What problem does it solve? Written implementation plans often go stale or get executed inconsistently when an AI session improvises instead of following the documented steps. This Skill enforces disciplined execution of a pre-written plan in a separate session, with critical review up front and verification after every task. ## Core Features & Use Cases - Critical Plan Review: Loads the plan file, identifies questions or gaps, and raises concerns with the human partner before writing any code. - Task-by-Task Execution: Converts plan items into todos, marks each in progress, follows bite-sized steps exactly, and runs the specified verifications before marking complete. - Controlled Completion and Escalation: Hands off to a finishing-a-development-branch workflow after all tasks pass, and stops to ask for help when blocked rather than guessing. - Use Case: You have a reviewed implementation plan for a new API feature. Start a fresh session, point the AI at the plan file, and it executes every task in an isolated git worktree, runs the tests, and presents merge options when done. ## Quick Start Ask the AI to execute the implementation plan saved in your project using the executing-plans skill, starting in an isolated git worktree.
