andrej-karpathy-skills packages coding practices for AI into a single CLAUDE.md file, distilled from Andrej Karpathy's observations about how models fail when they write code. It reduces to 4 principles: think before coding, simplicity first, surgical changes, and goal-driven execution. It has over 189,000 GitHub stars. Its whole appeal is that it is minimal, one file, the opposite of superpowers, which is a dozen-plus skills with enforcement gates.
After reviewing superpowers, I kept scanning Claude Code repos and hit another one with a comparable star count: andrej-karpathy-skills, over 189,000 stars. But when I opened it, it was nearly the opposite of superpowers in every way. Superpowers is a dozen-plus skills with gates and machinery. This one is a single CLAUDE.md file, under seventy lines.
What can one file do to earn a couple hundred thousand stars? The answer is that it does not try to teach everything. It picks only the failure habits AI repeats when it writes code, and turns them into short rules the model follows. The source of those rules is a post by Andrej Karpathy on X about where models go wrong when they help you code.
This post goes in order: what it is and who made it, then the 4 principles it teaches, then how it differs from superpowers and which to pick, and finally whether you should install it and how to use it in your own work.
