Skip to content
Back to skills

Pui Brainstorm

ASecurity

Investigate a bounded Proto UI Contract, Prototype, Module, Host Capability, Adapter, schema, or ownership question and turn a genuinely unresolved direction into one semantic decision packet. Use for spec brainstorming, admission questions, competing semantic models, uncataloged behavior, or unresolved cross-layer boundaries.

  • 36 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added October 4, 2026
designgo

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned October 4, 2026

npx -y skills add Proto-UI/Proto-UI --skill pui-brainstorm --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Pui Brainstorm?

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

Security grade badge for Pui Brainstorm
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/proto-ui-pui-brainstorm/badge)](https://www.skillsdirectory.com/skills/proto-ui-pui-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: pui-brainstorm
description: Investigate a bounded Proto UI Contract, Prototype, Module, Host Capability, Adapter, schema, or ownership question and turn a genuinely unresolved direction into one semantic decision packet. Use for spec brainstorming, admission questions, competing semantic models, uncataloged behavior, or unresolved cross-layer boundaries.
---

# Shape a semantic decision

1. Require a bounded question and a `pui-trace` authority map.
2. Separate observed facts from hypotheses and desired behavior.
3. Trace the information path from input fact through semantic owner to observable output and synchronization boundary.
4. Identify candidate owners, portable invariants, host responsibilities, negative boundaries, compatibility effects, alternatives, and evidence needed to falsify each claim.
5. State what remains uncataloged and what existing lifecycle permits.
6. Produce one concentrated decision packet: unresolved question, evidence, competing choices, recommendation, exclusions, residual risks, proposed entity and test graph, and the exact decision that unlocks automatic continuation.

Do not create a normative entity, approve admission, select ownership, widen a public guarantee, or start implementation. Preserve the packet in a dated record only when the user has authorized that repository change.

## Explicit handoff

Do not load or execute another skill. Return exactly one handoff conforming to `internal/agent-operations/schemas/skill-handoff.schema.json`. Carry required prior artifacts by reference, include every artifact this leaf produces according to `skills.yaml`, and set `nextSkillId` to one eligible registered leaf or `null`.

Communicate with the user in the user's current language. Author governed repository artifacts in their required language and keep technical identifiers canonical.

Files in this skill

  • SKILL.md1.8 KB
  • agents/openai.yaml266 B

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.