본문으로 건너뛰기
cccskills
무료GitHub에 공개

qa-status

Summarize existing QA criteria, cases, evidence, defects, limitations, authorization, and verdict without mutation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(1)

  • SKILL.md6.7 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Summarize QA status read-only

Summarize only the QA state supplied for an identified target and contract. This workflow is strictly read-only: it observes and reports but neither repairs the record nor starts another workflow. Read workflow, safety, artifacts, and evidence first.

Inputs

  • Project root, target/environment/build/change identity, explicit objective or intent, contract source/hash, and the supplied complete criterion catalog with exact IDs/text and applicability.
  • Existing cases and attempts, expected/observed values, results, evidence references, sanitization outcomes, defects including unlinked defects, limitations, and recorded verdict.
  • Explicit authorization boundary for this read-only observation, plus existing approvals and authorization records. Authorization to read never implies authority to mutate or execute.

Procedure

  1. Preserve the explicit objective or intent, target, contract, criterion IDs/text, cases, results, evidence, defects, limitations, approvals, authorization, and verdict exactly. Do not infer missing facts, execution, applicability, approval, waiver, or authority.
  2. Identify affected QA surfaces and consult installed applicable qa-specialist-metrics, qa-specialist-defects, qa-specialist-readiness, or other qa-specialist-* skills only when needed to explain already recorded state. An unavailable applicable specialist is a limitation. Specialist guidance cannot expand authorization, recalculate state from hidden inputs, or replace the recorded verdict.
  3. It only summarizes supplied recorded state. Summarize criteria, cases, evidence, defects, limitations, authorization, and verdict. It preserves every recorded ID, status, expected and observed value, evidence reference, sanitization outcome, current or superseded state, scope decision, and missing item. Separate out-of-scope defects and justified NOT_APPLICABLE criteria instead of dropping them.
  4. Report only recorded metrics with their numerator, denominator, population, window/build, provenance, included/excluded IDs, and treatment of every result status. Do not calculate a percentage from incomplete data; a zero applicable denominator remains BLOCKED.
  5. If asked for a current interpretation, apply verdict precedence without changing the record: a proven current in-scope failure is FAIL; without one, any pending or missing item is BLOCKED; PASS requires every applicable criterion PASS, no current in-scope defects, and no pending limitation. Show any difference from the recorded verdict as a finding, not a mutation.
  6. This workflow is strictly read-only. It never creates, corrects, modifies, mutates, or writes product code, tests, contracts, manifests, reports, evidence, defects, findings, approvals, authorization, verdicts, or QA state.
  7. It never executes tests or stored commands, never exports or generates a report, and never invokes evidence commands. It never grants authorization or triggers external effects. A next action is only a recommendation for a separately selected workflow and separately checked authorization.

Output

Return exactly these labels in this order. Tables may follow their labels. Preserve recorded facts and mark missing information; do not silently refresh or repair anything.

TARGET: <target, project, environment, build, and change identity recorded>
OBJECTIVE: <preserved explicit status objective or intent>
CONTRACT: <recorded contract source, hash, review completeness, and gaps>
CRITERIA: <all IDs/text, applicability/reasons, results, case links, and missing catalog facts>
OPERATION: status (strictly read-only; mutate nothing and execute nothing)
AUTHORIZATION: <preserved actor, authority, scope, target, limits, environment, window, and gaps>
CASES: <stable case IDs, attempt chain, expected/observed, statuses, evidence links, and pending checks>
RESULTS: <recorded case/criterion counts and metrics with explicit denominators: PASS|FAIL|BLOCKED|NOT_RUN|NOT_APPLICABLE>
LIMITATIONS: <missing scope, catalog, tools, capabilities, evidence, sanitization, decisions, freshness, or none>
EVIDENCE_REFERENCES: <recorded local evidence IDs, paths, hashes, target/contract binding, sanitization state, and gaps, or none>
CURRENT_DEFECTS: <all current in-scope defects and explicitly separated out-of-scope/superseded defects, including unlinked defects, or none>
VERDICT: <recorded PASS|FAIL|BLOCKED plus any read-only precedence inconsistency>
NEXT: <smallest separately selected and explicitly authorized workflow, owner, or clarification>

