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
| name | subagent-driven-development |
| description | Use when executing implementation plans with independent tasks in the current session |
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
digraph when_to_use {
"Have implementation plan?" [shape=diamond];
"Tasks mostly independent?" [shape=diamond];
"Stay in this session?" [shape=diamond];
"subagent-driven-development" [shape=box];
"executing-plans" [shape=box];
"Manual execution or brainstorm first" [shape=box];
"Have implementation plan?" -> "Tasks mostly independent?" [label="yes"];
"Have implementation plan?" -> "Manual execution or brainstorm first" [label="no"];
"Tasks mostly independent?" -> "Stay in this session?" [label="yes"];
"Tasks mostly independent?" -> "Manual execution or brainstorm first" [label="no - tightly coupled"];
"Stay in this session?" -> "subagent-driven-development" [label="yes"];
"Stay in this session?" -> "executing-plans" [label="no - parallel session"];
}
vs. Executing Plans (parallel session):
Read plan, extract all tasks with full text, note context, create TodoWrite with all tasks, then dispatch implementer subagent per task with two-stage review:
For each task:
vs. Manual execution:
vs. Executing Plans:
Efficiency gains:
Quality gates:
Never:
If subagent asks questions:
If reviewer finds issues:
If subagent fails task:
Required workflow skills:
Subagents should use:
Alternative workflow:
Smart dependency management for any language. Auto-detects project type, applies safe updates automatically, prompts for major versions, diagnoses and fixes dependency issues.
Patterns and guidelines for writing Playwright E2E tests in this project — page object rules, assertion placement, and locator conventions. Use when writing new tests or reviewing existing ones.
Use when Codex updates, fixes, or adds unit tests in this project. Covers basic unit test conventions, Vitest usage, and Cloudflare-related unit tests that should use Cloudflare's Vitest worker-pool integration instead of hand-rolled runtime mocks.
You MUST use this 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
Run, write, and debug Playwright E2E tests for this project. Use when running a single test file or a single named test, writing new E2E tests, working with Page Objects, or mocking songs. Covers test setup, page object initialization, and song fixture mocking.