본문으로 건너뛰기
cccskills
무료GitHub에 공개

pui-regression

Reproduce and repair a bounded Proto UI regression whose expected behavior and owning layer are already governed. Use this before domain implementation skills whenever work starts from a reproducible failure, including bug fixes, drift repairs, broken exports, Runtime failures, Adapter parity defects, Prototype defects, or public-projection regressions. Do not use when expected semantics or ownership is unresolved.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(2)

  • SKILL.md2.4 KB
  • agents/openai.yaml243 B

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Repair a governed regression

For event ordering, input attribution, CSS ownership or a suspect fixture, read internal/agent-operations/testing-method.md before designing the red case. Separate injected facts from observations and retain meaningful assertions when correcting an older test.

  1. Require a minimal reproduction, pui-trace map, fixed expected behavior, affected surfaces, and explicit exclusions.
  2. Classify the owning layer before editing. Keep the regression transition primary even when the owning layer is an Adapter, Module, Host Capability, or Prototype; propose a domain leaf later only if a separately governed artifact must change.
  3. Add or identify evidence that fails for the governed reason before the fix.
  4. Repair the smallest owning layer. Preserve unrelated behavior and avoid opportunistic refactoring.
  5. Update T-* mapping only to the extent the executable evidence proves.
  6. Record another domain leaf in the handoff only when its governed artifact genuinely must change; do not load it here.
  7. Record the focused failure/pass evidence, affected integration checks, and broader validation boundary for a later pui-validate transition.

When the repair would change a normative criterion, owner, public API, compatibility promise, or lifecycle, continue only if current authority already fixes that transition; otherwise route the smallest product-direction decision. Do not edit the spec merely to make the implementation pass, hide a lower-layer defect in a Prototype or stylesheet, or treat screenshots as sole protocol evidence.

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 technical identifiers canonical.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Proto-UI/Proto-UI362026년 10월 18일 업데이트

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Proto-UI/Proto-UI362026년 10월 18일 업데이트

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Proto-UI/Proto-UI362026년 10월 18일 업데이트

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Proto-UI/Proto-UI362026년 10월 18일 업데이트

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Proto-UI/Proto-UI362026년 10월 18일 업데이트

pui-ci

무료

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.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Proto-UI/Proto-UI362026년 10월 18일 업데이트

Proto-UI의 스킬 모두 보기

이 스킬의 문제 신고