Skip to content
Back to skills

Pui Prototype

ASecurity

Maintain an existing Proto UI Prototype or implement a governed Base or design-language component slice. Use for governed component behavior, anatomy, inheritance, exports, CLI registration, style projection, demos, or public preview work. Do not use to admit a new semantic subject or invent Base ownership from a component name.

  • 36 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added October 4, 2026
designgoapidocumentation

Works with

  • cli
  • api

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-prototype --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Pui Prototype?

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

Security grade badge for Pui Prototype
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/proto-ui-pui-prototype/badge)](https://www.skillsdirectory.com/skills/proto-ui-pui-prototype)

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-prototype
description: Maintain an existing Proto UI Prototype or implement a governed Base or design-language component slice. Use for governed component behavior, anatomy, inheritance, exports, CLI registration, style projection, demos, or public preview work. Do not use to admit a new semantic subject or invent Base ownership from a component name.
---

# Work on a Prototype or component slice

1. Require `pui-orient`, `pui-trace`, and implementation authorization from the current bounded request, governed work item, or active standing scope.
2. Classify the work as maintenance, governed Base implementation, or governed design-language projection.
3. For maintenance, preserve existing criteria and add failing-before evidence at the owning layer.
4. For Base work, require current authority to fix the independent subject, information ownership, negative boundary, public surface, test graph, and host prerequisites.
5. For design-language work, inherit Base semantics and own only the governed presentation, compatibility, anatomy, or style delta.
6. Keep source, types, exports, CLI surfaces, spec graph, tests, and reachable public package previews coherent.
7. Use the Prototype's public anatomy and behavior in demos. Do not simulate missing protocol in page code.
8. Record evidence, documentation, and validation as separate eligible handoffs. Do not load them inside this transition.

Route only criteria, ownership, public API, classification, compatibility, or dependency choices not decided by current authority to an attended product-direction decision. Keep raw host escapes and negative patches out of the implementation.

## 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. Keep public API names canonical.

Files in this skill

  • SKILL.md2 KB
  • agents/openai.yaml255 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.