# Andrej Karpathy Skills Claude

> CLAUDE.md guidelines that install four principles into Claude Code or other AI coding agents to redu

CLAUDE.md guidelines that install four principles into Claude Code or other AI coding agents to reduce common LLM coding mistakes: stating assumptions before writing code, keeping implementations simple, making surgical edits limited to the requested change, and turning tasks into verifiable success criteria with tests. Use when setting up or improving a CLAUDE.md file for an AI coding agent, or when the agent overcomplicates code, makes unrequested edits, or proceeds on unclear requirements.

- Page: https://ss33.ai/skills/reason-machines/andrej-karpathy-skills-claude-57306787706
- Publisher: reason-machines
- Category: [AI & Agents](https://ss33.ai/skills/category/ai-and-agents-y6jz7i) › [Skill & prompt authoring](https://ss33.ai/skills/category/ai-and-agents-y6jz7i/skill-and-prompt-authoring-p179rh)
- Source: https://github.com/reason-machines/trending-skills/blob/c61b1a456af4015e9a367e0245292281bb3c87d9/skills/andrej-karpathy-skills-claude/SKILL.md

## Skill

This skill's licence does not allow redistribution, so the store does not serve its text. Get it from the author: https://github.com/reason-machines/trending-skills/blob/c61b1a456af4015e9a367e0245292281bb3c87d9/skills/andrej-karpathy-skills-claude/SKILL.md