vkirill/claude-lane-stack/karpathy-guidelines
Claude Code and agent skill by vkirill/claude-lane-stack
- community
Checking that the SKILL.md file is still in the repository.
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code. Derived from Andrej Karpathy's LLM coding pitfalls.
Install
npx vskill@latest install vkirill/claude-lane-stack/karpathy-guidelinesSKILL.md
The same SKILL.md was published earlier as vkirill/claude-lane-stack/karpathy-guidelines.
Karpathy Guidelines
Derived from Karpathy on LLM coding pitfalls. Bias: caution over reckless speed. Trivial tasks — use judgment.
1. Think Before Coding
Don't assume. Don't hide confusion. Surface tradeoffs.
- State assumptions explicitly. If uncertain, ask (Lane Pilot writer: see below).
- Multiple interpretations → present them; don't pick silently.
- Prefer simpler approaches; push back when warranted.
- Unclear → stop, name the confusion, ask.
Inside a Lane Pilot writer thread (LANE_PILOT_AGENT_TYPE set) nobody answers mid-task, and a question in prose is not recognised: when the contract is unclear or contradictory, change no files and make the first line of your answer NEEDS_HUMAN: <one question for the project owner>. Everything you can look up or decide yourself (see Autonomy zone) you decide.
2. Simplicity First
Minimum code that solves the problem. Nothing speculative.
- No features beyond the ask.
- No single-use abstractions or fake "flexibility".
- No error handling for impossible cases.
- 200 lines that could be 50 → rewrite.
3. Surgical Changes
Touch only what you must. Clean up only your own mess.
- Don't "improve" adjacent code, comments, or formatting.
- Don't refactor what isn't broken.
- Match existing style.
- Unrelated dead code → mention, don't delete.
- Remove only what your change made unused.
Test: every changed line traces to the user request.
4. Goal-Driven Execution
Define success criteria. Loop until verified.
- "Add validation" → tests for invalid inputs, then make them pass.
- "Fix the bug" → failing test first, then green.
- Multi-step:
step → verify: commandlist.
Strong criteria → autonomous loop. Weak ("make it work") → clarify first (in a Lane Pilot writer thread: the NEEDS_HUMAN: first line above).
Autonomy zone (MAY)
Inside the task scope, decide tech details, edit order, and local design without asking. Do not ask the user what you can look up in the repo or docs.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingplugins/lane-stack/skills/karpathy-guidelines/SKILL.md
Popularity
- Repository stars
- 122
- Repository forks
- 2
- 7-day trend score
- 29
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/vkirill/claude-lane-stack/karpathy-guidelines)