Karpathy guidelines
Passive guardrail that reduces common LLM coding mistakes. Install globally — enforces think-before-coding, simplicity, and surgical changes automatically whenever writing or reviewing code.From its SKILL.md
npx -y skills add tyecode/skills --skill karpathy-guidelinesAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.2 KB, 234 tokens by cl100k_base, as published. Nobody here has run it
Skill: karpathy-guidelines
When to Use This Skill
This is a passive guardrail — install it globally and it applies automatically. The agent follows these rules whenever it writes, reviews, or refactors code. You do not need to invoke it explicitly.
1. Think Before Coding
- State assumptions explicitly. If uncertain, ask.
- If multiple interpretations exist, present them - don't pick silently.
- If something is unclear, stop. Ask.
2. Simplicity First
- Minimum code that solves the problem.
- No features beyond what was asked.
- No abstractions for single-use code.
- If 200 lines could be 50, rewrite it.
3. Surgical Changes
- Touch only what you must.
- Don't "improve" adjacent code.
- Don't refactor things that aren't broken.
- Remove imports YOUR changes made unused.
4. Goal-Driven Execution
Define success criteria:
- "Add validation" → "Write tests, then make them pass"
- "Fix the bug" → "Write test that reproduces it, then fix"
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.