brainstorming

Guides collaborative design exploration and spec writing before any implementation work begins.

Updated Sep 11, 2026
One-click install
npx skills add https://github.com/CYRUS-pinto/pi-bot --skill brainstorming-cyrus-pinto
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: brainstorming
Source: https://github.com/CYRUS-pinto/pi-bot/tree/main/.agents/skills/brainstorming
Command: npx skills add https://github.com/CYRUS-pinto/pi-bot --skill brainstorming-cyrus-pinto

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve? It prevents wasted implementation effort by forcing intent exploration, requirement clarification, and explicit human approval before any code is written, catching unexamined assumptions early. ## Core Features & Use Cases - Three-Path Classification: Routes every request into spike, bounded, or architectural tracks with appropriately scaled process and approval gates. - Structured Design Dialogue: Asks clarifying questions one at a time, proposes 2-3 approaches with trade-offs, and presents sectioned designs for approval. - Spec Writing and Review: Writes validated designs to dated spec files, runs self-review checks for placeholders and contradictions, and hands off to implementation planning. - Visual Companion Server: Serves browser-based mockups, diagrams, and clickable option screens via a local Node.js server with WebSocket event capture. - Use Case: When asked to add a new feature, classify the request, present a short design in chat, wait for explicit approval, then implement — or for larger work, produce a committed spec document first. ## Quick Start Ask the agent to brainstorm and design the feature you have in mind before writing any code, and approve the presented design before implementation starts.

Frequently Asked Questions about brainstorming

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

FAQPage Schema
How do I brainstorm a feature design before writing code?

Classify the request as spike, bounded, or architectural, then explore project context and ask clarifying questions one at a time. Present a design scaled to the task and wait for explicit approval before any implementation begins.

What is the difference between spike, bounded, and architectural tasks?

A spike answers a feasibility question with throwaway work. Bounded covers well-scoped changes to existing code flows with a short in-chat design. Architectural covers new projects or subsystem restructuring and requires a full written spec.

When should I write a design spec document?

Write a spec only on the architectural path, after the user approves the presented design sections. Save it to docs/superpowers/specs with a dated filename, self-review for placeholders and contradictions, then get user review before planning.

How does the visual brainstorming companion work?

A local Node.js server watches a content directory for HTML files and serves the newest one to the browser over an authenticated session key. User clicks are captured via WebSocket and recorded as JSON events for the agent to read.

Can I skip the approval step for simple changes?

No. Every path ends with explicit human approval before implementation, even for trivial changes. Simple tasks only shrink the design artifact to a few sentences in chat; the approval gate itself never scales down.