AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Ag Criar Cenario Qat

skill-andregusman-raiz-a-gusman-claude-ag-criar-cenario-qat · by andregusman-raiz

[INTERNAL — invocada via ag-4-teste-final] Cria cenarios QAT de alta qualidade seguindo metodologia User Story → QAT Scenario. Gera spec com 4 camadas (L1-L4), rubrica v2 especifica, golden sample e anti-patterns.

↗ Repository
— No reviews yet
0 installs
24 views
0.0% view→install

Install

$ agentstack add skill-andregusman-raiz-a-gusman-claude-ag-criar-cenario-qat

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-andregusman-raiz-a-gusman-claude-ag-criar-cenario-qat)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Ag Criar Cenario Qat? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

ag-criar-cenario-qat — Criar Cenario QAT (INTERNAL)

> Internal skill — invocada automaticamente por ag-4-teste-final via Agent tool. Não use diretamente via /. Para criar cenário QAT customizado use /ag-4-teste-final qat [path].

Papel

O Scenario Designer: transforma features em cenarios QAT que simulam usuarios reais. Cada cenario e um contrato de qualidade com 4 camadas de validacao, golden sample e anti-patterns.

Diferenca de ag-testar-qualidade-qat: ag-testar-qualidade-qat EXECUTA cenarios existentes. ag-criar-cenario-qat CRIA cenarios novos. Diferenca de ag-testar-codigo: ag-testar-codigo cria testes unitarios/integracao. ag-criar-cenario-qat cria testes de QUALIDADE de output.

Invocacao

/ag-criar-cenario-qat feature="Chat educacional" persona="Professor 5o ano"
/ag-criar-cenario-qat feature="Gerador de plano de aula" persona="Coordenador pedagogico" id=QAT-15
/ag-criar-cenario-qat feature="RAG sobre documento" persona="Pesquisador" resultado="Resumo com citacoes"

Pre-requisitos

  1. Estrutura tests/qat/ no projeto (copiar de ~/.claude/shared/templates/qat/)
  2. tests/qat/qat.config.ts existente
  3. tests/qat/rubrics/v2/ com rubricas disponiveis

Ciclo de Criacao

Phase 0: Preflight (estrutura QAT, proximo ID, contexto do projeto)
Phase 1: Design (User Story DADO/QUANDO/ENTAO, tipo, criterios, rubrica)
Phase 2: Golden Sample (output ideal score 9-10, justificativa)
Phase 3: Anti-Patterns (3-5 contra-exemplos com scores esperados)
Phase 4: Implementar spec (4 camadas L1-L4 com Playwright)
Phase 5: Registrar em qat.config.ts
Phase 6: Validacao (typecheck, completude, report)

Output

  • tests/qat/scenarios/qat-XX-nome.spec.ts (cenario 4 camadas)
  • tests/qat/knowledge/golden-samples/QAT-XX.md (output de referencia)
  • tests/qat/knowledge/anti-patterns/QAT-XX.md (contra-exemplos)
  • tests/qat/rubrics/v2/nome.rubric.ts (se criada nova rubrica)
  • tests/qat/qat.config.ts atualizado

Interacao com outros agentes

  • ag-testar-qualidade-qat: Complementar — ag-criar-cenario-qat cria, ag-testar-qualidade-qat executa
  • ag-implementar-codigo: Pos-build — quando ag-implementar-codigo constroi feature nova, ag-criar-cenario-qat cria cenario QAT
  • ag-revisar-codigo: Code review — ag-revisar-codigo verifica se PR de feature inclui cenario QAT
  • ag-especificar-solucao: Pos-spec — quando spec define nova feature, ag-criar-cenario-qat pode criar cenario antecipado

Referencia

  • Agent completo: ~/.claude/agents/ag-criar-cenario-qat.md
  • Pattern: ~/.claude/shared/patterns/qat-scenario-design.md
  • KB Pattern: ~/.claude/shared/patterns/qat-knowledge-base.md
  • Templates: ~/.claude/shared/templates/qat/

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills