Menü
Executar testes do projeto. Usar apos modificar codigo para verificar regressoes.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
| name | run-tests |
| description | Executar testes do projeto. Usar apos modificar codigo para verificar regressoes. |
| disable-model-invocation | true |
| allowed-tools | Bash, Read, Grep |
| argument-hint | [mobile|backend|admin] [--file path] |
Executar testes do projeto StiveX.
/run-tests — Roda testes mobile (default)/run-tests mobile — Testes RNTL do {{MOBILE_DIR}}/run-tests backend — Testes Django do {{BACKEND_DIR}}/run-tests admin — Testes do {{ADMIN_DIR}}/run-tests mobile --file path/to/test — Teste especificocd {{MOBILE_DIR}} && npx jest --no-coverage
# Teste especifico:
cd {{MOBILE_DIR}} && npx jest --no-coverage path/to/test
cd {{BACKEND_DIR}} && source venv/bin/activate && python manage.py test
# App especifica:
cd {{BACKEND_DIR}} && source venv/bin/activate && python manage.py test accounts
cd {{ADMIN_DIR}} && npm run lint
$ARGUMENTS (default: mobile)GroupListScreen.test.tsx — Falha intermitente conhecidaDashboardScreen.stale.test.tsx — Timeout intermitenteCheck for drift between spec.md, plan.md, tasks.md, and the actual code. Reports the gaps; does not fix them.
Run a category-specific quality pass (security / performance / accessibility / i18n / privacy / observability) against the current plan and code.
Surface [NEEDS CLARIFICATION] markers in spec.md (or plan.md) to the user, one at a time, and edit the file with the answers.
Bootstrap or amend constitution.md (framework, preset, or project). Inspects existing project context first; enforces the amendment process: issue first, one article per PR, reviewer non-author.
Print the pipeline quick-reference — a one-screen summary of every /aia:* command and its hand-offs, prefixed by a state-aware "Próximo passo" line.
Execute an approved plan + tasks list by dispatching one fresh subagent per task and applying two-stage review (spec compliance, then code quality) before moving on.