# Ag 7 Qualidade

> Maquina autonoma de qualidade (wrapper MERIDIAN). Descobre app, testa 5 dimensoes (ALIVE/REAL/WORKS/LOOKS/FEELS), corrige, re-testa ate convergencia MQS >= 85. Quality Certificate.

- **Type:** Skill
- **Install:** `agentstack add skill-andregusman-raiz-a-gusman-claude-ag-7-qualidade`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [andregusman-raiz](https://agentstack.voostack.com/s/andregusman-raiz)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [andregusman-raiz](https://github.com/andregusman-raiz)
- **Source:** https://github.com/andregusman-raiz/a-gusman-claude/tree/main/skills/ag-7-qualidade

## Install

```sh
agentstack add skill-andregusman-raiz-a-gusman-claude-ag-7-qualidade
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# QUALIDADE — Maquina Autonoma de Qualidade (MERIDIAN)

## Invocacao

```
/qualidade https://app.example.com
/qualidade ~/Claude/GitHub/example-platform
/qualidade https://app.example.com --threshold 90
/qualidade --audit-only https://app.example.com
/qualidade --resume
```

## O que faz

Delega para **ag-meridian (MERIDIAN)** — a maquina autonoma de QA com 5 fases:

1. **PRE-FLIGHT**: Detecta modo (URL vs local), verifica recursos
2. **SCOUT**: Descobre app, mapeia rotas, detecta auth
3. **SIEGE**: Testa 5 dimensoes (ALIVE, REAL, WORKS, LOOKS, FEELS)
4. **FORGE**: Corrige bugs encontrados (ciclo convergente)
5. **DELIVER**: Quality Certificate, baselines, Fix PR

Convergencia: MQS >= threshold (default 85). Max 5 ciclos.

## Implementacao

Este skill delega diretamente para ag-meridian:

```
Agent({
  subagent_type: "ag-meridian",
  prompt: "[input completo do usuario]",
  model: "opus",
  run_in_background: true
})
```

Toda a logica, state management e convergencia estao em ag-meridian.

## Regras Criticas de Verificacao (feedback SophiA — 21 PRs)

O MERIDIAN DEVE seguir estas regras aprendidas de falhas reais:

1. **NUNCA declarar fix completo baseado em build/typecheck** — reproduzir bug via Playwright
2. **Presenca != Corretude** — "pagina tem dados" nao significa "dados corretos"
3. **API 200 != E2E funcional** — tracar dados: API → adapter → state → DOM
4. **Snapshot estatico != Teste** — se nao houve click/select/type, feature NAO foi testada
5. **Testar interacoes adjacentes** — mudar filtro, trocar tab, selecionar outro item apos fix

## Source & license

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

- **Author:** [andregusman-raiz](https://github.com/andregusman-raiz)
- **Source:** [andregusman-raiz/a-gusman-claude](https://github.com/andregusman-raiz/a-gusman-claude)
- **License:** MIT

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

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-andregusman-raiz-a-gusman-claude-ag-7-qualidade
- Seller: https://agentstack.voostack.com/s/andregusman-raiz
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.