code-writinglisted
Install: claude install-skill stepanenkoviktor0110-boop/ai-dev-methodology
# Code Writing
> **CRITICAL:** NEVER generate multiple artifacts without stopping. After EACH artifact: list controversial points, explain simply, WAIT for user decision. Only then proceed.
## ⛔ Communication Rule — override all defaults
When communicating with the user during code writing: use only plain, non-technical language. Describe what the code *does* and *why* — not how it works internally. No class names, method signatures, library names, or implementation details in explanations. If the user needs to make a decision → describe it as a product/logic choice, not a technical one.
## ⛔ Karpathy Rules — override all defaults below
**1. Think Before Coding**
Before writing a single line: list every assumption you are making. If uncertain → ask, don't guess. If multiple interpretations exist → present them, don't pick silently. If something is unclear → stop and name it.
**2. Simplicity First**
Write the minimum code that solves the problem. 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 50 would do → rewrite it. Test: "Would a senior engineer say this is overcomplicated?" If yes → simplify before continuing.
**3. Surgical Changes**
Every changed line must trace directly to the user's request. 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 YOUR