跳到主内容
智客 ZICQ

技能库 智客分类:Agent 工作流 superpowers OpenClaw

Superpowers

Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功能分支——触发测试验证+合并/PR选项. 不用于:一行修正(只是编辑),读取代码,或非代码任务. 需要执行工具和会话_ sprawn.

741 安装量 · 26 星标

官方网址:ClawHub

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

Spec-first,TDD,子代理驱动软件开发工作流程

何时用

(1)构建任何新功能或应用——触发脑暴_计划_子剂执行回路 (2)调试出一个bug或测试失败——引发系统化的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个已经被打破",(4)完成一个功能

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Superpowers — OpenClaw Edition、The Pipeline、Phase 1: Brainstorming、Phase 2: Writing Plans、Phase 3: Subagent-Driven Development、Phase 4: Systematic Debugging。

文件分析

文件分析:除 SKILL.md 外,正文引用了 references/brainstorming.md、references/writing-plans.md、references/subagent-development.md、references/tdd.md、references/systematic-debugging.md、references/finishing-branch.md,属于带资源的技能包,这些文件按需再读。

官方 description(原文)

Spec-first, TDD, subagent-driven software development workflow. Use when: (1) building any new feature or app — triggers brainstorm → plan → subagent execution loop, (2) debugging a bug or test failure — triggers systematic root-cause process, (3) user says "let's build", "help me plan", "I want to add X", or "this is broken", (4) completing a feature branch — triggers test verification + merge/PR options. NOT for: one-liner fixes (just edit), reading code, or non-code tasks. Requires exec tool and sessions_spawn.

Superpowers — OpenClaw EditionThe PipelinePhase 1: BrainstormingPhase 2: Writing PlansPhase 3: Subagent-Driven DevelopmentPhase 4: Systematic DebuggingPhase 5: Finishing a BranchOpenClaw Subagent Dispatch PatternKey Principles

来源分类:ClawHub Debugging

SKILL.md 与 Agent 调用

官方规范 ↗
name
superpowers
description
Spec-first, TDD, subagent-driven software development workflow. Use when: (1) building any new feature or app — triggers brainstorm → plan → subagent execution loop, (2) debugging a bug or test failure — triggers systematic root-cause process, (3) user says "let's build", "help me plan", "I want to add X", or "this is broken", (4) completing a feature branch — triggers test verification + merge/PR options. NOT for: one-liner fixes (just edit), reading code, or non-code tasks. Requires exec tool and sessions_spawn.
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。
指令中引用的文件 · 6
  • references/brainstorming.md
  • references/writing-plans.md
  • references/subagent-development.md
  • references/tdd.md
  • references/systematic-debugging.md
  • references/finishing-branch.md

以下路径提取自原文;文件是否齐全请以来源仓库中的完整目录为准。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

该技能引用了附属文件,请从来源获取完整目录;仅复制 SKILL.md 可能缺少依赖。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「superpowers」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-2480c0081c6b021c-%E8%B6%85%E7%BA%A7%E5%8A%9B%E9%87%8F.html
请存为 .cursor/skills/superpowers/SKILL.md 或 .claude/skills/superpowers/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。
该技能还带 scripts/、references/、assets/ 等文件,请从 https://clawhub.ai/skills/superpowers 取完整目录,不要只建一个 SKILL.md。

