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
- 2026-11-10
- Stars
- ★ 13
- Forks
- 4
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
tailscale-generation-skill-authoring
This skill should be used when the user asks to "create a Tailscale generation skill", "add a local generation skill", "document a generation endpoint", "add an image generation provider", "add a TTS provider", "add video generation", "add 3D generation", or needs guidance on where HivemindOS Tailscale or local generation providers belong in the shared skills shelf.
localtts
This skill should be used when the user asks to "generate local TTS", "use local text to speech", "use remote TTS over Tailscale", "make speech audio", "add a TTS provider", "use Qwen3-TTS", or needs TTS endpoint setup through local or HivemindOS Tailscale routes.
comfyui-image-generation
This skill should be used when the user asks to "generate images", "generate images with ComfyUI", "use local ComfyUI", "use remote ComfyUI", "use Z-Image", "add an image generation provider", or needs image-generation endpoint setup through local or HivemindOS Tailscale routes.
wrangler
Cloudflare Workers CLI for deploying, developing, and managing Workers, KV, R2, D1, Vectorize, Hyperdrive, Workers AI, Containers, Queues, Workflows, Pipelines, and Secrets Store. Load before running wrangler commands to ensure correct syntax and best practices. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
workers-best-practices
Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
sandbox-sdk
Build sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.