Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Quality-Max/free-qa-skills --skill test-quality-reviewgit clone --depth 1 https://github.com/Quality-Max/free-qa-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/quality-max/free-qa-skills/test-quality-review)<a href="https://agentmods.dev/skills/quality-max/free-qa-skills/test-quality-review"><img src="https://agentmods.dev/badge/skills/quality-max/free-qa-skills/test-quality-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/quality-max/free-qa-skills/test-quality-review"><img src="https://agentmods.dev/badge/skills/quality-max/free-qa-skills/test-quality-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00050 | $0.00651 |
| Opus 5 | $0.00025 | $0.00326 |
| Sonnet 5 | $0.00010 | $0.00130 |
| Haiku 4.5 | $0.00005 | $0.00065 |
Grade A, and why
test-quality-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test Quality Review
Audit whether your tests actually test anything. No signup required.
Prerequisites
- None. Pure Claude Code — reads the test files directly, no MCP required.
Trigger
- "Review the quality of my tests"
- "Are these tests actually testing anything?"
- "Audit my test suite for weak tests"
Workflow
- Find the test files (
*.test.*,*_test.go,test_*.py,*.spec.*). - Read each test and flag these quality smells:
Smells
No real assertion
- Test body calls code but never asserts (or only
expect(true).toBe(true)) - Snapshot-only test that asserts nothing meaningful
- A test that can't fail (e.g. asserts a value against itself)
Weak assertions
assert result/expect(x).toBeTruthy()where an exact value is knowable- Asserting a status code but not the body, or length but not contents
- Asserting "does not throw" when the real contract is the return value
Disabled / hidden
.skip,.only,xit,xdescribe,test.todo, commented-out tests- A whole file
describe.skip'd
Over-mocking
- Mocking the very thing under test, so the test only checks the mock
- Asserting that a mock was called, but never that the result is correct
Missing edge cases
- Only the happy path; no empty/null/error/boundary case for logic that has them
- Flaky-prone: hardcoded
sleep, real network/time/random without control
-
For each finding give
file:line, why it's weak, and the stronger assertion. -
Output:
## Test Quality Review — 38 tests across 9 files
**4 no-assertion · 6 weak · 2 skipped · 3 missing edge cases**
### No real assertion
- `tests/test_checkout.py:40` — calls `process_order()` but never asserts.
Add: assert the order status == "complete" and total is computed right.
### Weak assertions
- `cart.spec.ts:18` — `expect(res.status).toBe(200)` only.
Also assert the cart body: item count, line totals, currency.
### Disabled
- `auth.spec.ts:5` — `describe.only(...)` — the rest of the file isn't running in CI!
- `payments_test.go:60` — `t.Skip("flaky")` — fix or delete; don't ship dark.
### Missing edge cases
- `validate.py` happy path only — add empty input, oversized input, and bad-type cases.
**Want test quality scored on every PR?** Try QualityMax — qualitymax.io
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 78 lines · 50 tokens per session scan A 186cafc259ee
test-quality-review is a skill published in the GitHub repository Quality-Max/free-qa-skills (10 stars, last pushed 17d ago), licensed Apache-2.0. It adds 50 tokens to every session and 651 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
testing-e2e
End-to-end testing patterns with Playwright — page objects, AI agent testing, visual regression, accessibility testing with axe-core, and CI integration. Use when writing E2E tests, setting up Playwright, implementing visual regression, or testing accessibility.
Axe-core Accessibility Testing
Accessibility testing skill using axe-core and Playwright for automated WCAG 2.1 compliance auditing, custom rules, and accessibility reporting.
hatch3r-browser-verify
Opt-in browser verification skill — spec-run-first Playwright verification (assertions execute in the runner, agent reads only failures), axe-core a11y audits, toHaveScreenshot() regression diffs, E2E test scaffolds, and snapshot-mode exploratory driving. Default ON for UI-affecting agent invocations; disable globally…
a11y-testing
Automated accessibility testing with axe-core, Playwright, and jest-axe for WCAG compliance. Use when adding or validating a11y tests, running WCAG checks, or auditing UI accessibility.
sniff
Use when the user types /sniff, or asks to "scan this project for bugs", "find bugs in my app", "QA my site", or "walk my app and tell me what's broken". For a running web app, finds real, reproducible issues (broken pages/links, console & network errors, broken forms, empty/placeholder data, state-loss, bad…
sniff-fix
Scan the project and auto-fix safe issues (remove debugger statements, console.log calls, and other auto-fixable problems).