📦 obra/superpowers：赋予编码智能体超能力的开发方法论

Superpowers 是一套为你的编码智能体打造的完整软件开发方法论，构建在一组可组合技能和一些初始指令之上，确保你的智能体会使用这些技能。

我们正在招聘一名全职人员来帮助 Superpowers 社区和代码工作。你可以在 https://primeradiant.com/jobs/superpowers-community-engineer/ 查看职位说明。如果你身边有合适的人选，请务必推荐给我们。

为你的智能体赋予超能力：Claude Code、Antigravity、Codex App、Codex CLI、Cursor、Factory Droid、GitHub Copilot CLI、Kimi Code、OpenCode、Pi。

这一切从你启动编码智能体的那一刻开始。当它发现你正在构建某个东西时，它不会直接跳入尝试编写代码。相反，它会退后一步，询问你真正想要达成什么。

一旦它从对话中梳理出一份规范，就会分成足够短的片段展示给你，让你能够真正阅读和消化。

在你确认设计之后，你的智能体会整理出一份实现计划，这份计划足够清晰，即使是一位品味糟糕、缺乏判断力、没有项目背景且厌恶测试的热情初级工程师也能遵循。它强调真正的红/绿测试驱动开发（TDD）、YAGNI（你不会需要它）和 DRY 原则。

接下来，当你说“开始”后，它会启动一个 子智能体驱动开发 流程，让智能体完成每个工程任务，检查并审查其工作，然后继续推进。你的智能体经常能够自主工作一两个小时而不偏离你们共同制定的计划。

还有很多其他内容，但这是系统的核心。由于技能是自动触发的，你不需要做任何特殊操作。你的编码智能体就此拥有了超能力。

如果你在企业中使用 Superpowers，并且可以受益于商业支持、额外工具或托管支出，请随时通过 sales@primeradiant.com 联系我们。

安装方式因运行环境而异。如果你使用多个环境，请为每个环境分别安装 Superpowers。

Claude Code

Superpowers 可通过 Claude 官方插件市场 获取。

Superpowers 市场为 Claude Code 提供了 Superpowers 及其他一些相关插件。

Antigravity

从本仓库安装 Superpowers 插件：

agy plugin install https://github.com/obra/superpowers

Antigravity 会运行插件的会话启动钩子，因此 Superpowers 从第一条消息起就会生效。使用相同命令重新安装即可更新。

Codex App

Superpowers 可通过 Codex 官方插件市场 获取。

• 在 Codex 应用中，点击侧边栏的 Plugins。
• 你应在 Coding 分类下看到 Superpowers。
• 点击 Superpowers 旁的 + 并按照提示操作。

Codex CLI

Superpowers 可通过 Codex 官方插件市场 获取。

• 在 Cursor Agent 聊天中，从市场安装：

• 或在插件市场中搜索 “superpowers”。

Kimi Code

Superpowers 可在 Kimi Code 的插件市场中找到。

• 打开 Kimi Code 的插件管理器：

• 前往 Marketplace > Superpowers 并安装。

• 或直接从本仓库安装：

  /plugins install https://github.com/obra/superpowers
  

• 详细文档：docs/README.kimi.md

OpenCode

OpenCode 使用自己的插件安装方式；即使你已在其他环境中使用 Superpowers，也请单独安装。

Pi

从本仓库安装 Superpowers 作为 Pi 包：

pi install git:github.com/obra/superpowers

对于本地开发，将本仓库 checkout 作为临时包加载运行 Pi：

pi -e /path/to/superpowers

Pi 包加载 Superpowers 技能和一个小型扩展，在会话启动和每次压缩后注入 using-superpowers 引导程序。Pi 拥有原生技能支持，因此不需要兼容的 Skill 工具。子智能体和任务列表工具仍是可选的 Pi 伴侣包。

1. brainstorming（头脑风暴） – 在编写代码前激活。通过提问完善粗略想法，探索替代方案，分段展示设计以供验证。保存设计文档。

2. using-git-worktrees（使用 git 工作树） – 在设计获批后激活。在新分支上创建隔离工作空间，运行项目设置，验证干净的测试基线。

3. writing-plans（编写计划） – 在获得已批准的设计后激活。将工作分解为一口大小的任务（每个 2-5 分钟）。每个任务都有确切文件路径、完整代码和验证步骤。

4. subagent-driven-development（子智能体驱动开发） 或 executing-plans（执行计划） – 在有了计划后激活。为每个任务分派一个全新子智能体，并执行两阶段审查（先检查是否符合规范，再审查代码质量），或以批次方式执行，中间设置人工检查点。

