Individual skill
subagent-driven-development
当在当前会话中执行包含独立任务的实现计划时使用
skills/subagent-driven-development/SKILL.md
Source commit 020339d1410e51a9eca16d26f4eac4cfee166d8a
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Not checked yet
- Last checked
- Nov 2, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 8,494
- Repository last updated
- Oct 26, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- ai-coding Repository topic
- chinese Repository topic
- claude-code Repository topic
- cursor Repository topic
- mcp Repository topic
- skills Repository topic
- superpowers Repository topic
- tdd Repository topic
- agent-skills Repository topic
- agentic-coding Repository topic
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 32,976 bytesimplementer-prompt.mddoc · 6,175 bytesre-review-prompt.mddoc · 4,999 bytesscripts/review-packageruns · 2,029 bytesscripts/sdd-workspaceruns · 3,684 bytesscripts/task-briefruns · 1,580 bytestask-reviewer-prompt.mddoc · 9,106 bytes
Read excerpt
# 子智能体驱动开发
通过为每个任务分派一个全新的实现子智能体来执行计划：每个任务完成后做一次任务审查（规格合规性 + 代码质量），全部任务结束后再做一次覆盖整个分支的宽范围审查。
**为什么用子智能体：** 你把任务委派给具有隔离上下文的专用智能体。通过精心设计它们的指令和上下文，确保它们专注并成功完成任务。它们绝不应继承你会话的上下文或历史记录——你要精确构造它们所需的一切。这样也能为你自己保留用于协调工作的上下文。
**核心原则：** 每个任务一个全新子智能体 + 任务审查（规格 + 质量）+ 结尾宽范围审查 = 高质量、快速迭代
**旁白：** 工具调用之间最多说一句简短的旁白——进度账本和工具结果本身就是记录。
**持续执行：** 不要在任务之间停下来向你的人类伙伴确认。不间断地执行计划里的所有任务。唯一该停下的理由是：你无法解决的 BLOCKED 状态、确实妨碍推进的歧义，或所有任务已完成。"我该继续吗？"之类的询问和进度小结都在浪费他们的时间——他们让你执行计划，那就执行。
**做裁决，不要停摆。** 一个正在跑的计划不等人。冲突、歧义、计划缺陷、你本来想申请突破的上限——你自己定。规格是有约束力的权威，计划是它的论证，两者都答不上来的部分由你的判断来定。每个决定都以 `Ruling: <你决定了什么> — <为什么> — <如果错了代价是什么>` 记进账本，然后继续。一个错误的裁决，代价是你人类伙伴看得见、也撤得掉的返工；一个停在问题上的会话，代价是他们的一整天，而且什么也换不来。
