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.
Installs just this skill. Get the whole plugin for auto-invocation.
⚡ How it fires
How this skill gets triggered: by you, by Claude, or both.
Fires itselfClaude auto-loads it when your prompt matches the work.
You can call itInvoke it directly when you want it.
Slash command/andrej-karpathy
👁️ Context preview
The summary Claude sees to decide when to auto-load this skill.
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.
📊 Stats
Stars43,759
Forks6,464
LanguagePython
LicenseMIT
📦 Ships with agentic-awesome-skills
</> SKILL.md
andrej-karpathy.SKILL.md
---name: andrej-karpathy
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.
risk: safe
source: community
source_repo: multica-ai/andrej-karpathy-skills
source_type: community
license: MIT
license_source: "https://github.com/multica-ai/andrej-karpathy-skills/blob/main/skills/karpathy-guidelines/SKILL.md"
date_added: '2026-03-06'
author: renat
tags:
- coding-guidelines
- code-review
- llm-coding
- simplicity
tools:
- claude-code
- antigravity
- cursor
- gemini-cli
- codex-cli
---# 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.
