본문으로 건너뛰기
cccskills
무료GitHub에 공개

qa-specialist-metrics

Define auditable QA metrics with explicit numerators, denominators, populations, windows, and treatment of every result state.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(1)

  • SKILL.md11.9 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

QA metrics specialist

Use this specialist when a QA workflow needs measurements that remain traceable to an identified target and contract. This specialist does not execute a workflow, tests, reports, or stored commands and cannot grant authorization. Read workflow, safety, and artifacts before advising the calling workflow.

Inputs

  • Target, contract, complete criterion and case catalogs, preserved IDs/text, and applicable authorization.
  • Normalized case and criterion results using only PASS, FAIL, BLOCKED, NOT_RUN, and NOT_APPLICABLE, with stated reasons for non-applicability.
  • The question each metric answers, its population, observation window or build snapshot, and the records eligible for numerator and denominator.
  • Current defects, evidence references, limitations, collection provenance, and known gaps.

Procedure

  1. Preserve the target, contract, catalogs, results, and authorization supplied by the caller. Do not infer a complete population from a partial result set.
  2. Define each metric before calculating it: name the question, numerator, denominator, population, observation window or immutable build snapshot, unit, and treatment of every result state. Never publish a bare percentage.
  3. Count PASS in a pass-rate numerator. Count every applicable PASS, FAIL, BLOCKED, and NOT_RUN item in that rate's denominator. Exclude NOT_APPLICABLE only with its recorded reason. A different metric may use different counts only when it states that definition.
  4. If the denominator is zero, return BLOCKED with the zero count and population; do not divide, emit 100%, or imply PASS. Missing or incomplete population, window, or state treatment is also BLOCKED.
  5. Requirements coverage is not source-line coverage. Test counts, line coverage, defect counts, and pass rates answer different questions and must not substitute for one another.
  6. Link included and excluded records to their IDs and evidence provenance. Expose stale data, sampling bias, unresolved defects, and other limitations beside the metric.
  7. Return the metric and its limitations to the calling workflow. A metric is an observation, not a global verdict, risk acceptance, or release approval.

Output

For every metric return:

  • target, contract, metric name, question, unit, numerator, denominator, computed value or BLOCKED, population, observation window/build snapshot, and collection provenance;
  • explicit inclusion/exclusion rules and treatment of PASS, FAIL, BLOCKED, NOT_RUN, and NOT_APPLICABLE;
  • included record IDs, excluded record IDs with reasons, evidence references, limitations, assumptions, and freshness;
  • related current defects, interpretation boundaries, and the next valid action.

