# Qa

> A Claude skill from waitdeadai/minmaxing.

- **Type:** Skill
- **Install:** `agentstack add skill-waitdeadai-minmaxing-qa`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [waitdeadai](https://agentstack.voostack.com/s/waitdeadai)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [waitdeadai](https://github.com/waitdeadai)
- **Source:** https://github.com/waitdeadai/minmaxing/tree/main/.claude/skills/qa

## Install

```sh
agentstack add skill-waitdeadai-minmaxing-qa
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# /qa

Browser-based E2E QA with Playwright. Pass/Fail only — no "mostly works", no "looks okay".

**MAX_PARALLEL_AGENTS** — ceiling for browser test lanes. Split QA only across independent flows, browsers, or surfaces.

**Use when:** User says "QA this", "test this feature", "browser test", "E2E test", "verify this works", "swarm QA".

**Swarm:** "swarm QA" → `/qa` with an efficacy-first QA wave up to `MAX_PARALLEL_AGENTS`.

---

## Playwright E2E Protocol

### Step 1: Ensure Playwright is Available

```bash
npx playwright --version || npm install -D @playwright/test && npx playwright install chromium
```

### Step 2: Create/Run Test

For UI verification, write a Playwright test:

```javascript
// e2e/qa-[feature].spec.js
const { test, expect } = require('@playwright/test');

test('feature works', async ({ page }) => {
  await page.goto('http://localhost:3000');
  // ... test steps
  await expect(page.locator('.result')).toHaveText('expected');
});
```

Run with:
```bash
npx playwright test e2e/qa-[feature].spec.js --reporter=line
```

### Step 3: Pass/Fail Verification

- **PASS** = test exits with code 0
- **FAIL** = test exits with non-zero OR assertion error

### Step 4: Atomic Bug Fix

If test fails, fix the bug (not the test) and re-run.

---

## QA Output Format

```
## QA Results: [Feature]
- Result: PASS | FAIL
- Evidence: npx playwright test output
- Fix: [file:line] if failed
```

---

## Anti-Patterns

- Modifying tests to pass instead of fixing code → BLOCK
- Skipping E2E when UI involved → BLOCK
- "Looks okay" without running test → BLOCK

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [waitdeadai](https://github.com/waitdeadai)
- **Source:** [waitdeadai/minmaxing](https://github.com/waitdeadai/minmaxing)
- **License:** Apache-2.0

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-waitdeadai-minmaxing-qa
- Seller: https://agentstack.voostack.com/s/waitdeadai
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.