- Home
- Skills
- Testing & Debugging
- 🧪 Test Quality Auditor
More screenshots
Works with the AI Agents you already use
🧪 Test Quality Auditor
Reports include rule identifiers, severity, file locations and suggested next steps.
$15
🧪 Test Quality Auditor
Example session with this skill installed
Review supported unit-test source in services/ for weak-test patterns. Report findings for human review and identify syntax or coverage that needs manual inspection; do not execute or rewrite the tests.
- Read your context and instructions
- Compiled the test quality auditor
Illustrative review note
A source pattern such as expect(mockUser).toBe(mockUser) merits manual review because it compares a value with itself. Check whether the assertion observes behavior produced by the system under test.
This is an illustrative explanation, not a captured execution or proof that the test has no value. The current scanner has syntax-coverage limits and can miss tests or flag legitimate ones. Review the input coverage and findings alongside actual test results.
Connects securely to your tools. The creator never sees your data.
About this skill
Review weak-test signals, not coverage scores
Test Quality Auditor reads supported JavaScript, TypeScript and Python test source and flags patterns that may deserve a closer look: missing or trivial assertions, repeated mock values, snapshot checks, tautologies, placeholders and mock-heavy setup.
What you get
A read-only Python scanner, synthetic examples, a fixture check and review guidance. Reports include rule identifiers, severity, file locations and suggested next steps. The scanner does not execute or rewrite the tests, measure coverage or establish whether a test verifies the intended behavior.
Current delivered version: important limits
The current package uses narrow text-pattern extraction. Python class-indented unittest methods, async tests and return-annotated test functions are not recognized reliably. JavaScript function callbacks, quoted titles and nested callback syntax can be missed or truncated. A snapshot finding can remain even when a behavioral assertion is present.
Zero findings is not evidence that every test was assessed. Missing paths are not shown in the default Markdown report, and the current scanner's exit status is not a reliable quality or coverage gate. Review input coverage and findings manually; do not use this version as an unattended CI pass/fail gate.
Run locally
Use an agent that can read the supplied repository files and run Python. The scanner uses the standard library and needs no network calls. Use redacted fixtures because reported excerpts may contain source text. No time-saving estimate, complete framework coverage or test-effectiveness guarantee is implied.
Static heuristics, not test execution or intent analysis. Current extraction misses class-indented unittest methods, async/annotated Python and some JavaScript callback/title forms. Snapshot findings can be false positives. Zero findings or exit 0 does not establish complete assessment; manually review coverage.
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 any payment.
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 5 months ago
Requires
Permissions
File Scopes
Notes: Read-only. Prints each finding with rule id, severity, file, and line. Writes nothing and reads no environment variables.