# Brainstorm And Refine

> >-

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

## Install

```sh
agentstack add skill-tony-ai-workflow-plugins-brainstorm-and-refine
```

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

## About

# Weave Brainstorm & Refine

The full pipeline: generate independent originals from each model, then iteratively refine them through judge-weave-incorporate cycles.

## When to Use

- You want the best of both worlds: creative divergence then convergent refinement
- You want to explore a problem space broadly, then hone in on the best solution
- You need a high-quality result and are willing to spend tokens on multiple passes

## Key Features

- Phase 1 (Brainstorm): Independent originals from each model, optional `--variants=N`
- Transition gate: You choose which originals enter refinement
- Phase 2 (Refine): Iterative judge-weave-distribute cycle over `--passes=N`
- Full rationale chain from brainstorm through every refinement pass
- `--judge=host|round-robin`: Host judges every pass, or rotate judging across models

## The Pipeline

1. **Brainstorm**: Each model generates independent original responses
2. **Review**: All originals presented — you pick which ones to refine
3. **Refine**: Judge picks the best, weaves in strengths from runners-up, redistributes to all models
4. **Repeat**: Each pass improves the woven result until convergence or passes exhausted

## How to Invoke

Run the `/weave:brainstorm-and-refine` command with your prompt. The command handles both phases, the transition gate, and artifact persistence.

## Source & license

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

- **Author:** [tony](https://github.com/tony)
- **Source:** [tony/ai-workflow-plugins](https://github.com/tony/ai-workflow-plugins)
- **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-tony-ai-workflow-plugins-brainstorm-and-refine
- Seller: https://agentstack.voostack.com/s/tony
- 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%.