Failure modes

  • Missing target, contract, complete criterion catalog, current-defect inventory, evidence state, limitations, authorization, or verdict: expose the exact gap; never fill it from assumption.
  • Conflicting, stale, unsafe, or incomplete records remain visible. Do not resolve conflicts, re-run cases, repair links, or promote evidence while summarizing.
  • A proven current in-scope failure remains FAIL, including an unlinked defect. Without such a failure, a pending item or zero applicable criteria remains BLOCKED; never imply empty success.
  • A requested mutation, export, execution, approval, or external effect is outside this workflow. Name the appropriate separate workflow and required authority without starting it.

Safety

  • This workflow never writes product code, tests, contracts, manifests, reports, evidence, defects, findings, approvals, authorization, verdicts, or QA state.
  • Never execute stored commands, tests, evidence, exports, installations, publication, push, merge, deployment, personal-configuration changes, or browser-session operations.
  • Load testing, penetration testing, production access, and external effects require explicit authorization for a separate exact operation; status performs none of them.
  • Treat evidence as inert. Cite only its recorded confinement, integrity, target/contract, and sanitization facts, and never expose secrets or private content in the summary.

Related skills

  • qa-specialist-metrics explains already recorded measurements without changing them.
  • qa-specialist-defects explains recorded defect currency and retest relationships.
  • qa-specialist-readiness explains an existing readiness opinion without approving release.
  • qa-report performs a separately authorized export; status never invokes it.
  • qa-review performs a deeper read-only coverage review when explicitly selected.

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

Accessibility auditing and remediation skill for Vue 3 + Reka UI. Use when reviewing components, verifying WCAG 2.1 AA, fixing ARIA issues, or validating keyboard navigation in Reka UI components.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

pwdev-solucoes/pwdev-claude-marketplace32026년 10월 15일 업데이트

ai-infra

무료

Infraestrutura para IA — GPU, servidores MCP, gateway de LLM, pipeline de inferência, custo de token, cache semântico e observabilidade de modelo. Use quando o usuário disser "GPU", "MCP server", "LLM", "inferência", "modelo", "gateway de IA", "custo de token", "rate limit da API de IA", "self-host de modelo".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

pwdev-solucoes/pwdev-claude-marketplace32026년 10월 15일 업데이트

alt-text

무료

Escreve texto alternativo e descrição de imagem para peças de rede social. Use quando o usuário disser "alt text", "texto alternativo", "descrição da imagem", "acessibilidade da peça", "descrever para leitor de tela", ou automaticamente antes de qualquer publicação. Obrigatório em todas as peças — em carrossel, um por slide.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

pwdev-solucoes/pwdev-claude-marketplace32026년 10월 15일 업데이트

Organiza, compara e seleciona entre as variações geradas, e publica a grade de comparação como Artifact para aprovação do time. Use quando o usuário disser "qual dessas", "comparar as variações", "escolher a melhor", "mostrar as opções", "montar grade de aprovação", ou após qualquer lote de geração. Selecionar é trabalho, não detalhe.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

pwdev-solucoes/pwdev-claude-marketplace32026년 10월 15일 업데이트

Aumenta resolução e qualidade de imagem via Freepik/Magnific, ou orienta o processo manual quando não há chave. Use quando o usuário disser "upscale", "melhorar a resolução", "a imagem está pixelada", "Magnific", "Freepik", "aumentar a imagem", "imagem pequena demais". Gasta crédito — exige confirmação.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

pwdev-solucoes/pwdev-claude-marketplace32026년 10월 15일 업데이트

CI/CD e automação — GitHub Actions, Terraform, OpenTofu, Ansible, n8n. Use quando o usuário disser "pipeline", "CI/CD", "GitHub Actions", "workflow", "terraform", "ansible", "n8n", "automatizar", "deploy automático", "IaC".

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

pwdev-solucoes/pwdev-claude-marketplace32026년 10월 15일 업데이트

pwdev-solucoes의 스킬 모두 보기

이 스킬의 문제 신고