Skip to content
Back to skills

Pui Adapter Assess

ASecurity

Assess one bounded Proto UI Adapter question without changing repository or external state. Use for new-Adapter research, target compatibility, catalog readiness, reviewed Module support or omission evidence, Host Capability fidelity, lifecycle translation, dependency risk, or implementation readiness. Do not catalog, implement, repair, or approve the Adapter slice.

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

Works with

  • 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-adapter-assess --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Pui Adapter Assess?

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

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

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-adapter-assess
description: Assess one bounded Proto UI Adapter question without changing repository or external state. Use for new-Adapter research, target compatibility, catalog readiness, reviewed Module support or omission evidence, Host Capability fidelity, lifecycle translation, dependency risk, or implementation readiness. Do not catalog, implement, repair, or approve the Adapter slice.
---

# Assess one Adapter question

1. Require current `pui-orient` and `pui-trace` artifacts for the bounded question.
2. Read the Adapter decision, cataloging guide, target profile when present, related Module and Host Capability entities, tests, current translation code, issue boundary, and exact exclusions.
3. Classify the question as new-Adapter research, catalog readiness, compatibility assessment, support or omission evidence, capability-fidelity assessment, or implementation readiness. Do not move between classes silently.
4. Inspect real translation behavior and executable evidence. Distinguish observed support, explicit omission, uncataloged scope, implementation attachment, and faithful realization.
5. Identify target and runtime range, lifecycle ownership, failure behavior, dependency implications, portable-semantic gaps, incompatible host behavior, and evidence still needed.
6. Return a read-only assessment packet containing facts, unknowns, recommendation, exclusions, residual risks, and one eligible next registered leaf. Use the schema's gate field only for an unresolved Adapter identity/semantics/compatibility choice or a privileged operation; otherwise route governed parity, evidence, and implementation work forward immediately. Do not load that next leaf.

Remain read-only. Do not create a support matrix from packages or dependencies, infer conformance from source attachment, edit catalog entities, or authorize 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 target, entity, and API identifiers canonical.

Files in this skill

  • SKILL.md2.3 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.