What problem does it solve?
This Skill optimizes the execution of implementation plans by dispatching fresh subagents for each independent task, integrating code reviews between tasks to ensure high quality and fast iteration within the current session.
Core Features & Use Cases
- Fresh Subagent Per Task: Prevents context pollution by using a new, focused subagent for each task, ensuring clarity and efficiency.
- Inter-Task Code Review: Integrates mandatory code reviews after each task to catch issues early, preventing them from cascading.
- Automated Task Execution: Dispatches subagents to implement, test, and commit work based on a plan, streamlining the development process.
- Use Case: When executing a detailed implementation plan with independent tasks, use this skill to automate the process, ensuring each task is completed by a focused subagent, reviewed for quality, and integrated seamlessly.
Quick Start
1. Load Plan (e.g., from writing-plans skill)
2. Execute Task with Subagent
Task tool (general-purpose):
description: "Implement Task N: [task name]"
prompt: |
You are implementing Task N from [plan-file].
Read that task carefully. Your job is to:
1. Implement exactly what the task specifies
2. Write tests (following TDD if task says to)
3. Verify implementation works
4. Commit your work
5. Report back
Work from: [directory]
Report: What you implemented, what you tested, test results, files changed, any issues
3. Review Subagent's Work (using requesting-code-review skill)
4. Apply Review Feedback
5. Mark Complete, Next Task
