forrestchang/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
52K stars550 forks+8K today
What it does
This repository provides guidelines derived from Andrej Karpathy's observations on pitfalls in large language model coding to improve the behavior of Claude Code. It outlines four principles aimed at reducing overcomplication and ensuring clarity, simplicity, and goal-driven execution.
Star history
Not enough history yet — 1 day(s) recorded. The daily snapshot builds this up.
Tracking
- Last trending
- 2026-04-25
Creator kit
Hook
Learn how to improve Claude Code behavior with Andrej Karpathy's insights on avoiding common LLM coding pitfalls!
Content angles
- Create a blog post explaining the four principles and their importance in AI development.
- Develop a video tutorial demonstrating how to apply these guidelines in real-world scenarios.
- Write an article analyzing the impact of overcomplicated code on software maintenance.
Who should care
AI developers, machine learning engineers, and software architects interested in improving coding practices for large language models.