multica-ai/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
From the publisher
README & documentation
Source previewRead the project’s overview, installation instructions and usage examples. The original README is the source of truth.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. English | 简体中文 From Andrej's post: Four principles in one file that directly address these issues: Don't assume. Don't hide confusion. Surface tradeoffs. LLMs often pick an interpretation silently and run with it. This principle forces explicit reasoning: Minimum code that solves the problem. Nothing speculative. Combat the tendency toward overengineering: The test: Would a senior engineer say this is overcomplicated? If yes, simplify. Touch only what you must. Clean up only your own mess. When editing existing code: When your changes create orphans: The test: Every changed line should trace directly to the user's request. Define success criteria. Loop until verified. Transform imperative tasks into verifiable goals: For multi-step tasks, state a brief plan: Strong success criteria let the LLM loop independently. Weak criteria ("make it work") require constant clarification. Option…
Read the full README ↗ · Preview checked 2026-10-28T14:32:57.916Z
Inside the original README — Document outline
- Karpathy-Inspired Claude Code Guidelines
- The Problems
- The Solution
- The Four Principles in Detail
- 1. Think Before Coding
- 2. Simplicity First
- 3. Surgical Changes
- 4. Goal-Driven Execution
- Install
- Using with Cursor
- Key Insight
- How to Know It's Working
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the README
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
What this repository does
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Repository facts
- Owner
- multica-ai
- Primary language
- Not reported
- Stars
- 227,179
- Forks
- 22,671
- Open issues + pull requests
- 138
- License
- Not reported — inspect the license file
- Archived
- No
- Default branch
- main
- Created
- 2026-01-27T03:53:13.000Z
- Last push
- 2026-04-20T10:05:04.000Z
Topics and intended use
No topics were included in the latest source metadata.
Review the README for scope, installation, examples and limitations. We do not run repository code or certify it.
Evaluate before installing
Review licensing and dependencies, inspect recent commits and unresolved issues, and test in an isolated environment before production use. Stars and forks alone cannot answer these questions.
Source and freshness
Source: GitHub. Metadata observed 2026-10-31T12:17:20.397Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.