brainstorming

Convert ambiguous ideas into validated architecture and specification designs through an approval-gated workflow.

3|Updated Feb 2, 2026
One-click install
npx skills add https://github.com/pedropaulovc/agent-plugins --skill brainstorming-pedropaulovc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: brainstorming
Source: https://github.com/pedropaulovc/agent-plugins/tree/main/plugins/superpowers/skills/brainstorming
Command: npx skills add https://github.com/pedropaulovc/agent-plugins --skill brainstorming-pedropaulovc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents wasted implementation work by turning rough ideas into validated designs through structured clarification, trade-off exploration, and explicit user approval.

Core Features & Use Cases

  • Context exploration: Reviews the current project state (files, docs, and recent commits) to ground the design in reality.
  • Batched clarifying questions: Uses AskUserQuestion to gather up to four related requirements at a time, grouped by theme (purpose, constraints, success criteria).
  • 2–3 approach proposal with trade-offs: Surfaces multiple viable solutions, recommends one, and explains why before committing to direction.
  • Incremental design validation with approvals: Presents the design section-by-section and pauses for confirmation, revising when needed.
  • Design documentation + implementation handoff: Writes a validated design doc into docs/plans/YYYY-MM-DD-<topic>-design.md, commits it, and then transitions only to the writing-plans skill.

Quick Start

Tell the assistant to brainstorm and produce an implementation-ready design for the feature you want to build, then wait for approval before any implementation starts.

Frequently Asked Questions about brainstorming

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I turn an ambiguous engineering idea into a validated architecture design?

To turn an ambiguous engineering idea into a validated architecture design, this skill explores project context, asks batched clarifying questions, and proposes 2-3 approaches with trade-offs. It requires explicit user approval before saving the final specification design doc.

What is the best way to gather requirements and propose technical trade-offs before implementation?

The best way to gather requirements and propose trade-offs is through an approval-gated workflow that groups up to four related clarifying questions by theme. This ensures constraints and success criteria are clarified before recommending a specific engineering planning direction.

Does this requirements gathering process integrate with existing project files and recent commits?

Yes, the requirements gathering process integrates with existing project files and recent commits. It performs context exploration to review the current project state, ensuring the specification design and architecture proposals are grounded in your actual codebase reality.

How do I document a finalized feature design and transition to writing implementation plans?

To document a feature design and transition to writing plans, the skill saves a validated design doc into docs/plans/YYYY-MM-DD-<topic>-design.md and commits it. After user approval, it explicitly transitions to the writing-plans skill for implementation.

Can I revise architecture proposals section-by-section during the design approval workflow?

Yes, you can revise architecture proposals section-by-section during the design approval workflow. The skill presents the design incrementally and pauses for confirmation at user approval checkpoints, allowing you to request revisions before the final design doc is saved.

When should I not use a structured specification design workflow for feature development?

You should not use a structured specification design workflow for feature development when requirements are already fully defined or for trivial changes. It is specifically built for ambiguous modification requests where constraints must be clarified to prevent wasted implementation work.