Apply Karpathy-inspired coding behavior guidelines — think before coding, prefer simplicity, make surgical changes, and execute toward verifiable goals. Reduces wrong assumptions, overengineering, and unintended side-effects.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Four behavioral guidelines that directly address the most common LLM coding pitfalls identified by Andrej Karpathy. Apply these when writing, reviewing, or modifying code.
Don't assume. Don't hide confusion. Surface tradeoffs.
Before implementing anything:
Why this matters: LLMs often pick an interpretation silently and run with it, leading to implementations that solve the wrong problem.
Minimum code that solves the problem. Nothing speculative.
The test: Would a senior engineer say this is overcomplicated? If yes, simplify.
Why this matters: LLMs tend to over-engineer — bloating abstractions, adding configurability nobody asked for, and implementing 1,000 lines when 100 would do.
Touch only what you must. Clean up only your own mess.
When editing existing code:
When your changes create orphans:
The test: Every changed line should trace directly to the user's request.
Why this matters: LLMs sometimes change or remove code they don't sufficiently understand as side-effects, even when it's orthogonal to the actual task.
Define success criteria. Loop until verified.
Transform imperative tasks into verifiable goals:
| Instead of... | Transform to... |
|---|---|
| "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 the AI loop independently. Weak criteria ("make it work") require constant clarification.
Why this matters: LLMs are exceptionally good at looping until they meet specific goals. Give them success criteria, not just instructions.
These guidelines are working if you see:
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
The English summary is being prepared. Showing the original description.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
The English summary is being prepared. Showing the original description.
Control a headless browser to navigate URLs, click elements, fill forms, extract content from JavaScript-rendered pages, take screenshots, and automate end-to-end web workflows.
The English summary is being prepared. Showing the original description.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
The English summary is being prepared. Showing the original description.
Review code for quality, simplicity, and maintainability. Identifies unnecessary abstractions, duplicated logic, oversized functions, missing error handling, and naming issues — then fixes them automatically before presenting the result.
The English summary is being prepared. Showing the original description.
WooCommerce store operations through NV oOS Pro — product research, catalog cross-referencing, inventory lookups, and Shopify or Flowhub comparisons where integrations are configured.
The English summary is being prepared. Showing the original description.