pitfall into a rule Claude Code actually follows — one CLAUDE.md, four principles, no silent mistakes.
Get the whole plugin, auto-invoked
Stats
551
Stars
0
Views
95
Forks
Active
Maintenance
MIT
License
9d ago
Last commit
14d ago
Created
Repo: 0xwilliamortiz/andrej-karpathy-skills