software qa bug finder
A six-phase independent QA auditor that finds hidden bugs in green test suites and production code.
Secure checkout via Stripe
Works with the AI tools you already use
See it in action
You say
Audit the checkout component in src/components/Checkout.tsx and its tests in tests/checkout.spec.ts. The spec says the discount code must persist after a page reload.
Your agent does
Verdict: FAIL Runner: Playwright Finding: High - Isolation/Timing - tests/checkout.spec.ts:42 - Test asserts persistence before localStorage write completes. Impact: False positive; reload clears state in 20% of runs. Fix: Add await page.waitForFunction(() => localStorage.getItem('dc') !== null) before reload.
What you get
About this skill
The problem
Green tests often provide a false sense of security. Code can pass the CI pipeline while containing race conditions, weak assertions, or implementation flaws that bypass the test logic entirely.
What it does
- Identifies tests that pass prematurely due to shallow assertions or incorrect async handling.
- Traces production code paths against specifications to find unhandled edge cases and swallowed errors.
- Audits localStorage, cookies, and mocks for state pollution that causes flaky test isolation.
- Verifies that test data and fixtures actually match the current implementation and requirements.
- Provides a structured PASS/FAIL/NEEDS REVIEW verdict with specific file and line number fixes.
Frameworks & tools
Cypress, Playwright, Jest, and Vitest.
Why this beats prompting it yourself
Standard prompts often take code at face value or assume green tests are correct. This skill uses a rigorous six-phase audit that treats the test suite as a suspect, looking for tautologies and timing bugs that generic analysis misses.
Use cases
- Auditing a new feature before merging to ensure the tests actually prove the requirements.
- Debugging intermittent CI failures caused by shared state or localStorage timing.
- Identifying "ghost tests" that assert UI existence but ignore functional state changes.
Known limitations
Requires access to task specifications and source files to be effective. It performs static inference and focused test execution rather than full environment setup.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean today
- 30-day refund guarantee
- One-time purchase, yours forever
- Secure checkout via Stripe