# Karpathy Guidelines

> 适用于代码改动容易过度设计、范围蔓延或需要严格审查时。Use when a code change risks overengineering, scope creep, broad refactors, or needs a conservative review for surgical changes and verifiable success criteria. 中文关键词：避免过度设计、最小改动、范围控制、明确假设、验收标准、保守审查、重构审查。

- Skill: `madnpc/karpathy-guidelines` (Agent Skill)
- Install (CLI): `npx skillmds@latest add madnpc/karpathy-guidelines`
- Raw SKILL.md: https://api.skillmd.com/api/skills/madnpc/karpathy-guidelines/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- License: MIT
- Author: madnpc (https://skillmd.com/u/madnpc)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/madnpc/karpathy-guidelines

---


# 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.

## 输出语言

默认使用简体中文与用户沟通，并以简体中文编写审查结论和说明。用户明确指定其他语言或既有文档语言另有约定时，遵从该约定；代码、命令、产品名和必须保持原文的引用不强行翻译。

**Tradeoff:** These guidelines bias toward caution over speed. For trivial tasks, use judgment.

## 1. Think Before Coding

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

Before implementing:
- State your assumptions explicitly. If uncertain, ask.
- If multiple interpretations exist, present them - don't pick silently.
- If a simpler approach exists, say so. Push back when warranted.
- If something is unclear, stop. Name what's confusing. Ask.

## 2. Simplicity First

**Minimum code that solves the problem. Nothing speculative.**

- No features beyond what was asked.
- No abstractions for single-use code.
- No "flexibility" or "configurability" that wasn't requested.
- No error handling for impossible scenarios.
- If you write 200 lines and it could be 50, rewrite it.

Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.

## 3. Surgical Changes

**Touch only what you must. Clean up only your own mess.**

When editing existing code:
- Don't "improve" adjacent code, comments, or formatting.
- Don't refactor things that aren't broken.
- Match existing style, even if you'd do it differently.
- If you notice unrelated dead code, mention it - don't delete it.

When your changes create orphans:
- Remove imports/variables/functions that YOUR changes made unused.
- Don't remove pre-existing dead code unless asked.

The test: Every changed line should trace directly to the user's request.

## 4. Goal-Driven Execution

**Define success criteria. Loop until verified.**

Transform tasks into verifiable goals:
- "Add validation" → "Write tests for invalid inputs, then make them pass"
- "Fix the bug" → "Write a test that reproduces it, then make it pass"
- "Refactor X" → "Ensure tests pass before and after"

For multi-step tasks, state a brief plan:
```
1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]
```

Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.