What problem does it solve?
LLM coding assistants often overcomplicate solutions, make silent assumptions, refactor unrelated code, and declare success without verification. This Skill provides behavioral guidelines that counteract these tendencies when writing, reviewing, or refactoring code.
Core Features & Use Cases
- Think Before Coding: Surfaces assumptions, ambiguities, and simpler alternatives before implementation instead of silently picking an interpretation.
- Simplicity and Surgical Changes: Enforces minimum-code solutions and restricts edits to lines directly traceable to the user's request, matching existing style.
- Goal-Driven Execution: Transforms vague tasks into verifiable success criteria (e.g., write a failing test, then make it pass) with explicit step-by-step verification plans.
- Use Case: When asking an AI to fix a bug or add a validation in a Rails codebase, activate these guidelines so the assistant writes a reproducing test first, changes only the necessary lines, and avoids speculative abstractions.
Quick Start
Ask the assistant to apply the behavioral guidelines while implementing your next code change so it states assumptions, keeps edits minimal, and defines verifiable success criteria.
