# Brainstorm

> Resolve unclear feature behavior or approach and produce an approved spec. Use for genuine uncertainty; not small or precise changes.

- **Type:** Skill
- **Install:** `agentstack add skill-bnet47-codexicon-brainstorm`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [bnet47](https://agentstack.voostack.com/s/bnet47)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [bnet47](https://github.com/bnet47)
- **Source:** https://github.com/bnet47/codexicon/tree/main/.agents/skills/brainstorm
- **Website:** https://bnet47.github.io/codexicon/repo-template-playbook.html

## Install

```sh
agentstack add skill-bnet47-codexicon-brainstorm
```

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

## About

# Brainstorm

Announce: "I'm using brainstorm to resolve the feature choices before implementation."

## 1. Load relevant project context

Read the project identity and only the architecture, conventions, decisions, or prior specs relevant to the feature. If the repository is still an unconfigured template, route to `$discover`.

## 2. Resolve the problem

Ask one targeted question at a time and stop when you can state:

- the problem and affected person;
- verifiable success;
- constraints and non-goals;
- the smallest shippable slice;
- unresolved risks.

## 3. Compare approaches

Present two or three genuinely viable approaches with tradeoffs in behavior, complexity, reversibility, and verification. Recommend one and explain why. Ask for a choice only when the alternatives materially change the product or cost; otherwise proceed with the recommended reversible option and state the assumption.

## 4. Write the spec

After the direction is accepted, save `agent_docs/briefs/[YYYY-MM-DD]-[feature-slug].md` without overwriting an existing file:

```markdown
# Spec: [Feature]

**Date:** [YYYY-MM-DD]
**Status:** Approved

## Problem
[Who is affected and what fails today.]

## Chosen solution
[User-visible behavior and the selected approach.]

## Acceptance criteria
- [ ] [Specific observable result.]

## Non-goals
- [Explicit exclusion.]

## Constraints and risks
- [Constraint, risk, or dependency.]

## First shippable slice
[Smallest complete proof of value.]

## Open questions
- [Unresolved question, or "None".]
```

Self-check that every criterion is testable, no placeholder remains, and the first slice is complete rather than merely scaffolding.

Offer `$write-plan` when implementation is multi-step. Do not implement, commit, or push during brainstorming unless the user explicitly expands the request.

## Source & license

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

- **Author:** [bnet47](https://github.com/bnet47)
- **Source:** [bnet47/codexicon](https://github.com/bnet47/codexicon)
- **License:** MIT
- **Homepage:** https://bnet47.github.io/codexicon/repo-template-playbook.html

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-bnet47-codexicon-brainstorm
- Seller: https://agentstack.voostack.com/s/bnet47
- 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%.