---
id: manual-superpowers
name: "Superpowers"
nameZh: "Superpowers 开发流程"
sourceCategory: "Agent Skills"
sourceCategoryZh: "Agent Skills"
url: "https://github.com/obra/superpowers"
sourceUrl: "https://github.com/obra/superpowers"
tags: ["Planning","Subagents","TDD"]
tagsZh: ["规划","子 Agent","TDD"]
categorySlugs: ["dev","testing","meta-tools"]
---

# Superpowers

中文名称：Superpowers 开发流程

## Description

Structures multi-step development with plans, subagents, and TDD.

用计划、子 Agent 和 TDD 组织多步骤开发流程。

## 中文说明

用计划、子 Agent 和 TDD 组织多步骤开发流程。

- 打开或安装 Skill：https://github.com/obra/superpowers
- 查看原始来源：https://github.com/obra/superpowers
- 分类：dev, testing, meta-tools
- 标签：规划、子 Agent、TDD

## Use This Skill

- Open or install the skill from: https://github.com/obra/superpowers
- Review the original source: https://github.com/obra/superpowers
- Categories: dev, testing, meta-tools
- Tags: Planning, Subagents, TDD
- 中文标签：规划、子 Agent、TDD

## README SEO Report

### Detailed Overview

Superpowers is a complete software development methodology for your coding agents, built on top of a set of composable skills and some initial instructions that make sure your agent uses them.

### Installation

Installation differs by harness. If you use more than one, install Superpowers separately for each one.

### Usage

1. brainstorming - Activates before writing code. Refines rough ideas through questions, explores alternatives, presents design in sections for validation. Saves design document. 2. using-git-worktrees - Activates after design approval. Creates isolated workspace on new branch, runs project setup, verifies clean test baseline. 3. writing-plans - Activates with approved design. Breaks work into bite-sized tasks (2-5 minutes each). Every task has exact file paths, complete code, verification steps. 4. subagent-driven-development or executing-plans - Activates with plan. Dispatches fresh subagent per task with two-stage review (spec compliance, then code quality), or executes in batches with human checkpoints. 5. test-driven-development - Activates during implementation....

### Capabilities

Testing - test-driven-development - RED-GREEN-REFACTOR cycle (includes testing anti-patterns reference) Debugging - systematic-debugging - 4-phase root cause process (includes root-cause-tracing, defense-in-depth, condition-based-waiting techniques) - verification-before-completion - Ensure it's actually fixed Collaboration - brainstorming - Socratic design refinement - writing-plans - Detailed implementation plans - executing-plans - Batch execution with checkpoints - dispatching-parallel-agents - Concurrent subagent workflows - requesting-code-review - Pre-review checklist - receiving-code-review - Responding to feedback - using-git-worktrees - Parallel development branches - finishing-a-development-branch - Merge/PR decision workflow...

### Source Archive

- Archive source type: github
- Primary README/SKILL doc: github/README.md
- Archived docs: github/README.md, github/AGENTS.md, github/CLAUDE.md, github/.claude-plugin/plugin.json

## 3W FAQ

### What is this skill?

Structures multi-step development with plans, subagents, and TDD.

### Who is this skill for?

This skill is for teams or AI agents working on dev, testing, meta-tools workflows.

### When should you use it?

Use it when the task matches these tags: Planning, Subagents, TDD.

## 中文 3W FAQ

### What：这个 skill 是什么？

用计划、子 Agent 和 TDD 组织多步骤开发流程。

### Who：适合谁使用？

适合处理 dev、testing、meta-tools 工作流的团队、运营人员、开发者或 AI Agent。

### When：什么时候使用？

当任务涉及 规划、子 Agent、TDD，或需要沉淀为 Claude Skills、Codex Skills、Gemini Skills、Kimi Skills、GLM Skills 或团队 SOP 时使用。