open-agent-power

Karpathy Guidelines — AI skill for Claude Code

AI community

Behavioral guidelines to reduce common LLM coding mistakes.

How to install Karpathy Guidelines

Installs to ~/.claude/skills/open-agent-power-open-knowledge-studio-karpathy-guidelines/SKILL.md

Terminal

mkdir -p ~/.claude/skills/open-agent-power-open-knowledge-studio-karpathy-guidelines && curl -fsSL https://raw.githubusercontent.com/open-agent-power/open-knowledge-studio/HEAD/.claude/skills/karpathy-guidelines.md -o ~/.claude/skills/open-agent-power-open-knowledge-studio-karpathy-guidelines/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Karpathy Guidelines does

name: karpathy-guidelines description: 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. license: MIT

Karpathy Guidelines

Behavioral guidelines to reduce common LLM coding mistakes, derived from [Andrej Karpathy's observations](https://x.com/karpathy/status/2015883857489522876) on LLM coding pitfalls.

**Tradeoff:**

Alternatives in AI

Claude Cookbook — Official notebooks and recipes for common patterns (RAG, tool use, Skills, MCP) 35.3k ★
Surface — Show ranked attack surface for a target from its recon manifest + hunt memory 3.8k ★
Define — Definition phase - Clarify and scope problems with multi-AI consensus 2.8k ★