5. test-driven-development（测试驱动开发） – 在实现过程中激活。强制执行红-绿-重构：先写失败测试，观察其失败，编写最少代码，观察通过，然后提交。删除在测试之前编写的代码。

6. requesting-code-review（请求代码审查） – 在任务之间激活。根据计划进行审查，按严重程度报告问题。严重问题会阻塞进度。

7. finishing-a-development-branch（完成开发分支） – 当任务完成时激活。验证测试，提供选项（合并/发起 PR/保留/丢弃），清理工作树。

智能体在执行任何任务前都会检查相关技能。 这是强制性工作流，而非建议。

技能目录

测试

• test-driven-development（测试驱动开发） – 红-绿-重构循环（包含测试反模式参考）

调试

• systematic-debugging（系统化调试） – 四阶段根因分析过程（包含根因追溯、纵深防御、基于条件的等待等技术）
• verification-before-completion（完成前验证） – 确保问题确实已修复

协作

• brainstorming（头脑风暴） – 苏格拉底式的设计提炼
• writing-plans（编写计划） – 详细的实现计划
• executing-plans（执行计划） – 带检查点的批量执行
• dispatching-parallel-agents（分派并行智能体） – 并行的子智能体工作流
• requesting-code-review（请求代码审查） – 审查前检查清单
• receiving-code-review（接收代码审查） – 对反馈的回应
• using-git-worktrees（使用 git 工作树） – 并行开发分支
• finishing-a-development-branch（完成开发分支） – 合并/PR 决策工作流
• subagent-driven-development（子智能体驱动开发） – 带两阶段审查（规范合规、代码质量）的快速迭代

元技能

• writing-skills（编写技能） – 遵循最佳实践创建新技能（包含测试方法论）
• using-superpowers（使用超能力） – 技能系统简介

原则

• 测试驱动开发 – 始终先写测试
• 系统化优于临时性 – 按流程走，而非靠猜测
• 降低复杂度 – 将简洁作为首要目标
• 证据优于声明 – 验证之后再宣布成功

阅读原始发布公告。

贡献

以下是 Superpowers 的一般贡献流程。请记住，我们通常不接受新技能的贡献，且任何技能更新都必须在我们支持的所有编码智能体中正常工作。

1. Fork 仓库
2. 切换到 'dev' 分支
3. 为你的工作创建分支
4. 遵循 writing-skills 技能来创建和测试新的或修改过的技能
5. 提交 PR，务必填写拉取请求模板。

技能行为测试使用 superpowers-evals 中的 drill eval 框架，将其克隆到 evals/ 目录——设置步骤见 evals/README.md。插件基础设施测试位于 tests/ 目录，通过相应的 run-*.sh 或 npm test 运行。

完整指南见 skills/writing-skills/SKILL.md。

更新方式在一定程度上取决于所使用的编码智能体，但通常是自动完成的。

许可证

MIT 许可证 - 详情见 LICENSE 文件

可视化伴侣遥测

由于技能和插件无法向创作者提供任何反馈，我们无从知晓有多少用户正在使用 Superpowers。默认情况下，头脑风暴的可选可视化伴侣功能中的 Prime Radiant 徽标会从我们的网站加载。它包含正在使用的 Superpowers 版本号。它不包含有关你的项目、提示或编码智能体的任何详细信息。我们看不到你的点击行为，也不知道你在构建什么。这仅帮助我们大致了解有多少用户正在使用 Superpowers 以及他们使用的版本。此功能 100% 可选。要禁用，请将环境变量 SUPERPOWERS_DISABLE_TELEMETRY 设置为任何真值。Superpowers 同样遵守 Claude Code 的 DISABLE_TELEMETRY 和 CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC 退出选项。

社区

Superpowers 由 Jesse Vincent 和 Prime Radiant 的其他成员共同打造。

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.

We're hiring someone to help out full time with Superpowers community and code work. You can read about the job at https://primeradiant.com/jobs/superpowers-community-engineer/ If this sounds like someone you know, definitely send them our way.

Give your agent Superpowers: Claude Code, Antigravity, Codex App, Codex CLI, Cursor, Factory Droid, GitHub Copilot CLI, Kimi Code, OpenCode, Pi.

It starts from the moment you fire up your coding agent. As soon as it sees that you're building something, it doesn't just jump into trying to write code. Instead, it steps back and asks you what you're really trying to do.

Once it's teased a spec out of the conversation, it shows it to you in chunks short enough to actually read and digest.

