patchright-skill
Patchright-based browser automation with bot detection bypass. Use when Claude needs to interact with local web applications, test localhost/dev servers, take screenshots, or perform UI interactions on private networks. Ideal for QA automation, frontend debugging, E2E testing, and pre-deployment verification on local development environments.
What this skill does
# Patchright - Browser Automation Skill
Patchright-based browser automation with bot detection bypass. Use for localhost, dev servers, web app testing, screenshots, and UI interactions.
## Triggers
**URL/Network:**
- localhost (http://localhost:*, http://127.0.0.1:*)
- Local IPs (192.168.x.x, 10.x.x.x, 172.16-31.x.x)
- Dev server ports (3000, 5173, 8080, 4200, 5000, etc.)
**Web App Testing:**
- "test the app", "check the site"
- "open localhost", "view in browser"
- "take screenshot", "capture screen"
- "check UI", "view page"
- QA, E2E testing, dev build verification
**Browser Interaction:**
- "click", "press button"
- "type", "fill form"
- "login", "sign up"
- "open menu", "click tab"
- "scroll", "navigate"
**Visual Verification:**
- "how does it look?", "is it working?"
- "check design", "verify layout"
- "responsive test", "screen size"
- "check rendering", "verify component"
**Development Workflow:**
- Verify changes after code edits
- Frontend debugging
- Real-time dev feedback
- Pre-deployment checks
## Core: Server Mode (Session Persistence!)
**Problem**: scripts/executor.py terminates process on each call -> browser session lost
**Solution**: scripts/server.py runs background server -> session persists
### Start Server (Required!)
```bash
cd ~/.claude/skills/patchright-skill
python scripts/server.py start &
```
### Server Commands
```bash
# Check status
python scripts/server.py status
# Stop server
python scripts/server.py stop
# Call tool
python scripts/server.py call '{"tool": "...", "args": {...}}'
```
## Usage
### 1. Navigate + Screenshot (Most Common Pattern)
```bash
cd ~/.claude/skills/patchright-skill
# Start server (if not running)
python scripts/server.py start &
sleep 2
# Navigate to page
python scripts/server.py call '{"tool": "navigate", "args": {"url": "http://localhost:3000"}}'
# Take screenshot
python scripts/server.py call '{"tool": "screenshot", "args": {"path": "screenshot.png", "full_page": true}}'
```
### 2. Click + Interaction
```bash
# Click element
python scripts/server.py call '{"tool": "click", "args": {"selector": "button.submit"}}'
python scripts/server.py call '{"tool": "click", "args": {"selector": "#menu-btn"}}'
python scripts/server.py call '{"tool": "click", "args": {"selector": "body"}}' # Click anywhere
# Type text
python scripts/server.py call '{"tool": "type", "args": {"selector": "#email", "text": "[email protected]"}}'
python scripts/server.py call '{"tool": "type", "args": {"selector": "input[name=password]", "text": "password123"}}'
```
### 3. Get Information
```bash
# Current URL
python scripts/server.py call '{"tool": "get_url"}'
# Page title
python scripts/server.py call '{"tool": "get_title"}'
# Element text
python scripts/server.py call '{"tool": "get_text", "args": {"selector": ".error-message"}}'
```
### 4. Wait
```bash
# Wait for element to appear
python scripts/server.py call '{"tool": "wait_for", "args": {"selector": ".loading-complete", "timeout": 10000}}'
```
## Tool Reference
| Tool | Description | Args |
|------|-------------|------|
| launch | Start browser | headless: bool (default: false) |
| close | Close browser | - |
| navigate | Go to URL | url: string (required) |
| screenshot | Save to file | path: string, full_page: bool |
| click | Click element | selector: string (required) |
| type | Type text | selector: string, text: string |
| get_text | Get element text | selector: string |
| wait_for | Wait for element | selector: string, timeout: int |
| get_url | Get current URL | - |
| get_title | Get page title | - |
## Examples
### Login Test
```bash
cd ~/.claude/skills/patchright-skill
python scripts/server.py start &
sleep 2
# Navigate to login page
python scripts/server.py call '{"tool": "navigate", "args": {"url": "http://localhost:3000/login"}}'
python scripts/server.py call '{"tool": "screenshot", "args": {"path": "login_page.png"}}'
# Fill form
python scripts/server.py call '{"tool": "type", "args": {"selector": "#email", "text": "[email protected]"}}'
python scripts/server.py call '{"tool": "type", "args": {"selector": "#password", "text": "admin123"}}'
python scripts/server.py call '{"tool": "screenshot", "args": {"path": "login_filled.png"}}'
# Submit
python scripts/server.py call '{"tool": "click", "args": {"selector": "button[type=submit]"}}'
sleep 2
python scripts/server.py call '{"tool": "screenshot", "args": {"path": "login_result.png"}}'
```
### App Navigation
```bash
# Enter app
python scripts/server.py call '{"tool": "navigate", "args": {"url": "http://localhost:3000"}}'
python scripts/server.py call '{"tool": "click", "args": {"selector": "body"}}' # Click to enter
sleep 2
python scripts/server.py call '{"tool": "screenshot", "args": {"path": "app_main.png", "full_page": true}}'
# Explore features
python scripts/server.py call '{"tool": "click", "args": {"selector": ".create-btn"}}'
python scripts/server.py call '{"tool": "screenshot", "args": {"path": "after_action.png"}}'
```
## Selector Tips
```css
/* ID */
#submit-btn
/* Class */
.nav-menu
button.primary
/* Attribute */
input[type=email]
button[data-testid="login"]
a[href="/about"]
/* Text content */
text=Login
text=Submit
/* Combined */
form#login button[type=submit]
.sidebar .menu-item:first-child
```
## Technical Specs
- **Engine**: patchright (undetected playwright fork)
- **Browser**: Google Chrome (channel: 'chrome')
- **Bot Detection Bypass**: YES (Cloudflare, reCAPTCHA, etc.)
- **Localhost Support**: YES
- **Private IP Support**: YES
- **Server Port**: 9222
## Troubleshooting
**"Server not running" error:**
```bash
python scripts/server.py start &
sleep 2
```
**Browser not visible:**
- headless=False is default, browser window should appear
- In server mode, browser persists in background
**Session disconnected:**
- Use scripts/server.py instead of scripts/executor.py
- Server keeps session alive once started
**Element not found:**
- Use wait_for to wait first
- Verify selector in DevTools
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.