Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLIAbout this skill
Use when auditing tests that may not verify real behavior: tautological assertions, missing assertions, skipped tests without a tracker, mock-everything tests, swallowed exceptions, snapshot churn, and framework traps in vitest/jest, pytest, Playwright, and bats. Trigger on requests such as "audit testes fracos", "tests que não pegam regressão", "test rigor audit", "weak test audit", "no-op tests", or "antes de refatorar X auditar testes primeiro". Especially useful before refactoring a SUT, after a large PR, or during legacy onboarding. Produces a markdown report grouped by file with severity, evidence, and suggested fixes; high-severity findings include TaskNote bodies.
Quick start
- Copy the install prompt. Use the green button above this README.
- Send it to your agent. Paste it into your coding agent’s chat and send.
- Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Review, license & listing details
This is an imported listing. We haven’t certified its safety, license, or compatibility. Skills may include executable scripts.
Only SKILL.md was scanned. Supporting files and scripts were not checked. No safety grade has been assigned.
0 potential findings · Scanned 11/4/2026 · Scanner 0.2.1
Content SHA-256: 1430a1b83aff050ef9992a2ca54055f68b85329e71ff3b90f5cf121c07a9bcaf
About this listing
- Category
- Engineering
- Reported license
- MIT
- Listing language (estimated)
- English
- Review status
- Not individually reviewed
- Agent compatibility
- Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.