菜单
Use when executing implementation plans with independent tasks in the current session
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
| name | subagent-driven-development |
| description | Use when executing implementation plans with independent tasks in the current session |
Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.
Core principle: Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration
Use when:
vs. Executing Plans (parallel session):
Dispatch Implementer Subagent:
agent_type: "general-purpose"If Implementer Asks Questions:
Dispatch Spec Reviewer Subagent:
Dispatch Code Quality Reviewer Subagent:
Mark Task Complete:
After all tasks:
Task tool (general-purpose):
description: "Implement Task N: [task name]"
prompt: |
You are implementing Task N: [task name]
## Task Description
[FULL TEXT of task from plan]
## Context
[Where this fits, dependencies, architectural context]
## Before You Begin
If you have questions about requirements, approach, or anything unclear - ask now.
## Your Job
1. Implement exactly what the task specifies
2. Write tests (following TDD)
3. Verify implementation works
4. Commit your work
5. Self-review for completeness and quality
6. Report back
Task tool (general-purpose):
description: "Review spec compliance for Task N"
prompt: |
Review whether implementation matches specification.
## What Was Requested
[FULL TEXT of task requirements]
## What Implementer Claims They Built
[From implementer's report]
## Your Job
Read the implementation code and verify:
- Did they implement everything requested?
- Did they build things that weren't requested?
- Any misunderstandings of requirements?
Report: ✅ Spec compliant OR ❌ Issues found: [list]
Task tool (code-review):
description: "Code quality review for Task N"
prompt: |
Review code quality for [what was implemented].
Base SHA: [commit before task]
Head SHA: [current commit]
Focus on: code cleanliness, test quality, maintainability
Never:
If subagent fails task:
Required workflow skills: