# Brainstorming

> Structured approach to explore ideas, clarify requirements, and propose designs before implementation. Use before any creative or planning work.

- **Type:** Skill
- **Install:** `agentstack add skill-omnigentx-jarvis-brainstorming`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [omnigentx](https://agentstack.voostack.com/s/omnigentx)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [omnigentx](https://github.com/omnigentx)
- **Source:** https://github.com/omnigentx/jarvis/tree/main/backend/.fast-agent/skills/brainstorming

## Install

```sh
agentstack add skill-omnigentx-jarvis-brainstorming
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Brainstorming Ideas Into Designs

Inspired by [obra/superpowers](https://github.com/obra/superpowers/tree/main/skills/brainstorming).

Turn rough ideas into fully-formed designs through structured exploration.

**Core rule:** Do NOT implement anything until the design is agreed upon.

## Process

### 1. Understand Context
- Review current project state (files, docs, existing code)
- Assess scope — is this one task or multiple sub-projects?
- If too large, decompose into smaller pieces first

### 2. Ask Clarifying Questions
- One question at a time
- Prefer multiple-choice when possible
- Focus on: purpose, constraints, success criteria

### 3. Explore Approaches
- Propose 2-3 different approaches with trade-offs
- Lead with your recommendation and explain why
- Be honest about complexity vs. simplicity

### 4. Present Design
- Architecture overview
- Components and their responsibilities
- Data flow
- Error handling strategy
- Testing approach

### 5. Get Agreement
- Present each section, confirm before moving on
- Be ready to revise based on feedback
- Document the final design

## Key Principles

- **YAGNI ruthlessly** — Remove features that aren't needed yet
- **Explore alternatives** — Always propose 2-3 approaches
- **Incremental validation** — Confirm each section
- **Design for isolation** — Each component should have one clear purpose
- **Smaller units** — Easier to understand, test, and modify

## In Multi-Agent Context

When brainstorming in a meeting:
- Use `speak()` to propose ideas and ask questions
- Wait for other agents' input before finalizing
- Summarize the agreed design before moving to implementation

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [omnigentx](https://github.com/omnigentx)
- **Source:** [omnigentx/jarvis](https://github.com/omnigentx/jarvis)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-omnigentx-jarvis-brainstorming
- Seller: https://agentstack.voostack.com/s/omnigentx
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.
