Skip to content
Back to skills

Brainstorming

ASecurity

Use when material scope or behavior decisions need exploration, or the user requests brainstorming. Handle a single routine ambiguity directly.

  • 2 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added October 15, 2026
documentation

Security analysis

A100/100

Pro scans all 6 files and shows the line behind each finding

Scanned October 15, 2026

npx -y skills add MVPavan/via --skill brainstorming --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Brainstorming?

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

Security grade badge for Brainstorming
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/mvpavan-brainstorming/badge)](https://www.skillsdirectory.com/skills/mvpavan-brainstorming)

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: brainstorming
description: Use when material scope or behavior decisions need exploration, or the user requests brainstorming. Handle a single routine ambiguity directly.
---

# Brainstorming

Resolve material scope or behavior decisions before committing to an approach.

## Route before grounding

- Clear, bounded behavior: return to the task; no interview or spec is required.
- One routine missing detail: infer from relevant code or ask one focused
  question, then continue independent work.
- Several live directions: use `references/exploration.md` when structured
  divergence would help.
- Requested interview: use the grilling skill. A written critique is a review,
  not automatic permission to interview or edit documents.
- Decisions already settled: synthesize them without reopening the discussion.

Read only the relevant existing code, authoritative docs and constraints needed
to distinguish the live choices. Name the closest existing solution before
proposing a new one.

## Resolve

Establish outcome, intended user, success criteria, constraints and exclusions.
Present materially different options with tradeoffs when alternatives remain.
Ask about consequential unresolved choices; group independent questions when
that is easier to answer. Carry prior decisions and authorization forward.
For interview technique or an explanation that benefits from a picture, consult
`references/interviewing.md` or `references/visuals.md`, respectively.

Stop exploring when a direction and its acceptance criteria are sufficient for
the next authorized step. Do not invent more questions or variants to fill a quota.

## Record and hand off

An in-chat decision is enough for bounded work unless a durable artifact was
requested. For a spec that planning or another session will consume, use
`references/spec-template.md`; default path is `docs/specs/YYYY-MM-DD-<topic>.md`.
Record sources, assumptions and excluded alternatives as needed for handoff.

A new unresolved spec is `Status: draft`. Mark it `Status: approved` only when
actual authorization covers its direction and scope, recording that evidence.
A blocking question must be resolved or explicitly excluded before approval.
Review consistency, scope and verifiability; independent critique is conditional
on material risk and the shared delegation policy.

This skill's output is decisions or a spec. Continue into planning/execution when
already authorized; a brainstorming-only request does not authorize code changes.

Files in this skill

  • SKILL.md2.4 KB
  • agents/openai.yaml42 B
  • references/exploration.md914 B
  • references/interviewing.md1 KB
  • references/spec-template.md4.3 KB
  • references/visuals.md1.8 KB

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.