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 when starting any conversation - establishes how to find and use skills, requiring skill tool invocation before ANY response including clarifying questions.
Use when exploring or modifying a codebase and you need a cheap structural map of files, directories, imports, exports, or direct members before reading full source.
Guide for writing ast-grep rules to perform structural code search and analysis. Use when searching codebases using AST patterns, finding specific language constructs, or executing complex structural code queries.
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.
Review changes since a fixed ref along two axes (Standards & Spec) using parallel sub-agents. Use when reviewing branches, PRs, or diffs.
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
| name | subagent-driven-development |
| description | Use when executing implementation plans with independent tasks in the current session. |
Execute implementation plans sequentially in a single session by delegating independent tasks to subagents, enforced by a two-stage review: spec compliance followed by code quality.
Pre-computation Announcement: "I'm using the subagent-driven-development skill to implement the plan."
Continuous Execution Rule: Run continuously to completion without pausing for human check-ins between tasks. Stop only if blocked, encountering ambiguous requirements, or when all tasks are complete.
./implementer-prompt.md - Task implementation../spec-reviewer-prompt.md - Specification alignment verification../code-quality-reviewer-prompt.md - Code quality and test verification.