After you've signed off on the design, your agent puts together an implementation plan that's clear enough for an enthusiastic junior engineer with poor taste, no judgement, no project context, and an aversion to testing to follow. It emphasizes true red/green TDD, YAGNI (You Aren't Gonna Need It), and DRY.

Next up, once you say "go", it launches a subagent-driven-development process, having agents work through each engineering task, inspecting and reviewing their work, and continuing forward. It's not uncommon for your agent to work autonomously for a couple hours at a time without deviating from the plan you put together.

There's a bunch more to it, but that's the core of the system. And because the skills trigger automatically, you don't need to do anything special. Your coding agent just has Superpowers.

If you're using Superpowers in enterprise and could benefit from commercial support, additional tooling, or managed spending, please don't hesitate to drop us a line at sales@primeradiant.com.

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

Superpowers is available via the official Claude plugin marketplace

The Superpowers marketplace provides Superpowers and some other related plugins for Claude Code.

Install Superpowers as a plugin from this repository:

agy plugin install https://github.com/obra/superpowers

Antigravity runs the plugin's session-start hook, so Superpowers is active from the first message. Reinstall with the same command to update.

Superpowers is available via the official Codex plugin marketplace.

• In the Codex app, click on Plugins in the sidebar.
• You should see Superpowers in the Coding section.
• Click the + next to Superpowers and follow the prompts.

Superpowers is available via the official Codex plugin marketplace.

• In Cursor Agent chat, install from marketplace:

• Or search for "superpowers" in the plugin marketplace.

Superpowers is available in Kimi Code's plugin marketplace.

• Open Kimi Code's plugin manager:

• Go to Marketplace > Superpowers and install it.

• Or install directly from this repository:

  /plugins install https://github.com/obra/superpowers
  

• Detailed docs: docs/README.kimi.md

OpenCode uses its own plugin install; install Superpowers separately even if you already use it in another harness.

Install Superpowers as a Pi package from this repository:

pi install git:github.com/obra/superpowers

For local development, run Pi with this checkout loaded as a temporary package:

pi -e /path/to/superpowers

The Pi package loads the Superpowers skills and a small extension that injects the using-superpowers bootstrap at session startup and again after compaction. Pi has native skills, so no compatibility Skill tool is required. Subagent and task-list tools remain optional Pi companion packages.

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. Enforces RED-GREEN-REFACTOR: write failing test, watch it fail, write minimal code, watch it pass, commit. Deletes code written before tests.

6. requesting-code-review - Activates between tasks. Reviews against plan, reports issues by severity. Critical issues block progress.

7. finishing-a-development-branch - Activates when tasks complete. Verifies tests, presents options (merge/PR/keep/discard), cleans up worktree.

The agent checks for relevant skills before any task. Mandatory workflows, not suggestions.

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
• subagent-driven-development - Fast iteration with two-stage review (spec compliance, then code quality)

Meta

• writing-skills - Create new skills following best practices (includes testing methodology)

• using-superpowers - Introduction to the skills system

• Test-Driven Development - Write tests first, always

• Systematic over ad-hoc - Process over guessing

• Complexity reduction - Simplicity as primary goal

• Evidence over claims - Verify before declaring success

Read the original release announcement.

The general contribution process for Superpowers is below. Keep in mind that we don't generally accept contributions of new skills and that any updates to skills must work across all of the coding agents we support.

1. Fork the repository
2. Switch to the 'dev' branch
3. Create a branch for your work
4. Follow the writing-skills skill for creating and testing new and modified skills
5. Submit a PR, being sure to fill in the pull request template.

Skill-behavior tests use the drill eval harness from superpowers-evals, cloned into evals/ — see evals/README.md for setup. Plugin-infrastructure tests live at tests/ and run via the relevant run-*.sh or npm test.

See skills/writing-skills/SKILL.md for the complete guide.

Superpowers updates are somewhat coding-agent dependent, but are often automatic.

MIT License - see LICENSE file for details

Visual companion telemetry

Because skills and plugins don't provide any feedback to creators, we have no idea how many of you are using Superpowers. By default, the Prime Radiant logo on brainstorming's optional visual companion feature is loaded from our website. It includes the version of Superpowers in use. It does not include any details about your project, prompt, or coding agent. We don't see your clicks or anything about what you're building. This helps us have a rough idea of how many folks are using Superpowers and which version of Superpowers they're using. It's 100% optional. To disable this, set the environment variable SUPERPOWERS_DISABLE_TELEMETRY to any true value. Superpowers also honors Claude Code's DISABLE_TELEMETRY and CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC opt-outs.

Community

Superpowers is built by Jesse Vincent and the rest of the folks at Prime Radiant.