# /qa: Find, reproduce and fix bugs with regression tests

Source: https://trendhub.net/skills/garrytan-gstack/qa
Skill folder: https://github.com/garrytan/gstack/tree/main/qa
Pack: gstack (https://trendhub.net/skills/garrytan-gstack)
Works with: Claude Code, Claude Code (team mode for a shared repo), Codex, Cursor, OpenCode, Gemini CLI and other agents

The QA skill tests a web page, API, CLI, job or webhook, records a baseline report, then fixes bugs in severity order. Each fix starts with a regression test that fails, then a minimal change, a re-test and its own commit. It stops to check in every five fixes, after two reverts or after touching an unrelated file, with a hard cap of fifty fixes.

## When to use it

- A staging site or local app needs a real click-through before release.
- A CLI, API or webhook behaves wrongly and you want each bug reproduced first.
- You want each fix to ship with its own regression test and commit.

## How it works

1. **Set up**: The agent parses target, tier and mode, asks you to commit or stash if the tree is dirty, and creates a fresh report folder.
2. **Run the baseline**: It explores the chosen surfaces using any test plan from earlier reviews and reports findings before fixing anything.
3. **Write the failing test**: For each bug it writes a regression test that fails for the right reason, matching nearby test style.
4. **Fix, re-test, commit**: It makes the smallest fix, re-runs the test and nearby happy path, and commits only verified changes.
5. **Report**: The final report lists verified, best-effort, reverted and deferred issues, with a browser health score where relevant.

## What it steers the agent away from

- Fixes committed without proof that the bug is gone.
- Weakening existing tests or editing CI configuration.
- Fix loops that sprawl across unrelated files.

## What it can touch

Drives a browser or runs commands against your target, edits source and tests, makes git commits and writes reports and screenshots.

## Pairs well with

- `/browse`
- `/plan-eng-review`
- `/qa-only`

## Questions

### Which bugs get fixed?

It depends on the tier: quick fixes critical and high, standard adds medium, exhaustive adds low and cosmetic issues.

### Can it test something without a web page?

Yes. It probes APIs, CLIs, jobs, workers and webhooks with the repo's own tools and reports contract results instead of a score.
