- Home
- Skills
- Testing & Debugging
- software qa bug finder
software qa bug finder
A six-phase independent QA auditor that finds hidden bugs in green test suites and production code.
$5
Works with the AI Agents you already use
software qa bug finder
Example session with this skill installed
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.
- Read your context and instructions
- Compiled the software qa bug
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.
Connects securely to your tools. The creator never sees your data.
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.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Testing & Debugging.
Requires access to task specs and source code. Performs static inference and focused inspection; does not install dependencies or run heavy validation loops.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 3 months ago