karpathy-guidelines
karpathy guidelines
What it does
- State your assumptions explicitly. If uncertain, ask.
- If multiple interpretations exist, present them - don't pick silently.
- If a simpler approach exists, say so. Push back when warranted.
- If something is unclear, stop. Name what's confusing. Ask.
- No features beyond what was asked.
- No abstractions for single-use code.
- No "flexibility" or "configurability" that wasn't requested.
Requirements & configuration
- Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
Derived from the skill's own SKILL.md documentation · extracted 2026-07-23
karpathy-guidelines FAQ
What does the karpathy-guidelines skill do?
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. State your assumptions explicitly. If uncertain, ask. If multiple interpretations exist, present them - don't pick silently.
What does karpathy-guidelines require?
Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
How do I install karpathy-guidelines?
Run: npx -y skills add https://github.com/multica-ai/andrej-karpathy-skills --skill karpathy-guidelines --agent claude-code — the source lives at github.com/multica-ai/andrej-karpathy-skills.
Maintain karpathy-guidelines?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[](https://getagentictools.com/skills/multica-ai-andrej-karpathy-skills-karpathy-guidelines?ref=badge) npx agentictools info skills/multica-ai-andrej-karpathy-skills-karpathy-guidelines The second line is the CLI lookup for this page — handy in READMEs and docs.
