LLM Skills — AI skill for Claude Code

Karpathy-Inspired Claude Code Guidelines

A single `CLAUDE.md` file to improve Claude Code behavior, derived from [Andrej Karpathy's observations](https://x.com/karpathy/status/2015883857489522876) on LLM coding pitfalls.

English | [简体中文](./README.zh.md)

The Problems

From Andrej's post:

"The models make wrong assumptions on your behalf and just run along with them without checking. They don't manage their confusion, don't seek clarifications, don't surface inconsistencies, don't present tradeoffs, don't push back when they should."

"They really like to overcomplicate code and APIs, bloat abstractions, don't clean up dead code... implement a bloated construction over 1000 lines when 100 would do."

"They still sometimes change/remove comments and code they don't sufficiently understand as side effects, even if orthogonal to the task."

The Solution

Four principles in one file that directly address these issues:

Principle	Addresses
Think Before Coding	Wrong assumptions, hidden confusion, missing tradeoffs
Simplicity First	Overcomplication, bloated abstractions
Surgical Changes	Orthogonal edits, touching code you shouldn't
Goal-Driven Execution	Leverage through tests-first, verifiable success criteria

Other

I also included some personal additions.

• 具体内容转到5.,因为我觉得要加一条让llm不要把key发到github上去,每天都有免费的key用,只能说感谢大自然的馈赠 (bushi

在 `4.`中添加了

If the project has no test infrastructure and the task is exploratory, state success criteria in plain language instead (e.g., "verify: running curl /api/users returns 200 with expected JSON").

The Four Principles in Detail

1. Think Before Coding

**Don't assume. Don't hide confusion. Surface tradeoffs.**

LLMs often pick an interpretation silently and run with it. This principle forces explicit reasoning:

• State assumptions explicitly — If uncertain, ask rather than guess
• Present multiple interpretations — Don't pi