What problem does it solve? LLM-generated code often suffers from overcomplication, unrequested features, silent assumptions, and sprawling edits that touch unrelated code. This Skill provides a set of behavioral guidelines, derived from Andrej Karpathy's observations on LLM coding pitfalls, that keep AI-assisted coding focused, minimal, and verifiable. ## Core Features & Use Cases - Think Before Coding: Surfaces assumptions, ambiguities, and simpler alternatives before implementation instead of silently picking an interpretation. - Simplicity First: Enforces minimum-code solutions with no speculative abstractions, configurability, or unrequested error handling. - Surgical Changes: Restricts edits to only what the task requires, matching existing style and avoiding drive-by refactors. - Goal-Driven Execution: Converts vague tasks into verifiable success criteria with test-driven loops and explicit step plans. - Use Case: When asking an AI to fix a bug or add a feature, activate these guidelines so the agent writes a failing test first, makes the minimal change to pass it, and avoids reformatting unrelated code. ## Quick Start Apply the karpathy guidelines while refactoring this function, keeping changes minimal and defining verifiable success criteria first.
