Karpathy Guidelines

A third-party skill from multica-ai, derived from Andrej Karpathy's observations on where LLMs go wrong when they write code. It adds no tools and runs no scripts. It is a short set of instructions that biases Claude toward caution: state assumptions and ask when something is unclear, write the minimum code that solves the problem, touch only the lines the request requires, and turn every task into a success criterion that can be checked, then loop until it passes. Use it when writing, reviewing, or refactoring code and you want fewer surprise rewrites, less overengineering, and smaller diffs. The tradeoff is speed: it favors care over pace, so for trivial tasks Claude should use judgment. Licensed MIT.

What it does

Four behavioral rules that cut common LLM coding mistakes: think before coding, keep it simple, make surgical changes, and work toward verifiable goals.

How to use this

Once it is installed, this skill picks itself up. You do not need to name it.

“follow the Karpathy guidelines”
“keep this change surgical”
“don't overcomplicate this”
“state your assumptions before coding”
Created by
multica-ai
Category
Engineering

Run this on Skills and Agents

You can run the skill on Skills and Agents by creating an account. You don't need to install anything. We provide the model and tokens. Your connected tools and company brain are ready to use.

Create an account

Skills give you best practices and templates to get the most out of your AI