What problem does it solve? Turning a written implementation plan into working code often goes wrong: steps get skipped, vague verification criteria slip through, and errors compound silently. This Skill enforces a disciplined execution loop—critically review the plan, execute each task with verification, commit per task, and stop to ask when blocked. ## Core Features & Use Cases - Critical Plan Review: Checks for missing dependencies between steps, vague verification conditions, and unstated environment assumptions before writing any code. - Structured Task Execution: Tracks progress with a todo list, runs the required tests for each task, and commits changes individually with task-referenced commit messages. - Exception Handling: Distinguishes implementation bugs from broken tests or flawed plans, and stops to consult the user instead of guessing when instructions are unclear. - Use Case: You have a 5-task plan in docs/plan.md for adding user validation to an API. The Skill reviews the plan, flags an ambiguous verification step, then implements, tests, and commits each task in sequence, ending with a full execution report. ## Quick Start Ask the AI to execute the implementation plan in docs/plan.md using the executing-plans skill, reviewing it first and committing after each task.
