QA Test — Testing skill for Claude Code
Claude Code skill for automated front-end QA testing with browser automation, discovery crawling, and adversarial break-it testing.
How to install QA Test
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open adampaulwalker/qa-test and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What QA Test does
Claude Code skill for automated front-end QA testing with browser automation, discovery crawling, and adversarial break-it testing.
Alternatives in Testing
- Playwright — claude-plugins-official Browser automation, E2E testing, screenshots 29.4k ★
- Playwright Automation — git clone Browser automation skill for end-to-end testing and web interaction 2.3k ★
- Vibetest Use — Vibetest MCP - automated QA testing using Browser-Use agents 826 ★
README
qa-test
A Claude Code skill for automated front-end QA testing. It drives a real browser through Playwright MCP, testing your application the way a user would - clicking buttons, filling forms, navigating pages, and verifying that everything works.
What It Does
The qa-test skill gives Claude Code two personas and five testing modes to thoroughly test any web application through its UI:
- Quinn - A veteran QA engineer who methodically tests against your success criteria, documenting every pass and failure with screenshots
- Jinx - A chaos tester who receives only a URL and systematically tries to break everything, with no knowledge of how the app is "supposed" to work
Testing Modes
| Mode | Flag | Description |
|---|---|---|
| Standard | (default) | Quinn tests against a provided success criteria file, verifying each criterion with screenshots and detailed reporting |
| Discovery | --discover |
Quinn crawls the application, clicking through every nav item, sidebar link, and modal to build a complete page inventory |
| Adversary | --adversary |
Jinx tries to break the app with extreme inputs, rapid clicks, navigation attacks, and viewport abuse |
| Full | --full |
Runs all three modes in sequence: discover the site, test criteria, then try to break it |
| Parallel | --parallel |
Spawns multiple agents with dedicated browser instances for large apps - Quinn agents test criteria concurrently while Jinx runs adversary testing |
Installation
Copy the skill files to your Claude Code skills directory:
mkdir -p ~/.claude/skills/qa-test
cp SKILL.md SUCCESS-CRITERIA-TEMPLATE.md RESEARCH.md BEST-PRACTICES.md ~/.claude/skills/qa-test/
Or clone this repo directly:
git clone https://github.com/adampaulwalker/qa-test.git ~/.claude/skills/qa-test
MCP Dependencies
**Required:**
claude mcp add playwright -- npx @playwright/mcp@latest
**Recommended:**
claude m
Related Skills
Fec Plan
Unified front-end planning entrance - implementation/architecture plan or testing strategy. The implementation
ShipGuard
Claude Code skills for automated E2E testing with agent-browser (Playwright CLI). Discover routes, generate YA
Agent Tools Claude Code
Agent Tools is a Claude Code plugin marketplace for engineering tasks, automated testing, code quality, browse
Wf Browser
Run AI-driven browser automation and E2E testing via the wf-browser skill
Smart Browser
Browser automation and API testing MCP server on Playwright + Chrome DevTools Protocol. Numbered element refs
Vindicate
A local-first Playwright test automation toolkit for AI coding agents (Cursor, Claude Code, Copilot), with MCP
Related Agents
Pentest Auditor
Runs automated penetration testing — web, API, browser, GitHub, and local code security probing. Dispatched by
Atlas
You are a specialized E2E testing agent. Your job is to run end-to-end tests, browser automation, and full-sta
Playwright Website Visual Tester
Use this agent when you need comprehensive visual testing of user flows, end-to-end testing with browser autom