superpowers-brainstorming
Use before any creative work - creating features, building components, adding functionality, or modifying behavior - guides through exploration, questioning, design proposal, and spec documentation before any implementation
Best use case
superpowers-brainstorming is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use before any creative work - creating features, building components, adding functionality, or modifying behavior - guides through exploration, questioning, design proposal, and spec documentation before any implementation
Teams using superpowers-brainstorming should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/superpowers-brainstorming/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How superpowers-brainstorming Compares
| Feature / Agent | superpowers-brainstorming | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Use before any creative work - creating features, building components, adding functionality, or modifying behavior - guides through exploration, questioning, design proposal, and spec documentation before any implementation
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Freelancers
Browse AI agent skills for freelancers handling client research, proposals, outreach, delivery systems, documentation, and repeatable admin work.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
Best AI Skills for ChatGPT
Find the best AI skills to adapt into ChatGPT workflows for research, writing, summarization, planning, and repeatable assistant tasks.
SKILL.md Source
# Superpowers Brainstorming - 想法到设计 ## 核心准则 **在创造性工作之前,通过协作对话将想法转化为完整的设计和规格说明。** **触发条件:** 创建功能、构建组件、添加功能、修改行为。 ## 硬性门槛 ``` 在调用任何实现技能、写任何代码、搭建任何项目、或采取任何实现动作之前, 必须先展示设计并获得主人批准。 无论感知到的复杂度如何,每个项目都要走这个流程。 ``` "简单"项目正是未审视假设造成最多浪费的地方。设计可以很短(真正简单的项目几句话就够),但必须展示并获得批准。 ## 流程检查表 按顺序完成每个任务: 1. **探索项目上下文** — 检查文件、文档、最近提交 2. **提出视觉化同伴**(如果主题涉及视觉问题)— 这是独立消息,不与澄清问题合并 3. **提出澄清问题** — 一次一个,理解目的/约束/成功标准 4. **提出 2-3 种方案** — 带有权衡和推荐 5. **展示设计** — 按复杂度缩放各部分,在每个部分后获批准 6. **写设计文档** — 保存到 `docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md` 并 commit 7. **规格自审** — 快速内联检查占位符、矛盾、模糊、范围 8. **主人审查书面规格** — 在继续之前请主人审查规格文件 9. **过渡到实现** — 调用 `superpowers-writing-plans` 技能创建实现计划 **终点状态是调用 writing-plans。不要调用任何其他实现技能。** ## 流程详解 ### 理解想法 - 先检查当前项目状态(文件、文档、最近提交) - 在问详细问题前,评估范围:如果请求描述多个独立子系统(如"构建有聊天、文件存储、计费、分析的平台"),立即标记。不要在需要先分解的项目上花时间细化细节。 - 对于适当范围的项目,一次问一个问题来细化想法 - 尽量用多选问题,但开放问题也可以 - 一次只问一个问题——如果主题需要更多探索,拆成多个问题 - 重点理解:目的、约束、成功标准 ### 探索方案 - 提出 2-3 个不同方案,带权衡 - 用对话方式展示选项,说明推荐和原因 - 用推荐选项开头并解释为什么 ### 展示设计 - 一旦相信理解了要构建什么,就展示设计 - 每个部分按复杂度缩放:直接的几句话,复杂的 200-300 字 - 每个部分后问"这样看起来对吗" - 覆盖:架构、组件、数据流、错误处理、测试 - 如果有不明白的地方准备好回去澄清 ### 为隔离和清晰而设计 - 将系统分成更小的单元,每个有明确目的,通过清晰接口通信,可以独立理解和测试 - 对于每个单元,应该能回答:它做什么,你怎么用它,它依赖什么? - 有人能在不读内部代码的情况下理解它做什么吗?能改变内部代码而不破坏消费者吗?如果不能,边界需要改进 - 更小、边界好的单元你也更容易处理——你更容易推理能放在脑子里的代码,编辑时也更可靠。当一个文件变大,通常是它做太多事的信号 ### 现有代码库中工作 - 在提出变更前先探索当前结构。遵循已有模式。 - 对于影响工作的现有代码问题(如长得太大的文件、边界不清、职责混乱),把针对性改进作为设计的一部分——好开发者在工作的代码中会做这些改进。 - 不要提无关的重构。聚焦于服务当前目标的内容。 ## 设计之后 **文档:** - 将经验证的设计(规格)写到 `docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md` - Commit 设计文档到 git **规格自审:** 写完规格文档后,用新眼光看: 1. **占位符扫描:** 有"TBD"、"TODO"、不完整部分或模糊需求吗?修复它们。 2. **内部一致性:** 各部分有矛盾吗?架构和功能描述匹配吗? 3. **范围检查:** 这个范围对于单一实现计划够聚焦吗?需要分解吗? 4. **模糊检查:** 任何需求能有两种解释吗?如果有,选一个并明确。 内联修复问题。不需要重新审查——修复并继续。 **主人审查门槛:** 规格审查循环通过后,在继续之前请主人审查书面规格: > "规格已写完并 commit 到 `<path>`。请审查,如果有要修改的告诉我,在我们开始写实现计划之前。" 