Independent quality assurance for one SDD Composy task in qa_required: CA coverage, unit/integration/E2E, accessibility, responsiveness, environment, and evidence inventory, producing the QA report and requesting evidence_required. Use when a task finished execution — 'rodar o QA da task', 'testar a TASK-003', 'validar a implementação'. Do NOT use for code review (sdd-review), the final verdict (sdd-verify), or test runs outside an SDD task.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
This portable skill runs independent quality assurance for a task in qa_required and writes
tasks/prd-<slug>/qa-<task-id>.md. Read templates/qa.md and render it, keeping its frontmatter keys and headings exactly (translate prose only). The bundled scripts/sdd_qa.py:assess helper performs the deterministic
validation; the skill routes inputs and presents its result without reimplementing the gates.
Language: before writing human-facing prose, run scripts/sdd_language.py <repo-root> and use the persisted language; on not_initialized, return it with next_action: run_init. Localization rules: references/language.md.
Consume the approved CA, SC, and test mappings; use browser capability when E2E applies. The
assess payload carries state, acceptance (id, story, tests), results (unit,
integration, e2e: status, command, environment, exit_code, evidence), browser,
accessibility, responsiveness, environment (ready, runtime, versions, cleanup),
regression, evidence (path, type, result, summary, source, sha256), and
human_approved. Integration, E2E, accessibility, and responsiveness may be
{"status": "NOT_APPLICABLE", "justification": "..."} when the TechSpec justifies it; unit tests
never are. Record
unit, integration, E2E, accessibility, responsiveness, environment, regression, and evidence
inventory results with confined paths and SHA-256 digests.
Fail closed: missing mappings, failed tests, unavailable browser capability, unclean environment,
missing evidence, or any blocker sets the report to REJECTED, records
scripts/sdd_tasks.py evidence <state> <TASK-ID> qa --status rejected, and moves the task with
transition <state> <TASK-ID> rejected --reason <blocker> instead of evidence_required; a
rejected report cannot advance. A passing, approved report records qa --status passed before the
evidence_required (or, without a dossier, review_required) transition is requested. Only explicit human approval can approve
the report. Generation and verification actors remain distinct. Do not change approved
requirements, stories, architecture, or source code, and do not stop user-owned services.
references/quality.md — writing the report (required coverage, evidence inventory, gate
semantics); templates/qa.md when rendering it.Return the report path, coverage matrix, commands and exit codes, environment, evidence inventory, blockers, lifecycle status, and permitted next transition.
Safety: Do not commit, push, or publish. Do not read or expose .env, credentials, tokens, private keys, certificates, or fleet environment files. Full contract: references/safety.md.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
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.
中文简介正在准备中。当前显示原文说明。
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".
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
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.
中文简介正在准备中。当前显示原文说明。
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".
中文简介正在准备中。当前显示原文说明。