karpathy-guidelines

Apply behavioral guidelines for surgical code changes and verifiable success criteria.

Updated Jun 30, 2026

Search Tags:#code quality #code review #refactoring #guidelines #LLM coding

Ready to run

npx skills add https://github.com/SunS1eep1ng/codex-dotfiles --skill karpathy-guidelines-suns1eep1ng

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: karpathy-guidelines
Source: https://github.com/SunS1eep1ng/codex-dotfiles/tree/main/skills/karpathy-guidelines
Command: npx skills add https://github.com/SunS1eep1ng/codex-dotfiles --skill karpathy-guidelines-suns1eep1ng

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill aids in avoiding overcomplication, making surgical changes, and defining verifiable success criteria to improve code quality.

Core Features & Use Cases

Behavioral Guidelines: Follow Andrej Karpathy's observations to reduce common LLM coding mistakes.
Simplicity First: Emphasize minimum code to solve the problem, avoiding speculative features.
Surgical Changes: Touch only necessary parts of the code and clean up your own mess.
Goal-Driven Execution: Define success criteria and loop until verified for verifiable goals.

Quick Start

Apply the Karpathy Guidelines to your codebase by reviewing and refactoring according to the provided behavioral guidelines.

Frequently Asked Questions about karpathy-guidelines

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I stop LLM coding from overcomplicating my codebase?▼

To stop LLM coding from overcomplicating your codebase, apply behavioral guidelines that enforce surgical changes and emphasize minimum code to solve the problem without speculative features. This approach targets code reviews and refactoring to systematically improve code quality.

What is the best way to define verifiable success criteria for LLM code generation?▼

The best way to define verifiable success criteria for LLM code generation is to establish goal-driven execution loops that continue until the objective is verified. This ensures LLM coding targets are met without unnecessary modifications or overcomplication.

How do I make surgical changes during code refactoring with an LLM?▼

To make surgical changes during code refactoring with an LLM, follow guidelines that restrict modifications to only necessary parts of the code and require cleaning up any resulting mess. This minimizes risk and maintains overall code quality.

Can I use these code quality guidelines for standard manual code reviews?▼

Yes, you can use these code quality guidelines for standard manual code reviews. The behavioral rules focusing on simplicity and surgical changes apply universally to refactoring and code quality improvement, regardless of whether an LLM generated the code.

Why does LLM generated code often include unnecessary speculative features?▼

LLM generated code often includes unnecessary speculative features because models lack inherent behavioral constraints to enforce simplicity. Applying specific coding guidelines corrects this by prioritizing minimum code to solve the problem and avoiding overcomplication.