karpathy-guidelines

multica-ai/andrej-karpathy-skills/karpathy-guidelines

The Karpathy Guidelines are a set of behavioral guidelines designed to reduce common coding mistakes made by large language models, inspired by Andrej Karpathy's observations on LLM coding pitfalls. The guidelines emphasize thinking before coding, simplicity first, surgical changes, and goal-driven execution. The guidelines consist of four core sections: first, think before coding by stating assumptions, asking questions, and presenting multiple interpretations when needed; second, prioritize simplicity by writing the minimum code that solves the problem, avoiding speculative features; third, make surgical changes by touching only what is necessary and cleaning up only your own mess; fourth, execute with a goal-driven approach by defining verifiable success criteria and looping until verified. These guidelines bias toward caution over speed, and for trivial tasks, judgment should be used.

安裝量 · 165查看來源

Installation

npx skills add https://github.com/multica-ai/andrej-karpathy-skills --skill karpathy-guidelines

技能檔案

SKILL.md

最近同步 · 2026年8月28日

SKILL.md›

---
name: karpathy-guidelines
description: Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
license: MIT
---

# 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.

**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.