Skip to content
Back to skills

Brainstorm

ASecurity

Explore and validate feature design before writing specs. Uses Socratic questioning to refine the idea, compares 2-3 approaches with trade-offs, and produces a design summary approved by the user before handing off to /spec.

  • 3 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added May 27, 2026
data-ai

Security analysis

A100/100

Scanned May 27, 2026

npx -y skills add ByeongminLee/nextjs-claude-code --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/byeongminlee-brainstorm/badge)](https://www.skillsdirectory.com/skills/byeongminlee-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: "Explore and validate feature design before writing specs. Uses Socratic questioning to refine the idea, compares 2-3 approaches with trade-offs, and produces a design summary approved by the user before handing off to /spec."
argument-hint: "[feature description]"
context: fork
---

## Model selection

Brainstorming always requires reasoning and design judgment → spawn `brainstormer` with `model: sonnet`.

## Task

Spawn `brainstormer` agent (sonnet) with the following prompt:

```
[HANDOFF]
TO: brainstormer (sonnet)
TASK: Brainstorm feature design based on the following description
DONE-WHEN:
  - User has approved the final design summary
  - A concise spec-ready summary has been presented
MUST-NOT:
  - Write or modify any source code
  - Write spec.md or design.md (that is /spec's job)
  - Proceed past any phase without user approval
READS:
  - spec/ARCHITECTURE.md
  - spec/PROJECT.md
  - spec/feature/ (scan existing features)
[/HANDOFF]

$ARGUMENTS
```

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.

Comments

Loading comments…

Newsletter

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