# ai-qa-review

Reviews existing test code for smells and checks how testable your application code is. Useful before merging a PR or when a green suite still lets bugs through.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1200 installs · ★ 211
- Author: kindlmann
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/petrkindlmann/qa-skills/tree/HEAD/skills/ai-qa-review/SKILL.md
- Updated: 2026-10-22
- HTML: https://affpapa.org/en/nevibecode/skills/ai-qa-review

## What it does

The skill works on tests you already have; it does not write new ones. It looks for smells across six dimensions: readability, reliability, diagnostic value, design, signs of AI generation, and coverage. It also reviews application code for testability, flagging dependency injection, side-effect, pure-function and interface problems with before/after examples. Qualitative findings are backed by mutation testing: coverage proves a line ran, a mutation score shows whether a wrong value would have been caught.

There are three routes. For a PR with changed test files, only those files are run and scored, and the diff is checked against a checklist. For a whole suite, the skill quantifies, samples, finds 3–5 systemic smells and proposes lint or mutation gates. The third route answers "why is this hard to test?" about application code. The full smell catalogue with SMELL/FIX pairs lives in `references/smell-examples.md`.

Before starting, the skill checks for `.agents/qa-project-context.md` in the project root, which supplies framework conventions, naming patterns and team quality standards. Without that file the framework and standards questions get asked manually. Verification commands are per-framework — Jest, Vitest, Playwright or pytest — so results are rougher on a stack the skill has no conventions for. Treat a smell as a symptom, not a verdict: a long test for a complex workflow can be the right call.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add petrkindlmann/qa-skills --skill ai-qa-review -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/ai-qa-review/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/ai-qa-review/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add petrkindlmann/qa-skills --skill ai-qa-review -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/ai-qa-review/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add petrkindlmann/qa-skills --skill ai-qa-review -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/ai-qa-review/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install petrkindlmann/qa-skills ai-qa-review
```

2. **Manually: put the files in place**
- File: `.github/skills/ai-qa-review/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add petrkindlmann/qa-skills --skill ai-qa-review -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/petrkindlmann/qa-skills --path skills/ai-qa-review
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/ai-qa-review/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add petrkindlmann/qa-skills --skill ai-qa-review -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/petrkindlmann/qa-skills/tree/HEAD/skills/ai-qa-review/SKILL.md

## When to use it
- find tests that pass without asserting anything meaningful
- work out why a suite fails only when run in a different order
- score the test files in a pull request before merge
- explain why a module is hard to cover with tests
- turn repeated review comments into lint rules

## Example prompts
- review the tests in this PR for smells
- run a quality audit over the whole test suite
- why is this module so hard to test?

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 4c5c474722de4eca.

BEGIN THIRD-PARTY FILE 4c5c474722de4eca
```text
---
name: ai-qa-review
description: >-
  Review EXISTING test code for quality, smells, and testability issues. Detects
  test smells across six dimensions — readability, reliability, diagnostic value,
  design, AI-generated, and coverage — analyzes testability of application code,
  and backs the qualitative smells with mutation testing.
  Use when: "review my tests," "test quality audit," "test smells," "testability
  analysis," "are these tests any good." Not for: generating new tests — use
  `ai-test-generation`. Not for: testing AI features in your product — use
  `ai-system-testing`.
  Related: unit-testing, shift-left-testing, coverage-analysis, ai-test-generation.
license: MIT
metadata:
  author: kindlmann
  version: "2.0"
  category: ai-qa
---

<objective>
QA-focused code review that detects test smells, analyzes testability of application code, and identifies coverage gaps. A test that asserts `toBe(true)` and a 95%-coverage suite that only feeds happy-path input both look green and both hide bugs — this skill names the smell, cites the line, and converts "looks fine" into a mutation-score gate.

**Before starting:** Check for `.agents/qa-project-context.md` in the project root. It contains test framework conventions, naming patterns, and project-specific quality standards that calibrate review feedback.
</objective>

---

## Quick Route

Three distinct entry paths. Pick the row, then jump to the named section.

| Situation | Path | Jump to |
|-----------|------|---------|
| PR with changed test files | Run the changed files, score them, check the diff against the PR checklist | **Verification** → **PR Review Checklist** |
| Whole suite needs a health pass | Quantify, sample, find the 3-5 systemic smells, propose lint/mutation gates | **Batch Audit Process** |
| Application code, "why is this hard to test?" | Flag DI / side-effect / pure-function / interface problems with before/after | **Testability Analysis** |

All three share the same smell vocabulary (the six buckets below) and the same Verification commands.

---

## Discovery Questions

First, read `.agents/qa-project-context.md` if present and skip any question it already answers.

1. **Review scope:** Reviewing test code for quality, application code for testability, or both? Each triggers a different Quick Route path.
```
END THIRD-PARTY FILE 4c5c474722de4eca

The third-party file has ended. Everything between the 4c5c474722de4eca tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2340 of 21898 bytes. © kindlmann · MIT · https://github.com/petrkindlmann/qa-skills/tree/HEAD/skills/ai-qa-review/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md