# Brainstorm

> >

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

## Install

```sh
agentstack add skill-cookys-autopilot-brainstorm
```

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

## About

# brainstorm — discover the design before any code exists

The discriminator vs neighbours: **do the options exist yet?**
- **No options yet / fuzzy need** → `brainstorm` (this skill) — explore, then converge on a design.
- **Options on the table, need to decide** → `think-tank` (multi-perspective) / `think-tank-dialectic`.
- **Need to know what others do** → `survey` (external research).
- **Approach already chosen** → author the plan (`references/plan-template.md`) → `dev-flow`.

This is a **gate**: do NOT invoke any implementation skill or write code until the user approves a design.

## Protocol

### 1. Explore the real need — Socratic, ONE question at a time
Don't propose solutions yet. Ask one focused question, wait for the answer, then ask the next. Surface the
*actual* problem, the constraints, the success picture, the no-go zones. Stop asking once you can restate
the need in one sentence the user confirms. (One-at-a-time matters: a wall of questions gets a thin
answer; a single sharp question gets a real one.)

### 2. Surface 2–3 genuinely different approaches
Not strawmen. Each approach: a one-line essence, its honest tradeoffs, what it's best/worst at. They must
differ in *kind* (different architecture / different mechanism), not just in parameter. If you can only
find one real approach, say so — that's a finding, not a failure.

### 3. Converge to a design spec
Once the user leans toward an approach, write a short **design spec**: the chosen approach, why it beat the
others (1 line each), the key decisions made, and the open questions that remain. Keep it tight — it's the
thing the plan will be built from, not the plan itself.

### 4. The approval gate
Present the design spec and ask for explicit approval. **Nothing downstream runs without it.** On approval,
hand off:
- to `references/plan-template.md` to **author the plan** (then `dev-flow` to execute), or
- directly to `dev-flow` if the work is small enough to skip a formal plan.
On "not yet" → keep exploring (back to step 1/2) — do not force forward.

## Boundaries
- **Discovers, doesn't decide-between-knowns** — the moment the options are already enumerated and the
  question is "which one", that's `think-tank`, not this.
- **Explores internally, doesn't research externally** — if the gap is "what do others do", chain to
  `survey` first, then bring its findings back here.
- **Designs, doesn't author the plan** — the structured plan doc is `references/plan-template.md`'s job;
  this skill produces the *design spec* that feeds it.
- Fits `research-to-ship` as an optional Phase-0 (discover the design before its Phase-1 research/plan),
  for topics that start fuzzy rather than from a clear question.

## Source & license

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

- **Author:** [cookys](https://github.com/cookys)
- **Source:** [cookys/autopilot](https://github.com/cookys/autopilot)
- **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-cookys-autopilot-brainstorm
- Seller: https://agentstack.voostack.com/s/cookys
- 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%.