Skip to content
Back to skills

Pui Trace

ASecurity

Trace a Proto UI change through authoritative spec lifecycle, legacy explanation, dated context, implementation, executable evidence, package surfaces, and public projections. Use before deciding scope, changing behavior, reviewing a pull request, or investigating drift.

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

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-trace --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Pui Trace?

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

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

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-trace
description: Trace a Proto UI change through authoritative spec lifecycle, legacy explanation, dated context, implementation, executable evidence, package surfaces, and public projections. Use before deciding scope, changing behavior, reviewing a pull request, or investigating drift.
---

# Trace authority and evidence

Produce an authority map without changing behavior.

1. Read `AGENTS.md` and `spec/README.md` completely.
2. Search existing entity IDs, aliases, criteria, anchors, relations, revisions, sources, and lifecycle.
3. Follow the coherent chain from knowledge or decision through semantic owner, host boundary, Adapter profile, tests, implementation, exports, and documentation where applicable.
4. Use `internal/contracts/**` only for explanation or an uncataloged gap. Use dated records as context, never as project authority.
5. Distinguish governed fact, implementation evidence, public projection, observation, proposal, and unknown.
6. Treat implementation disagreement as drift to investigate, not an implicit spec amendment.
7. Record negative boundaries, direct and indirect consumers, generated projections, validation commands, and unresolved conflicts.

Return paths and entity anchors precise enough for another skill to act without repeating discovery. Stop at a contradiction that requires semantic choice.

## 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 repository identifiers canonical.

Files in this skill

  • SKILL.md1.8 KB
  • agents/openai.yaml243 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.