mcpbeat Sign in

Karpathy Guidelines Agent Skill

by coco-research

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

1k tokens
context cost
the whole folder, loaded on every use
2
files
instructions only
0
copies elsewhere
how many repositories repackaged it
196
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository 
npx skills add https://github.com/coco-research/coco --skill karpathy-guidelines

The instruction itself

5 sections, as written by the author

Karpathy Guidelines

Behavioral guidelines to reduce common LLM coding mistakes, derived from Andrej Karpathy's observations on LLM coding pitfalls.

Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.

1. Think Before Coding

Don't assume. Don't hide confusion. Surface tradeoffs.

Before implementing:

  • State your assumptions explicitly. If uncertain, ask.
  • If multiple interpretations exist, present them - don't pick silently.
  • If a simpler approach exists, say so. Push back when warranted.
  • If something is unclear, stop. Name what's confusing. Ask.

2. Simplicity First

Minimum code that solves the problem. Nothing speculative.

  • No features beyond what was asked.
  • No abstractions for single-use code.
  • No "flexibility" or "configurability" that wasn't requested.
  • No error handling for impossible scenarios.
  • If you write 200 lines and it could be 50, rewrite it.

Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.

3. Surgical Changes

Touch only what you must. Clean up only your own mess.

When editing existing code:

  • Don't "improve" adjacent code, comments, or formatting.
  • Don't refactor things that aren't broken.
  • Match existing style, even if you'd do it differently.
  • If you notice unrelated dead code, mention it - don't delete it.

When your changes create orphans:

  • Remove imports/variables/functions that YOUR changes made unused.
  • Don't remove pre-existing dead code unless asked.

The test: Every changed line should trace directly to the user's request.

4. Goal-Driven Execution

Define success criteria. Loop until verified.

Transform tasks into verifiable goals:

  • "Add validation" → "Write tests for invalid inputs, then make them pass"
  • "Fix the bug" → "Write a test that reproduces it, then make it pass"
  • "Refactor X" → "Ensure tests pass before and after"

For multi-step tasks, state a brief plan:

1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]

Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.

Other skills for the same job

different authors, same section of the catalogue
Karpathy Guidelines
by hyyhf
×3

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

629 tokens
Plan Writing
by ComeOnOliver
×2

Structured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features, refactoring, or any multi-step work.

4k tokens
Modern Javascript Patterns
by ComeOnOliver
×2

Master ES6+ features including async/await, destructuring, spread operators, arrow functions, promises, modules, iterators, generators, and functional programming patterns for writing clean, efficient JavaScript code. Use when refactoring legacy code, implementing modern patterns, or optimizing JavaScript applications.

9k tokens
Modern Javascript Patterns
by ComeOnOliver
×2

Master ES6+ features including async/await, destructuring, spread operators, arrow functions, promises, modules, iterators, generators, and functional programming patterns for writing clean, efficient JavaScript code. Use when refactoring legacy code, implementing modern patterns, or optimizing JavaScript applications.

8k tokens
Contributor Pr Description
by flutter
vendor ×1

Guidelines and format for writing pull request descriptions in this repository. Use this skill whenever the user asks you to draft a pull request description, submit a PR, or update a PR description.

697 tokens
Angular Best Practices
by lingxling
×1

Angular performance optimization and best practices guide. Use when writing, reviewing, or refactoring Angular code for optimal performance, bundle size, and rendering efficiency.

4k tokens
Gh Fix CI
by christophacham
×1

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions. Uses `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treats external providers (for example Buildkite) as out of scope and reports only the details URL. Do NOT use for addressing PR review comments (use gh-address-comments) or general CI outside GitHub Actions.

7k tokens scripts
Angular Best Practices
by ComeOnOliver
×1

Angular performance optimization and best practices guide. Use when writing, reviewing, or refactoring Angular code for optimal performance, bundle size, and rendering efficiency.

6k tokens

How to use it

Copy the folder

Take coco-research/karpathy-guidelines from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.