What problem does it solve? Turning a spec or requirements document into working code often fails because the plan is too vague for an engineer (or AI agent) with zero codebase context. This Skill converts requirements into a granular, actionable implementation plan where every task includes exact file paths, complete code, and verification commands. ## Core Features & Use Cases - Granular Task Breakdown: Splits work into 2-5 minute steps following the RED-GREEN-REFACTOR TDD cycle, from failing test to commit. - Structured Templates: Provides a plan header template (goal, architecture, tech stack) and a per-task template covering files, test code, run commands with expected output, and commit steps. - Pipeline Integration: Fits between requirements gathering and execution, handing off to the executing-plans skill with a verification-before-completion quality gate. - Use Case: After brainstorming a new API endpoint feature, use this Skill to produce a plan document listing every file to create or modify, the failing test to write first, the minimal implementation, and the exact pytest commands to verify each step. ## Quick Start Ask the AI to write an implementation plan for your feature spec using the writing-plans skill before touching any code.
