AGENT SKILL

andrej-karpathy

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.

License 许可
MIT
所属仓库
MHassan0000/Skills
最近更新
2026-08-07
Stars
★ 1
Forks
0

01 前言 Front Matter

name
andrej-karpathy
risk
safe
tags
[ "coding-guidelines", "code-review", "llm-coding", "simplicity" ]
tools
[ "claude-code", "antigravity", "cursor", "gemini-cli", "codex-cli" ]
author
renat
source
community
license
MIT
date_added
2026-03-06
description
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.
source_repo
multica-ai/andrej-karpathy-skills
source_type
community
license_source
https://github.com/multica-ai/andrej-karpathy-skills/blob/main/skills/karpathy-guidelines/SKILL.md

03 SKILL.md 正文

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.

When to Use This Skill

  • Use when writing, reviewing, or refactoring code with an LLM.
  • Use when a change needs to stay surgical and avoid speculative abstractions.
  • Use when assumptions, tradeoffs, and verification criteria should be made explicit.
  • Use when code has become overcomplicated and needs to be simplified.

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 such as "make it work" require constant clarification.

Examples

User request: "Add validation to this form."

Better response:
1. Assumption: validation should run before submit and show inline errors.
2. Plan: add a small validator, add tests for invalid inputs, then verify existing submit behavior.
3. Scope: only touch the form component and its test file.
User request: "Refactor this service."

Better response:
1. Ask what behavior must remain unchanged.
2. Identify a concrete smell, such as duplicated parsing logic.
3. Make the smallest refactor and run the existing service tests.

Limitations

  • These guidelines are behavioral guardrails, not a replacement for project-specific architecture or style rules.
  • For emergency fixes, prioritize the smallest verified correction over extensive planning.
  • For exploratory prototypes, some caution can be relaxed, but assumptions and verification should still be explicit.

04 同仓库更多 Skills

MHassan0000
MHassan0000/Skills

vercel-react-best-practices

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

★ 1
MHassan0000
MHassan0000/Skills

stop-slop

Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells and produce more human-like writing.

★ 1
MHassan0000
MHassan0000/Skills

ogilvy-copywriting

Apply David Ogilvy's advertising principles when writing or reviewing copy, headlines, product descriptions, landing pages, ads, emails, or any persuasive text. Use when the goal is copy that sells, not copy that wins awards. Covers positioning, headlines, promises, brand voice, long-form copy, and visual logic. Source: How to Create Advertising That Sells (1972) + Ogilvy on Advertising.

★ 1
MHassan0000
MHassan0000/Skills

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

★ 1
MHassan0000
MHassan0000/Skills

webapp-testing

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

★ 1
MHassan0000
MHassan0000/Skills

web-artifacts-builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

★ 1