Skip to content
Back to skills

Pui Maintenance Review

ASecurity

Independently review one Proto UI autonomous-maintenance remediation in a fresh read-only context. Use after pui-remediate produces a packet and actual diff. Classify technical-completion eligibility without making product or integration decisions.

  • 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-maintenance-review --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Pui Maintenance Review?

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

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

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-maintenance-review
description: Independently review one Proto UI autonomous-maintenance remediation in a fresh read-only context. Use after pui-remediate produces a packet and actual diff. Classify technical-completion eligibility without making product or integration decisions.
---

# Review maintenance remediation

1. Require a fresh context, raw finding, baseline, remediation packet, actual diff, and validation logs.
2. Read `AGENTS.md`, the autonomous-maintenance procedure, and Review Synthesizer prompt completely.
3. Reconstruct scope and authority independently.
4. Check packet fidelity, consumer coverage, exclusions, evidence truthfulness, generated projections, and residual risks.
5. Remain read-only. Attempt to falsify completion.
6. Return `adequate`, `incomplete`, or `misleading` with exact evidence.

Return technical gaps to `pui-remediate`. Route an adequate governed repair to `pui-maintenance-close`; return only a genuinely unresolved product or compatibility direction to a maintainer. Keep this context non-mutating so the verdict remains independent.

## 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 evidence references exact.

Files in this skill

  • SKILL.md1.5 KB
  • agents/openai.yaml265 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.