What problem does it solve? LLM-generated code often suffers from overcomplication, unrequested features, silent assumptions, and sweeping changes that touch unrelated code. This Skill provides behavioral guidelines that keep AI coding assistants focused, surgical, and verifiable when writing, reviewing, or refactoring code. ## Core Features & Use Cases - Think Before Coding: Surfaces assumptions, presents alternative interpretations, and stops to ask when requirements are unclear instead of guessing silently. - Simplicity First: Enforces minimum-code solutions with no speculative abstractions, unrequested configurability, or impossible-scenario error handling. - Surgical Changes: Restricts edits to lines that trace directly to the user's request, matching existing style and leaving unrelated code untouched. - Goal-Driven Execution: Transforms vague tasks into verifiable success criteria, such as writing a failing test before fixing a bug. - Use Case: When asking an AI to fix a bug in a large codebase, these guidelines ensure it writes a reproduction test first, changes only the relevant lines, and avoids refactoring adjacent code. ## Quick Start Ask the AI to fix a bug or implement a feature while following the karpathy guidelines to keep changes minimal and verifiable.