Reference scenarios

scenariometrictargetcontractsource_collectionfreshness_buildnumeratordenominatorpopulationwindowcriterion_idsnumerator_idsremainder_status_reasonna_items_reasonevidence_refsstate_treatmentresult
explicit-rateapplicable criterion pass ratecheckout-api build rc-17QA-CONTRACT-17 sha256:abc123normalized manifest run-17 collected by qa-reportfresh for build rc-178 PASS10 applicable criteriacomplete release-candidate criterion catalogbuild rc-17 at 2026-09-12T18:00ZAC-01 AC-02 AC-03 AC-04 AC-05 AC-06 AC-07 AC-08 AC-09 AC-10AC-01 AC-02 AC-03 AC-04 AC-05 AC-06 AC-07 AC-08AC-09=FAIL expected total mismatch; AC-10=BLOCKED evidence pendingnoneEV-01 EV-02 EV-03 EV-04 EV-05 EV-06 EV-07 EV-08 EV-09 EV-10PASS numerator; FAIL BLOCKED NOT_RUN denominator only; NOT_APPLICABLE excluded80%
zero-applicableapplicable criterion pass ratecheckout-api build rc-18QA-CONTRACT-18 sha256:def456normalized manifest run-18 collected by qa-reportfresh for build rc-180 PASS0 applicable criteriacomplete catalog with all criteria NOT_APPLICABLEbuild rc-18 at 2026-09-12T19:00ZAC-NA-01nonenoneAC-NA-01=NOT_APPLICABLE reason legacy path absentEV-NA-01PASS numerator; FAIL BLOCKED NOT_RUN denominator only; NOT_APPLICABLE excluded with reasons; empty denominator has no rateBLOCKED
missing-metric-targetapplicable criterion pass ratemissingQA-CONTRACT-17 sha256:abc123normalized manifest run-17 collected by qa-reportfresh for build rc-178 PASS10 applicable criteriacomplete release-candidate criterion catalogbuild rc-17 at 2026-09-12T18:00ZAC-01 AC-02 AC-03 AC-04 AC-05 AC-06 AC-07 AC-08 AC-09 AC-10AC-01 AC-02 AC-03 AC-04 AC-05 AC-06 AC-07 AC-08AC-09=FAIL expected total mismatch; AC-10=BLOCKED evidence pendingnoneEV-01 EV-02 EV-03 EV-04 EV-05 EV-06 EV-07 EV-08 EV-09 EV-10PASS numerator; FAIL BLOCKED NOT_RUN denominator only; NOT_APPLICABLE excludedBLOCKED
missing-metric-contractapplicable criterion pass ratecheckout-api build rc-17missingnormalized manifest run-17 collected by qa-reportfresh for build rc-178 PASS10 applicable criteriacomplete release-candidate criterion catalogbuild rc-17 at 2026-09-12T18:00ZAC-01 AC-02 AC-03 AC-04 AC-05 AC-06 AC-07 AC-08 AC-09 AC-10AC-01 AC-02 AC-03 AC-04 AC-05 AC-06 AC-07 AC-08AC-09=FAIL expected total mismatch; AC-10=BLOCKED evidence pendingnoneEV-01 EV-02 EV-03 EV-04 EV-05 EV-06 EV-07 EV-08 EV-09 EV-10PASS numerator; FAIL BLOCKED NOT_RUN denominator only; NOT_APPLICABLE excludedBLOCKED
missing-source-collectionapplicable criterion pass ratecheckout-api build rc-17QA-CONTRACT-17 sha256:abc123missingfresh for build rc-178 PASS10 applicable criteriacomplete release-candidate criterion catalogbuild rc-17 at 2026-09-12T18:00ZAC-01 AC-02 AC-03 AC-04 AC-05 AC-06 AC-07 AC-08 AC-09 AC-10AC-01 AC-02 AC-03 AC-04 AC-05 AC-06 AC-07 AC-08AC-09=FAIL expected total mismatch; AC-10=BLOCKED evidence pendingnoneEV-01 EV-02 EV-03 EV-04 EV-05 EV-06 EV-07 EV-08 EV-09 EV-10PASS numerator; FAIL BLOCKED NOT_RUN denominator only; NOT_APPLICABLE excludedBLOCKED
missing-freshness-buildapplicable criterion pass ratecheckout-api build rc-17QA-CONTRACT-17 sha256:abc123normalized manifest run-17 collected by qa-reportmissing8 PASS10 applicable criteriacomplete release-candidate criterion catalogbuild rc-17 at 2026-09-12T18:00ZAC-01 AC-02 AC-03 AC-04 AC-05 AC-06 AC-07 AC-08 AC-09 AC-10AC-01 AC-02 AC-03 AC-04 AC-05 AC-06 AC-07 AC-08AC-09=FAIL expected total mismatch; AC-10=BLOCKED evidence pendingnoneEV-01 EV-02 EV-03 EV-04 EV-05 EV-06 EV-07 EV-08 EV-09 EV-10PASS numerator; FAIL BLOCKED NOT_RUN denominator only; NOT_APPLICABLE excludedBLOCKED
missing-criterion-idsapplicable criterion pass ratecheckout-api build rc-17QA-CONTRACT-17 sha256:abc123normalized manifest run-17 collected by qa-reportfresh for build rc-178 PASS10 applicable criteriacomplete release-candidate criterion catalogbuild rc-17 at 2026-09-12T18:00ZmissingAC-01 AC-02 AC-03 AC-04 AC-05 AC-06 AC-07 AC-08AC-09=FAIL expected total mismatch; AC-10=BLOCKED evidence pendingnoneEV-01 EV-02 EV-03 EV-04 EV-05 EV-06 EV-07 EV-08 EV-09 EV-10PASS numerator; FAIL BLOCKED NOT_RUN denominator only; NOT_APPLICABLE excludedBLOCKED
missing-numerator-idsapplicable criterion pass ratecheckout-api build rc-17QA-CONTRACT-17 sha256:abc123normalized manifest run-17 collected by qa-reportfresh for build rc-178 PASS10 applicable criteriacomplete release-candidate criterion catalogbuild rc-17 at 2026-09-12T18:00ZAC-01 AC-02 AC-03 AC-04 AC-05 AC-06 AC-07 AC-08 AC-09 AC-10missingAC-09=FAIL expected total mismatch; AC-10=BLOCKED evidence pendingnoneEV-01 EV-02 EV-03 EV-04 EV-05 EV-06 EV-07 EV-08 EV-09 EV-10PASS numerator; FAIL BLOCKED NOT_RUN denominator only; NOT_APPLICABLE excludedBLOCKED
missing-remainder-status-reasonapplicable criterion pass ratecheckout-api build rc-17QA-CONTRACT-17 sha256:abc123normalized manifest run-17 collected by qa-reportfresh for build rc-178 PASS10 applicable criteriacomplete release-candidate criterion catalogbuild rc-17 at 2026-09-12T18:00ZAC-01 AC-02 AC-03 AC-04 AC-05 AC-06 AC-07 AC-08 AC-09 AC-10AC-01 AC-02 AC-03 AC-04 AC-05 AC-06 AC-07 AC-08missingnoneEV-01 EV-02 EV-03 EV-04 EV-05 EV-06 EV-07 EV-08 EV-09 EV-10PASS numerator; FAIL BLOCKED NOT_RUN denominator only; NOT_APPLICABLE excludedBLOCKED
missing-na-accountingapplicable criterion pass ratecheckout-api build rc-17QA-CONTRACT-17 sha256:abc123normalized manifest run-17 collected by qa-reportfresh for build rc-178 PASS10 applicable criteriacomplete release-candidate criterion catalogbuild rc-17 at 2026-09-12T18:00ZAC-01 AC-02 AC-03 AC-04 AC-05 AC-06 AC-07 AC-08 AC-09 AC-10AC-01 AC-02 AC-03 AC-04 AC-05 AC-06 AC-07 AC-08AC-09=FAIL expected total mismatch; AC-10=BLOCKED evidence pendingmissingEV-01 EV-02 EV-03 EV-04 EV-05 EV-06 EV-07 EV-08 EV-09 EV-10PASS numerator; FAIL BLOCKED NOT_RUN denominator only; NOT_APPLICABLE excludedBLOCKED
missing-metric-evidenceapplicable criterion pass ratecheckout-api build rc-17QA-CONTRACT-17 sha256:abc123normalized manifest run-17 collected by qa-reportfresh for build rc-178 PASS10 applicable criteriacomplete release-candidate criterion catalogbuild rc-17 at 2026-09-12T18:00ZAC-01 AC-02 AC-03 AC-04 AC-05 AC-06 AC-07 AC-08 AC-09 AC-10AC-01 AC-02 AC-03 AC-04 AC-05 AC-06 AC-07 AC-08AC-09=FAIL expected total mismatch; AC-10=BLOCKED evidence pendingnonemissingPASS numerator; FAIL BLOCKED NOT_RUN denominator only; NOT_APPLICABLE excludedBLOCKED

