What problem does it solve? Written implementation plans often get executed inconsistently: steps get skipped, verifications are ignored, and blockers are worked around with guesses. This Skill enforces a disciplined process for carrying out a plan in a separate session, with critical review up front and explicit checkpoints along the way. ## Core Features & Use Cases - Critical Plan Review: Loads the plan file, identifies questions or concerns, and raises them with the human partner before any work begins. - Task-by-Task Execution: Converts plan items into todos, marks each in progress, follows the bite-sized steps exactly, and runs the specified verifications before marking completion. - Stop-and-Ask Discipline: Halts execution on blockers, unclear instructions, or repeated verification failures instead of guessing, and hands off to a finishing-a-development-branch step when all tasks are done. - Use Case: You have a reviewed implementation plan for a multi-file refactor. Start a fresh session, point the AI at the plan file, and it executes every task in order, runs each verification, and stops to ask whenever something is ambiguous. ## Quick Start Use the executing-plans skill to implement the plan in docs/refactor-plan.md, reviewing it critically first and stopping to ask if anything is unclear.
