karpathy-guidelines

Apply Karpathy-style guidelines to coding tasks for explicit assumptions and verifiable success criteria.

Updated Mar 8, 2026

Search Tags:#best-practices #code-review #prompting #surgical-changes #karpathy-guidelines #llm-coding

Ready to run

npx skills add https://github.com/ZiadNagar/zeVillage-AI-Toolkit --skill karpathy-guidelines-ziadnagar

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: karpathy-guidelines
Source: https://github.com/ZiadNagar/zeVillage-AI-Toolkit/tree/main/skills/karpathy-guidelines
Command: npx skills add https://github.com/ZiadNagar/zeVillage-AI-Toolkit --skill karpathy-guidelines-ziadnagar

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Behavioral guidelines to reduce common LLM coding mistakes by surfacing assumptions, promoting simplicity, and defining verifiable success criteria during coding tasks.

Core Features & Use Cases

Think Before Coding: explicit assumptions, questions, and tradeoffs surface
Simplicity First: minimal, well-scoped changes with clear boundaries
Surgical Changes: touch only what's necessary and clean up after
Goal-Driven Execution: plan steps with verifiable success criteria

Quick Start

Review the Karpathy Guidelines and apply them to your next coding task by outlining assumptions, choosing the simplest approach, and documenting a plan with verifiable success criteria.

Frequently Asked Questions about karpathy-guidelines

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

FAQPage Schema

How do I reduce LLM coding mistakes when generating code?▼

To reduce LLM coding mistakes, apply behavioral guidelines that surface explicit assumptions, promote simplicity, and define verifiable success criteria before execution. This structured approach forces the model to think before coding, minimizing errors and unnecessary changes.

What are Karpathy guidelines for AI code generation?▼

Karpathy guidelines are behavioral rules for LLM coding that enforce think-before-coding practices. They require defining explicit assumptions, making minimal surgical changes, and establishing a plan with verifiable success criteria to ensure safer code generation.

How do I apply surgical changes when reviewing LLM generated code?▼

To apply surgical changes during code review, ensure the LLM touches only what is necessary and cleans up afterward. This minimal change approach maintains clear boundaries, reduces regression risk, and keeps the codebase well-scoped.

Does prompt engineering for code generation require verifiable success criteria?▼

Yes, defining verifiable success criteria is a core guideline for LLM coding. It ensures generated code meets explicit requirements, allowing developers to verify outcomes and maintain goal-driven execution throughout the coding and refactoring process.

What's the best way to structure prompts for safer LLM code refactoring?▼

The best way to structure prompts for safer refactoring is to enforce think-before-coding guidelines: outline explicit assumptions, push for simplicity, and document a plan with verifiable success criteria before executing minimal, surgical changes.