Skip to content
cccskills
FreePublished on GitHub

pui-verify

Independently attempt to falsify one Proto UI autonomous-maintenance finding in a fresh non-mutating context. Use after pui-observe produced a candidate finding and route the result directly to remediation or closure when authority is clear.

The English summary is being prepared. Showing the original description.

Proto-UI/Proto-UI
See how to install

Files included (2)

  • SKILL.md2.1 KB
  • agents/openai.yaml244 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

Verify one finding

  1. Require a fresh context and the raw Observer artifacts, baseline, and candidate finding.
  2. Read AGENTS.md, the autonomous-maintenance procedure, Verifier prompt, mission, and governing sources completely.
  3. Reconstruct the evidence independently. Do not inherit the Observer's desired classification.
  4. Attempt falsification, identify the owning layer, correct scope, and distinguish authority drift from implementation or projection drift.
  5. Keep verification non-mutating so its classification remains independent.
  6. Return the protocol classification, corrected finding, evidence limits, residual uncertainty, and the next automatic route.

Route a rejected finding to pui-record. Route a confirmed implementation, test, or projection drift whose expected result is already governed to pui-remediate. Produce one concentrated unresolved-product-direction packet only when available authority leaves materially different semantic or compatibility outcomes open.

The registry always requires verification-report and maintenance-outcome. It additionally requires decision-packet when the handoff declares unresolved-product-direction; it does not require a fabricated decision for a governed remediation. The remediation route still requires its separate semantic and mutation authorization artifacts, and an autonomous handoff with an unresolved decision remains terminal.

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.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

pui-adapter

Free

Implement one governed Proto UI Adapter-profile realization slice. Use when target and runtime range, supported or omitted Module role, Host Capability fidelity, lifecycle translation, failure behavior, compatibility boundary, and evidence scope are fixed by current authority. Use pui-adapter-assess for research or readiness assessment and pui-regression first for a governed failing behavior.

The English summary is being prepared. Showing the original description.

Proto-UI/Proto-UI36Updated Oct 18, 2026

pui-adapter-assess

Free

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.

The English summary is being prepared. Showing the original description.

Proto-UI/Proto-UI36Updated Oct 18, 2026

pui-agent-identify

Free

Measure the active Agent model with pinned offline ModelTrace sampling and return an unsigned closed-set attribution record. Use before Agent-originated commits, Issue/PR creation or material updates, comments, reviews, and current collaboration writes in either execution mode. Do not treat a fingerprint, declared model label, or record reference as authenticated identity, permission, independent review, or acceptance.

The English summary is being prepared. Showing the original description.

Proto-UI/Proto-UI36Updated Oct 18, 2026

pui-assess

Free

Run Proto UI's dynamic comprehension assessment and derive an unsigned local task-fit result. Use when an Agent needs review calibration or a fresh autonomous task and review ceiling. Do not use a self-result as identity, permission, or acceptance evidence.

The English summary is being prepared. Showing the original description.

Proto-UI/Proto-UI36Updated Oct 18, 2026

pui-brainstorm

Free

Investigate a bounded Proto UI Contract, Prototype, Module, Host Capability, Adapter, schema, or ownership question and turn a genuinely unresolved direction into one semantic decision packet. Use for spec brainstorming, admission questions, competing semantic models, uncataloged behavior, or unresolved cross-layer boundaries.

The English summary is being prepared. Showing the original description.

Proto-UI/Proto-UI36Updated Oct 18, 2026

pui-ci

Free

Diagnose one bounded Proto UI Actions or CI failure from an exact workflow run and revision, then route the exact repair, validation, or recheck transition. Use to locate the owning failure and distinguish infrastructure from change failures. This leaf remains read-only.

The English summary is being prepared. Showing the original description.

Proto-UI/Proto-UI36Updated Oct 18, 2026

See all skills by Proto-UI

Report a problem with this skill