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
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/axelhu/superpowers-brainstormingWhat This Skill Does
The superpowers-brainstorming skill acts as your architectural navigator for any creative or technical project within OpenClaw. It enforces a strict, disciplined methodology that bridges the gap between raw ideas and production-ready code. By mandating a step-by-step progression—starting with context exploration, moving through clarifying questions, weighing architectural trade-offs, and culminating in a rigorous, committed design specification—this skill prevents the common pitfalls of "coding first and thinking later."
It ensures that every feature, component, or system modification is intentional, well-documented, and fully aligned with your goals. The skill guides you through a mandatory design-review loop, ensuring that you only proceed to implementation planning after a clearly defined, owner-approved blueprint is committed to the project's documentation folder.
Installation
To add this skill to your OpenClaw environment, use the following command:
clawhub install openclaw/skills/skills/axelhu/superpowers-brainstorming
Use Cases
- Complex Feature Development: Breaking down a large feature into smaller, manageable components with clear interfaces.
- Refactoring & Tech Debt: Strategically planning improvements in existing codebases while maintaining system stability.
- UI/UX Design Cycles: Using the visual companion features to iterate on layouts and models before writing a single line of code.
- Project Onboarding: Exploring existing project context and documentation to ensure new additions follow established design patterns.
Example Prompts
- "I want to add a real-time notification system to our dashboard. Can you help me brainstorm the architecture?"
- "We need to redesign the user authentication flow for better security. Let's start the brainstorming process."
- "I need to build a modular plugin system for our existing data processing pipeline. Can you explore the current structure and suggest some options?"
Tips & Limitations
- Strict Workflow: This skill is intentionally rigid. It forbids jumping to code execution. If you try to skip steps, the agent will guide you back to the design phase.
- Incremental Approval: Seek owner approval at every milestone. Do not treat the design as a static block; treat it as an evolving contract.
- Documentation Priority: The skill insists on writing specifications to
docs/superpowers/specs/to ensure project history and reasoning remain visible. - Avoid Over-design: While thorough, use the skill to prune unnecessary complexity—always apply YAGNI (You Ain't Gonna Need It) principles during the brainstorming sessions to keep your scope focused and maintainable.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-axelhu-superpowers-brainstorming": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read
Related Skills
Openclaw Sleep
Skill by axelhu
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-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
contacts
通讯录查询与维护技能。用于查找联系人信息(open_id、chat_id、account_id 等)、记录新联系人、或查询历史沟通偏好。触发时机:(1) 需要 @某人或向某渠道发消息时 (2) 认识新联系人后需要录入通讯录时 (3) 查询某人的联系方式或交流偏好时 (4) 询问"谁知道xxx的飞书ID"或"怎么联系xxx"时。
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