karpathy-guidelines

Guide coding tasks with explicit assumptions and verifiable success criteria.

1|Updated Apr 15, 2026

Search Tags:#llm #refactor #review #coding #guidelines #simplicity #success-criteria

Ready to run

npx skills add https://github.com/Manancode/claude-taste-skills --skill karpathy-guidelines-manancode

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: karpathy-guidelines
Source: https://github.com/Manancode/claude-taste-skills/tree/main/less-hallucinations
Command: npx skills add https://github.com/Manancode/claude-taste-skills --skill karpathy-guidelines-manancode

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Behavioral guidelines to reduce common LLM coding mistakes, to be used when writing, reviewing, or refactoring code, help teams avoid overcomplication, surface assumptions, and define verifiable success criteria.

Core Features & Use Cases

Clear thinking before coding: state assumptions, surface tradeoffs, and avoid unnecessary changes.
Surgical changes: modify only what's needed and keep surrounding code stable.
Goal-driven execution: define verifiable success criteria and iterate until they are met.

Quick Start

Apply these guidelines to your next coding task by reviewing assumptions, surfacing tradeoffs, and defining explicit success criteria.

Frequently Asked Questions about karpathy-guidelines

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

FAQPage Schema

What are the best practices for LLM coding to avoid overcomplication?▼

LLM coding best practices involve stating assumptions, surfacing tradeoffs, and making surgical changes to modify only what is needed while keeping surrounding code stable. This prevents overcomplication by enforcing clear thinking before code generation.

How do I define verifiable success criteria for LLM refactoring tasks?▼

Verifiable success criteria for LLM refactoring are defined by setting explicit, goal-driven outcomes before execution. You establish specific checkpoints to verify the refactor meets requirements, then iterate until the code passes those defined criteria.

How do I review code generated by an LLM for unnecessary changes?▼

To review generated code for unnecessary changes, apply guidelines that enforce surgical modifications. You verify that the LLM modified only what was needed for the task, keeping surrounding code stable and avoiding unrequested overcomplication.

When should I use explicit guidelines for LLM coding tasks?▼

You should use explicit guidelines for LLM coding tasks whenever your project requires precision and verifiable outcomes. They are essential during writing, reviewing, and refactoring to surface hidden assumptions and prevent behavioral mistakes.

Why does my LLM refactoring introduce unstable changes to surrounding code?▼

Your LLM refactoring introduces unstable changes when it lacks guidelines to minimize modifications. Without rules enforcing surgical changes, the model overcomplicates the codebase by altering surrounding code instead of modifying only what is needed.