karpathy-guidelines
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
- 最近更新
- 2026-10-11
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- karpathy-guidelines
- license
- MIT
- 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.
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.
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.
04 同仓库更多 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.
supabase-postgres-best-practices
Postgres performance optimization and best practices from Supabase. Use this skill when writing, reviewing, or optimizing Postgres queries, schema designs, or database configurations.
render-workflows
Sets up, develops, tests, and deploys Render Workflows. Covers first-time scaffolding (via CLI or manual), SDK installation (Python or TypeScript), task patterns (retries, subtasks, fan-out), local development, Dashboard deployment, and troubleshooting. Use when a user wants to set up Render Workflows for the first time, scaffold a workflow service, add or modify workflow tasks, test workflows locally, or deploy workflows to Render.
render-web-services
Configures Render web services—port binding, TLS, health checks, custom domains, auto-deploy, PR previews, persistent disks, and deploy lifecycle. Use when the user needs to set up a web service, fix health check failures, add a custom domain, configure zero-downtime deploys, or troubleshoot port binding issues.
render-static-sites
Deploys and configures static sites on Render's global CDN—build commands, publish paths, SPA routing, redirects, custom headers, and PR previews. Use when the user needs to deploy a static site, set up a React/Vue/Hugo/Gatsby frontend, configure SPA fallback routing, add redirect rules, customize response headers, or choose between a static site and a web service for their frontend. Trigger terms: static site, CDN, SPA, single-page app, React deploy, Vue deploy, Hugo, Gatsby, Docusaurus, Jekyll, staticPublishPath.
render-scaling
Scales Render services—configures autoscaling targets, chooses instance types, sets manual instance counts, and optimizes cost. Use when the user needs to handle more traffic, set up autoscaling, pick the right instance type, reduce costs, or troubleshoot scaling behavior like slow scale-down or stuck instances.