Skip to content
Back to skills

Brainstorm

ASecurity

Use when a person wants to think an idea through and keep the discussion: a feature, a tool choice, an architecture question, before a plan or without one, with the agent through an interview. Produces a board in aiview holding the decisions, the diagrams and what was investigated. Not for a swarm of seats working it (brainswarm), not for an implementation plan and not for bug fixes.

  • 14 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added October 25, 2026
ai-agents

Security analysis

A100/100

Scanned October 25, 2026

npx -y skills add Ovich/swarmstorm --skill brainstorm --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Brainstorm?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Brainstorm
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ovich-brainstorm/badge)](https://www.skillsdirectory.com/skills/ovich-brainstorm)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: brainstorm
description: "Use when a person wants to think an idea through and keep the discussion: a feature, a tool choice, an architecture question, before a plan or without one, with the agent through an interview. Produces a board in aiview holding the decisions, the diagrams and what was investigated. Not for a swarm of seats working it (brainswarm), not for an implementation plan and not for bug fixes."
---

# Brainstorm

**The discussion lives in one Markdown file from the first question, never in chat.**
`YYYY-MM-DD-<topic>.brainstorm.md`, through the `aiview` skill: kind `brainstorm`, tags = topic, group = the topic. With a
roadmap, the slot's slug is a tag. A resuming
session reads the board before asking anything again.

**Run the `interview` skill** and write each
answer into the board as it lands.

**The person asks for a swarm of seats to brainstorm or debate it**: the `brainswarm` skill
runs it on this board.

The board, in this order:

- **Human part**, written as the `aiview` skill's `references/human-part.md` says, refreshed at each settled decision.
- **Strategy**, a brainswarm only.
- **Decisions table**: the row core of the `interview` skill's `references/decisions.md`, plus `Log` (the entry `Q7`). The interview's `experiments` option is its first row.
- **Context being built on.**
- **Diagrams**, through the `write-diagrams` skill, drawn during the questions.
- **What ran**: the recipes the experiments hand back.
- **Interview log**, or a brainswarm's log, last: per question, verbatim, the options and the recommendation, then the answer as given.

**No code in the repository for the thing being discussed.**

**Close** by saying what is agreed and what is open.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.