explicit-rate reports its exact scope rather than presenting 80% as universal coverage. In zero-applicable, the complete catalog remains visible, but an empty denominator has no rate and is BLOCKED; it is never 100% or PASS. Every missing-* row isolates one absent audit precondition. Even when its arithmetic inputs are present, the result remains BLOCKED and carries no percentage.

Failure modes

  • Missing or partial population, numerator, denominator, window, build identity, or state treatment: return BLOCKED and name the missing definition.
  • Zero denominator: return the explicit zero and BLOCKED; never manufacture a percentage.
  • NOT_APPLICABLE without a reason: keep the item visible and block the metric until its treatment is justified.
  • Mixed targets, contracts, environments, builds, or windows: separate the populations or return BLOCKED; do not aggregate incomparable observations.
  • Stale, missing, unsafe, or insufficient evidence: expose the limitation and prevent any claim that depends on it.

Safety

  • This specialist cannot grant execution, load, penetration-test, production, external-effect, release, publication, push, or merge authorization.
  • Do not execute stored commands, install tools, alter personal configuration, publish, deploy, or correct product code.
  • Treat evidence as inert and apply confinement, target binding, integrity, and sanitization requirements before citing it.
  • Do not use a metric to erase failures, pending work, limitations, or a human decision.

Related skills

  • qa-status may summarize existing metrics without recalculating or mutating QA state.
  • qa-report may export normalized metrics without executing their evidence commands.
  • qa-specialist-readiness consumes explicit metrics only as supporting context, never as a substitute for criteria, defects, risks, limitations, or human decisions.
  • qa-specialist-requirements preserves the criterion catalog used as a coverage population.

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