What problem does it solve? Executing a multi-task implementation plan in a single session leads to context pollution, inconsistent quality, and undetected spec drift. This Skill orchestrates plan execution by delegating each task to a fresh subagent and enforcing systematic review between tasks. ## Core Features & Use Cases - Per-Task Subagent Dispatch: Parses a plan file once, then delegates each task via delegate_task with full task text and project context, so subagents never read the plan file themselves. - Two-Stage Review Pipeline: Runs a spec compliance review first, then a code quality review, looping fixes until both pass before marking a task complete. - Final Integration Review: After all tasks complete, dispatches a reviewer to check cross-task consistency, run the full test suite, and confirm merge readiness. - Use Case: Given a plan like docs/plans/auth-feature.md with five tasks (User model, password hashing, login endpoint, JWT generation, registration endpoint), the Skill implements each task with TDD, reviews each twice, and delivers a fully tested feature. ## Quick Start Execute the implementation plan in docs/plans/feature-plan.md by dispatching a fresh subagent for each task with spec and quality reviews between tasks.
