com um clique
test
Run tests with coverage reporting and quality gates.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Menu
Run tests with coverage reporting and quality gates.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Write a structured handoff at session end. Preserves context so the next agent can resume without human briefing. Invoke before ending any feature session longer than 30 minutes.
Multi-perspective code review against project standards with P1/P2/P3 severity classification. Works in Claude Code (Agent + optional GitHub MCP) and Cursor (Task subagents + gh/git). Use when the user invokes /review, asks for a PR or diff review, or wants a standards-aligned review with severity tags.
Multi-perspective code review (P1/P2/P3) for Cursor: inline checklists plus three parallel Task subagents (perf-auditor, security-reviewer, simplicity-reviewer with combined data-integrity prompt). Use when the user invokes /review, asks for a PR review, or wants repo-standard findings with severity.
Create well-formatted git commits following conventional commit standards.
Red→green→refactor discipline for new behavior — forces a failing test before implementation and a passing test before any claim of done.
Create or manage a git worktree for isolated parallel development — lets multiple agents work in the repo simultaneously without branch collisions.
| name | test |
| description | Run tests with coverage reporting and quality gates. |
Run tests with coverage reporting and quality gates.
/test [target] [--coverage] [--watch] [--failed] [--verbose]
target: Specific test file, directory, or test name (optional)--coverage: Generate coverage report (default: true)--watch: Watch mode for continuous testing--failed: Re-run only failed tests--verbose: Verbose outputWhen this skill is invoked:
Autonomy:
Thoroughness:
prd/00_technology.md for project-specific commands:
{lint_command} # Linting
{type_check_command} # Type checking
{test_coverage_command} # Tests with coverage
Problem-Solving:
Presentation:
Read prd/00_technology.md to find the correct test commands
Run tests with coverage (example patterns):
# See prd/00_technology.md for your specific command
{test_runner} tests/ --coverage
Report results:
==================== Test Results ====================
✅ Passed: 42
❌ Failed: 0
⏭️ Skipped: 2
⏱️ Duration: 3.45s
==================== Coverage ====================
Name Stmts Miss Cover
-----------------------------------------------------
src/{project}/__init__ 2 0 100%
src/{project}/main 45 0 100%
...
-----------------------------------------------------
TOTAL 523 0 100%
✅ Coverage requirement met
# Test a specific file
/test tests/unit/test_config
# Test a specific class/describe
/test tests/unit/test_api::TestHealthCheck
# Test a specific function/it
/test tests/unit/test_api::test_health_check
# Test a directory
/test tests/integration/
If coverage < minimum:
⚠️ Coverage below requirement: 95% (required: {min_coverage}%)
Missing coverage in:
- src/{project}/services/user:45-52 (error handling)
- src/{project}/api/auth:78-85 (edge case)
Suggested tests to add:
1. Test error handling in UserService.create()
2. Test authentication timeout scenario
Generate detailed report if available in your stack
When running integration tests:
The test skill enforces these quality gates (see prd/00_technology.md for specific values):
| Gate | Requirement | Action on Failure |
|---|---|---|
| Coverage | Minimum % | Block merge |
| All tests pass | 0 failures | Block merge |
| No skipped (without reason) | Documented skips only | Warn |
| Performance | No test > configured limit | Warn |
$ /test
🧪 Running tests...
tests/unit/test_config::TestSettings::test_default_values PASSED
tests/unit/test_config::TestSettings::test_is_development PASSED
tests/unit/test_api::test_health_check PASSED
tests/unit/test_api::test_root_endpoint PASSED
==================== 4 passed in 0.45s ====================
📊 Coverage: 100% ✅