본문으로 건너뛰기
cccskills
무료GitHub에 공개

qa-specialist-functional

Design traceable functional test conditions across positive, negative, boundary, and error behavior with observable expectations.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(1)

  • SKILL.md5.1 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

QA functional specialist

Use this specialist when a QA workflow needs functional conditions or cases derived from an approved contract. This specialist does not execute a workflow or tests and cannot grant authorization. Read workflow and safety before advising the calling workflow.

Inputs

  • Identified target and contract with preserved criterion IDs and text.
  • Applicable, sufficiently clear functional requirements and their observable expected behavior.
  • Actors, preconditions, inputs, state transitions, business rules, dependencies, and error contracts.
  • Supported platforms, environments, data constraints, known defects, and existing cases.
  • Authorization boundaries supplied by the calling workflow.

Procedure

  1. Preserve target, contract, criterion IDs, criterion text, and supplied authorization. Do not silently rewrite the source behavior.
  2. Partition each applicable behavior into valid and invalid equivalence classes. Identify exact boundaries and state transitions from the contract rather than guessing them.
  3. Propose at least one positive, negative, and boundary condition when each applies. Add explicit error, recovery, retry, ordering, or idempotency conditions when the behavior exposes them.
  4. For every condition, state preconditions, input or action, expected result, and how that result is observable. Expected and observed values remain distinct; this specialist supplies no observed result because it does not execute.
  5. Trace each condition to criterion IDs and risks. Explain any NOT_APPLICABLE partition and preserve uncovered applicable behavior as a gap.
  6. If a boundary, error contract, or expected observation is missing, return the affected condition as BLOCKED and ask the contract owner. Never invent limits or successful outcomes.
  7. Return the proposed conditions to the calling workflow, which decides authorized execution, binds evidence, records case results, and derives the global verdict.

Output

Return a functional coverage record containing:

  • target, contract, criteria, assumptions, and constraints;
  • condition ID, partition (positive, negative, boundary, or error), preconditions, input or action, expected observable result, criterion IDs, risk links, environment/data needs, and evidence need;
  • uncovered behavior, blockers, limitations, and justified non-applicability;
  • a recommended next action for the calling workflow.

These are proposed conditions, not executed case results. Do not populate observed values, evidence references, or PASS without execution.

Reference scenarios

scenariopartitioninputexpectedobservableoutcome
complete-tripletpositive2quantity 2 is accepted and total is recalculatedyesREADY
complete-tripletnegativetextvalidation rejects a non-numeric quantity and identifies the fieldyesREADY
complete-tripletboundary1minimum quantity 1 is accepted and total is recalculatedyesREADY
missing-observationerrorservice timeoutunspecifiednoBLOCKED

In complete-triplet, all three applicable partitions have expected behavior visible in product state or response. READY only marks a proposed condition for the calling workflow and is not a case result. In missing-observation, the contract supplies no expected timeout behavior, so the specialist asks the owner to define it and keeps the error condition BLOCKED.

Failure modes

  • Missing or ambiguous expected behavior: return the affected condition as BLOCKED and identify the missing oracle.
  • Boundary absent from the contract: ask for the limit; do not derive one from implementation behavior and present it as authoritative.
  • Applicable positive, negative, boundary, or error partition omitted: expose a coverage gap.
  • Required environment, account, data, or tool unavailable: record it as missing or unverified; do not claim execution.
  • Existing defect changes observed behavior: preserve the contractual expectation and send the defect to the appropriate workflow rather than normalizing the failure.

Safety

  • Functional design cannot grant authorization for execution, production access, load, penetration testing, or external effects.
  • Use synthetic or reviewed data proposals and never expose secrets or personal session state.
  • Do not execute commands, install tools, mutate product data, publish, push, merge, change personal configuration, or correct product code.
  • The calling workflow must enforce evidence confinement and sanitization if it executes a case.

Related skills

  • qa-test may turn approved proposed conditions into authorized executions and evidence-bound case results.
  • qa-specialist-requirements resolves ambiguity before functional partitioning.
  • qa-specialist-strategy prioritizes these conditions by risk and coverage gap.
  • qa-bug records reproducible failures without authorizing product correction.

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