Multi-agent Playwright test automation for web applications (5 specialized agents)
npx claudepluginhub joshuarweaver/cascade-code-testing-misc --plugin intenet1001-commits-cs-pluginsA collection of Claude Code plugins for web application testing, automation, and document generation.
Multi-agent Playwright test automation for web applications using 5 specialized agents:
| Agent | Role |
|---|---|
| Explorer | Page discovery, DOM analysis, selector extraction |
| Functional | Page load, button click, form validation testing |
| Visual | Responsive screenshots, accessibility (axe-core) |
| API | XHR/Fetch capture, status code validation |
| Performance | Core Web Vitals, load time measurement |
/plugin marketplace add intenet1001-commits/cs_plugins
/plugin install playwright-test
curl -fsSL https://raw.githubusercontent.com/intenet1001-commits/cs_plugins/main/install.sh | bash
git clone https://github.com/intenet1001-commits/cs_plugins ~/.claude/plugins/marketplaces/cs_plugins
/test - Run Playwright multi-agent tests
"Run Playwright test"┌─────────────────────────────────────────────────────────────┐
│ Test Coordinator │
├─────────────────────────────────────────────────────────────┤
│ Phase 1: Run Explorer first (generate page map) │
│ │
│ Phase 2: Run remaining 4 agents in parallel │
│ ┌──────────┬──────────┬──────────┬──────────┐ │
│ │Functional│ Visual │ API │Performance│ │
│ └──────────┴──────────┴──────────┴──────────┘ │
│ │
│ Phase 3: Aggregate results and generate unified report │
└─────────────────────────────────────────────────────────────┘
| Variable | Default | Description |
|---|---|---|
TEST_URL | http://localhost:9005 | Target URL for testing |
HEADLESS | true | Hide browser window |
SLOW_MO | 0 | Action delay time (ms) |
DEVTOOLS | false | Open developer tools |
After test execution, results are generated in:
tests/
├── results/
│ ├── REPORT.md # Unified markdown report
│ ├── page-map.json # Page structure map
│ ├── functional-tests.json # Functional test results
│ ├── visual-tests.json # Visual test results
│ ├── api-tests.json # API test results
│ └── performance-report.json # Performance metrics
└── screenshots/ # Responsive screenshots
MIT License - see LICENSE for details.
Issues and pull requests are welcome!
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Team-oriented workflow plugin with role agents, 27 specialist agents, ECC-inspired commands, layered rules, and hooks skeleton.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.