What problem does it solve? Written implementation plans often fail during execution because steps are skipped, verification is vague, or blockers are silently worked around. This Skill enforces a disciplined workflow: critically review the plan first, execute each task with explicit verification, commit per task, and stop to ask when blocked instead of guessing. ## Core Features & Use Cases - Critical Plan Review: Checks for missing dependencies between steps, vague verification criteria, and hidden environment assumptions before any code is written. - Structured Task Execution: Tracks progress with a todo list, runs the required tests or checks per task, and creates one commit per task referencing its task number. - Blocker Escalation: Defines explicit stop conditions (missing dependencies, repeated test failures, unclear instructions) so the AI asks the human partner rather than guessing. - 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 unclear verification step, then implements each task, runs the test suite, commits with messages like "feat: add user input validation (task 2/5)", and produces a final execution report. ## Quick Start Ask the AI to use the executing-plans skill to implement the plan in docs/plan.md, reviewing it first and committing after each completed task.
