What problem does it solve? LLM coding assistants often overcomplicate solutions, make sweeping unrequested changes, hide assumptions, and lack verifiable success criteria. This Skill provides behavioral guidelines that keep AI-generated code simple, surgical, and goal-driven. ## Core Features & Use Cases - Think Before Coding: Surfaces assumptions, presents alternative interpretations, and stops to ask when requirements are unclear. - Simplicity First: Enforces minimum code that solves the problem, rejecting speculative abstractions and unrequested configurability. - Surgical Changes: Restricts edits to only what the task requires, matching existing style and avoiding unrelated refactors. - Goal-Driven Execution: Transforms vague tasks into verifiable success criteria with test-driven loops. - Use Case: When asking an AI agent to fix a bug in a large repository, the guidelines ensure it writes a reproducing test first, changes only the relevant lines, and verifies the fix rather than refactoring surrounding code. ## Quick Start Ask the AI to apply the karpathy-guidelines skill while implementing or reviewing your next code change.
