karpathy-guidelines

Name: karpathy-guidelines
Availability: InStock
Author: nomanplay

Enforce cautious, verifiable coding behavior with explicit assumptions and testable success criteria.

Updated Mar 27, 2026

Search Tags:#testing #code review #debugging #refactoring #assumption checking #llm coding #surgical changes

Ready to run

npx skills add https://github.com/NoManPlay/my-skills --skill karpathy-guidelines-nomanplay

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: karpathy-guidelines
Source: https://github.com/NoManPlay/my-skills/tree/main/skills/karpathy-guidelines
Command: npx skills add https://github.com/NoManPlay/my-skills --skill karpathy-guidelines-nomanplay

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you avoid common LLM coding mistakes by enforcing cautious reasoning, minimal implementation, and verifiable outcomes so changes are correct, not overcomplicated.

Core Features & Use Cases

Think before coding: explicitly surface assumptions, ambiguities, and tradeoffs instead of guessing.
Simplicity first: implement only what is requested, avoiding speculative features and unnecessary refactors.
Surgical changes: modify only what you must, align with existing style, and clean up only what your changes create.
Goal-driven execution: convert work into testable success criteria and loop until verified (especially for bugs and refactors).

Quick Start

Ask an AI to apply the Karpathy guidelines to your plan and produce a minimal, test-backed, surgical patch that states assumptions and defines clear success checks.

Frequently Asked Questions about karpathy-guidelines

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

FAQPage Schema

How do I prevent LLM coding mistakes during refactoring?▼

Avoid LLM coding mistakes by enforcing cautious reasoning, minimal implementation, and verifiable outcomes. This approach requires explicit assumptions, surgical changes, and goal-driven execution with tests to ensure modifications are correct and not overcomplicated.

What is the best way to write safer code with surgical changes?▼

Writing safer code with surgical changes requires modifying only what is necessary, aligning with existing style, and cleaning up only artifacts your changes introduce. This minimal implementation approach prevents speculative features and unnecessary refactors.

How do I enforce assumption checking before writing code with an LLM?▼

Enforce assumption checking by requiring the LLM to explicitly surface ambiguities, tradeoffs, and assumptions before coding. This cautious reasoning mechanism ensures the AI thinks through the plan and produces a minimal, test-backed, surgical patch instead of guessing.

How do I verify LLM generated code with goal-driven execution?▼

Verify LLM generated code by converting work into testable success criteria and looping until verified. This goal-driven execution ensures bugs and refactors are validated against explicit success checks, confirming the code functions as intended.

Can I use this approach for both code review and debugging?▼

Yes, you can use this approach for code review and debugging. It enforces cautious reasoning and verifiable outcomes during writing, reviewing, and refactoring, ensuring unsafe assumptions and overengineering are caught across the development lifecycle.