Ag Referencia Qualidade
Quality Gates minimos, checklist pos-execucao, regras anti-teatralidade, metricas CI. Reference skill carregado on-demand.
Install
$ agentstack add skill-andregusman-raiz-a-gusman-claude-ag-referencia-qualidade ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo 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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-andregusman-raiz-a-gusman-claude-ag-referencia-qualidade) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
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 →About
Quality Gates (Minimos)
Antes de declarar qualquer tarefa como concluida:
| Gate | Criterio | Comando Tipico | |------|----------|----------------| | Build | Sem erros | bun run build | | TypeCheck | 0 erros | bun run typecheck ou bunx tsc --noEmit | | Lint | 0 erros novos | bun run lint | | Tests | 0 falhas novas | bun run test ou pytest | | Security | 0 vulnerabilidades criticas | bun run audit | | UX Render | 0 L1 failures (quando configurado) | /ag-testar-ux-qualidade --layers=L1 | | UX Compliance | WCAG AA + Lighthouse >= 90 | /ag-testar-ux-qualidade --layers=L4 |
Teste Focado (durante desenvolvimento)
Preferir execucao de teste individual para feedback rapido:
bunx vitest run path/to/test.test.ts # Um arquivo
bunx vitest run --reporter=verbose # Suite completa (somente no final)NUNCA rodar bun run test durante desenvolvimento iterativo — somente para validacao final.
Checklist Minimo Pos-Execucao
bun run typecheck && bun run lint && bun run testRegras Anti-Teatralidade (Obrigatorias)
Ao escrever ou revisar testes:
- Cada expect() DEVE poder FALHAR em cenario real
- NUNCA:
.catch(() => false),|| true, conditional sem else, expect always-true - SEMPRE: hard-code valores esperados, testar ambos paths (sucesso + falha)
- SEMPRE: mutation mental antes de declarar done ("se eu introduzir bug, este teste falha?")
- Ver detalhes:
.claude/rules/test-quality-enforcement.md
Metricas de Qualidade (CI)
- Theatrical scan: CI bloqueia merge se anti-patterns detectados (test-quality job)
- Mutation testing: Stryker roda semanalmente (mutation-testing.yml), target 80%
- DORA metrics: Change Fail Rate, Lead Time, Deploy Frequency (dora-metrics.yml)
- Quality gates: TS budget, ESLint budget, file size, bun run audit (quality-gates.yml)
- Audit local:
bash .claude/scripts/test-quality-audit.sh [path]
Compaction Preservation
Ao executar /compact, SEMPRE incluir instrucao: > "Preserve: lista de arquivos modificados, task atual, comandos de teste, erros encontrados"
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
- Source: andregusman-raiz/a-gusman-claude
- License: MIT
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.