等主人回复。如果请求变更,做修改并重新运行规格审查循环。只有在主人批准后才能继续。 **实现:** - 调用 `superpowers-writing-plans` 技能创建详细实现计划 - 不要调用其他技能。writing-plans 是下一步。 ## 关键原则 - **一次一个问题** — 不要用多个问题压垮 - **多选优先** — 比开放问题更容易回答 - **YAGNI 彻底** — 从所有设计中移除不必要功能 - **探索替代方案** — 在确定之前总是提出 2-3 个方案 - **增量验证** — 展示设计,获得批准后再继续 - **灵活** — 有不明白的回去澄清 ## 视觉化同伴(Canvas) 当预期接下来的问题涉及视觉内容时(模型、布局图、图表),提供 canvas 展示: - 使用 `canvas` 工具展示模型、图表、选项对比等视觉内容 - **每个问题决定是否用浏览器:** 用户看这个比读文字更好吗? - **用 canvas:** 内容本身是视觉的——模型、线框图、布局对比、架构图、并排视觉设计 - **用文字:** 内容是文字的——需求问题、概念选择、权衡列表、A/B/C/D 文本选项、范围决策 关于 UI 主题的问题不自动是视觉问题。"在这个语境中个性意味着什么?"是概念问题——用文字。"哪种向导布局更好?"是视觉问题——用 canvas。 ## 执行检查表 每次开始创意工作前,确认: - [ ] 已探索项目上下文 - [ ] 已询问澄清问题(一次一个) - [ ] 已提出 2-3 种方案并说明推荐 - [ ] 主人已批准设计 - [ ] 设计文档已写完并 commit - [ ] 已做规格自审并修复问题 - [ ] 主人已审查书面规格 - [ ] 已调用 writing-plans 开始实现
Related Skills
superpowers-executing-plans
Use when executing a written implementation plan in the current session with sequential task execution and review checkpoints - for when subagent-driven mode is not available
superpowers-writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code - guides writing comprehensive implementation plans with bite-sized tasks, TDD, and DRY/YAGNI principles
superpowers-verification
Use when about to claim any work is complete, fixed, passing, or successful - requires running fresh verification commands and reading actual output before making any success claims; evidence before assertions always
superpowers-tdd
Use when implementing any feature or bugfix, before writing implementation code - enforces RED-GREEN-REFACTOR cycle: write failing test first, verify it fails, write minimal code, verify it passes, then refactor
superpowers-systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior - enforces systematic four-phase debugging: root cause investigation, pattern analysis, hypothesis testing, and evidence-based fix verification
superpowers-subagent-dev
Use when executing implementation plans with independent tasks - coordinates task execution by dispatching subagents per task with verification checkpoints, adapted for OpenClaw's isolated session model
superpowers-parallel-agents
Use when facing 2 or more independent tasks that can be worked on without shared state - dispatches parallel subagents using sessions_spawn for concurrent investigation and execution, adapted for OpenClaw
superpowers-overview
Use when starting any development work or when unsure which superpowers development skill to use - provides entry point and navigation to the full superpowers skill suite for OpenClaw agents
superpowers-isolated-workspace
Use when starting feature work that needs isolation from current workspace - creates isolated git branches with clean setup and safety verification, adapted for OpenClaw environments
superpowers-finishing-branch
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - presents structured options for merge, PR, or cleanup; adapted for OpenClaw git workflow without worktrees
superpowers-requesting-code-review
Use when completing tasks, implementing major features, or before merging - dispatches code review subagent to catch issues before they cascade, adapted for OpenClaw sessions_spawn model
superpowers-receiving-code-review
Use when receiving code review feedback - requires technical verification before implementing suggestions, with reasoned pushback when feedback is technically questionable; no performative agreement