Skip to content
Back to skills

Pui Spec

ASecurity

Create or revise a governed Proto UI spec entity after identity, ownership, lifecycle intent, semantic scope, relations, and evidence plan are fixed by current authority. Use for Contract, Prototype, Module, Adapter profile, Decision, Host Capability, Test, Version, or Knowledge entity work. Do not use to decide an unresolved admission or lifecycle promotion.

  • 36 stars
  • 0 votes
  • 0 copies
  • 1 view
  • 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-spec --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Pui Spec?

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

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

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-spec
description: Create or revise a governed Proto UI spec entity after identity, ownership, lifecycle intent, semantic scope, relations, and evidence plan are fixed by current authority. Use for Contract, Prototype, Module, Adapter profile, Decision, Host Capability, Test, Version, or Knowledge entity work. Do not use to decide an unresolved admission or lifecycle promotion.
---

# Author a governed spec change

1. Read `AGENTS.md`, `spec/README.md`, the schema, relevant engine validation, and the complete governing decision or accepted-direction record.
2. Require a `pui-trace` map and current-user or standing authorization for the fixed identity, owner, lifecycle intent, semantic boundary, compatibility, and evidence scope.
3. Search existing IDs and relations again before creating anything.
4. Model one coherent semantic slice. Write addressable criteria, precise directional relations, version bounds, sources, open questions, and revisions where semantics changed. Record `lifecycleRationale` for new ordinary entities or lifecycle changes, classify canonical `openQuestions[].blocks` targets, and validate the changed authoring scope with `pnpm check:spec-authoring -- --base <base-sha>` as defined in `spec/README.md`.
5. Add or update `T-*` evidence and real executable implementation paths for normative behavior.
6. Change generated projections through their generators.
7. Record spec graph, catalog, projection, focused evidence, and proportional type checks for a later `pui-validate` transition.

Route an actually undecided schema design, ownership, public surface, compatibility, lifecycle promotion, or evidence meaning to the smallest product-direction decision. Do not create inventory placeholders or infer a matrix from files, dependencies, packages, or names.

## 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. Preserve canonical identifiers and governed localization.

Files in this skill

  • SKILL.md2.2 KB
  • agents/openai.yaml224 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.