当前没有明确的 GitHub 技能包地址,请按来源页面的安装器说明操作。

ClawHub ↗

阅读排版
--- name: superpowers description: > Spec-first, TDD, subagent-driven software development workflow. Use when: (1) building any new feature or app — triggers brainstorm → plan → subagent execution loop, (2) debugging a bug or test failure — triggers systematic root-cause process, (3) user says "let's build", "help me plan", "I want to add X", or "this is broken", (4) completing a feature branch — triggers test verification + merge/PR options. NOT for: one-liner fixes (just edit), reading code, or non-code tasks. Requires exec tool and sessions_spawn. --- # Superpowers — OpenClaw Edition Adapted from [obra/superpowers](https://github.com/obra/superpowers). Mandatory workflow — not suggestions. ## The Pipeline ``` Idea → Brainstorm → Plan → Subagent-Driven Build (TDD) → Code Review → Finish Branch ``` Every coding task follows this pipeline. "Too simple to need a design" is always wrong. --- ## Phase 1: Brainstorming **Trigger:** User wants to build something. Activate before touching any code. **See:** [references/brainstorming.md](references/brainstorming.md) **Summary:** 1. Explore project context (files, docs, recent commits) 2. Ask clarifying questions — **one at a time**, prefer multiple choice 3. Propose 2–3 approaches with trade-offs + recommendation 4. Present design in sections, get approval after each 5. Write design doc → `docs/plans/YYYY-MM-DD--design.md` → commit 6. Hand off to **Phase 2: Writing Plans** **HARD GATE:** Do NOT write any code until user approves design. --- ## Phase 2: Writing Plans **Trigger:** Design approved. Activated by brainstorming phase. **See:** [references/writing-plans.md](references/writing-plans.md) **Summary:** - Write a detailed task-by-task implementation plan - Each task = 2–5 minutes: write test → watch fail → implement → watch pass → commit - Save to `docs/plans/YYYY-MM-DD-.md` - Announce: `"I'm using the writing-plans skill to create the implementation plan."` - After saving, offer two execution modes: - **Subagent-driven (current session):** `sessions_spawn` per task + two-stage review - **Manual execution:** User runs tasks themselves --- ## Phase 3: Subagent-Driven Development **Trigger:** Plan exists, user chooses subagent-driven execution. **See:** [references/subagent-development.md](references/subagent-development.md) **Per-task loop (OpenClaw):** 1. `sessions_spawn` an implementer subagent with task + full plan context 2. Wait for completion announcement 3. `sessions_spawn` a spec-reviewer subagent → must confirm code matches spec 4. `sessions_spawn` a code-quality reviewer subagent → must approve quality 5. Fix any issues, re-review if needed 6. Mark task done, move to next 7. Final: dispatch overall code reviewer → hand off to Phase 5 **TDD is mandatory in every task.** See [references/tdd.md](references/tdd.md). --- ## Phase 4: Systematic Debugging **Trigger:** Bug, test failure, unexpected behaviour — any technical issue. **See:** [references/systematic-debugging.md](references/systematic-debugging.md) **HARD GATE:** No fixes without root cause investigation first. **Four phases:** 1. Root Cause Investigation (read errors, reproduce, check recent changes, trace data flow) 2. Pattern Analysis (find working examples, compare, identify differences) 3. Hypothesis + Testing (one hypothesis at a time, test to prove/disprove) 4. Fix + Verification (fix at root, not symptom; verify fix doesn't break anything) --- ## Phase 5: Finishing a Branch **Trigger:** All tasks complete, all tests pass. **See:** [references/finishing-branch.md](references/finishing-branch.md) **Summary:** 1. Verify all tests pass 2. Determine base branch 3. Present 4 options: merge locally / push + PR / keep / discard 4. Execute choice 5. Clean up --- ## OpenClaw Subagent Dispatch Pattern When dispatching implementer or reviewer subagents, use `sessions_spawn`: ``` Goal: [one sentence] Context: [why it matters, which plan file] Files: [exact paths] Constraints: [what NOT to do — no scope creep, TDD only] Verify: [how to confirm success — tests pass, specific command] Task text: [paste full task from plan] ``` Run `sessions_spawn` with the task as a detailed prompt. The sub-agent announces results automatically. --- ## Key Principles - **One question at a time** during brainstorm - **TDD always** — write failing test first, delete code written before tests - **YAGNI** — remove unnecessary features from all designs - **DRY** — no duplication - **Systematic over ad-hoc** — follow the process especially under time pressure - **Evidence over claims** — verify before declaring success - **Frequent commits** — after each green test

相关技能

Agent 工作流

Skill Creator

创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.

Agent 工作流

Clawdhub

使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.

Agent 工作流

Agent Team Orchestration

管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.

Agent 工作流

Find Skills

帮助用户发现并安装代理技能,当他们询问诸如"我如何做X","为X找到一个技能","是否有一种技能可以...",或者表达对扩展能力的兴趣时. 当用户寻找可能作为可安装技能存在的功能时,应当使用这种技能.