313 lines
11 KiB
TypeScript
313 lines
11 KiB
TypeScript
|
import type { BuiltinSkill } from "../types"
|
||
|
|
|
||
|
|
export const playwrightSkill: BuiltinSkill = {
|
||
|
|
name: "playwright",
|
||
|
|
description: "MUST USE for any browser-related tasks. Browser automation via Playwright MCP - verification, browsing, information gathering, web scraping, testing, screenshots, and all browser interactions.",
|
||
|
|
template: `# Playwright Browser Automation
|
||
|
|
|
||
|
|
This skill provides browser automation capabilities via the Playwright MCP server.`,
|
||
|
|
mcpConfig: {
|
||
|
|
playwright: {
|
||
|
|
command: "npx",
|
||
|
|
args: ["@playwright/mcp@latest"],
|
||
|
|
},
|
||
|
|
},
|
||
|
|
}
|
||
|
|
|
||
|
|
export const agentBrowserSkill: BuiltinSkill = {
|
||
|
|
name: "agent-browser",
|
||
|
|
description: "MUST USE for any browser-related tasks. Browser automation via agent-browser CLI - verification, browsing, information gathering, web scraping, testing, screenshots, and all browser interactions.",
|
||
|
|
template: `# Browser Automation with agent-browser
|
||
|
|
|
||
|
|
## Quick start
|
||
|
|
|
||
|
|
\`\`\`bash
|
||
|
|
agent-browser open <url> # Navigate to page
|
||
|
|
agent-browser snapshot -i # Get interactive elements with refs
|
||
|
|
agent-browser click @e1 # Click element by ref
|
||
|
|
agent-browser fill @e2 "text" # Fill input by ref
|
||
|
|
agent-browser close # Close browser
|
||
|
|
\`\`\`
|
||
|
|
|
||
|
|
## Core workflow
|
||
|
|
|
||
|
|
1. Navigate: \`agent-browser open <url>\`
|
||
|
|
2. Snapshot: \`agent-browser snapshot -i\` (returns elements with refs like \`@e1\`, \`@e2\`)
|
||
|
|
3. Interact using refs from the snapshot
|
||
|
|
4. Re-snapshot after navigation or significant DOM changes
|
||
|
|
|
||
|
|
## Commands
|
||
|
|
|
||
|
|
### Navigation
|
||
|
|
\`\`\`bash
|
||
|
|
agent-browser open <url> # Navigate to URL
|
||
|
|
agent-browser back # Go back
|
||
|
|
agent-browser forward # Go forward
|
||
|
|
agent-browser reload # Reload page
|
||
|
|
agent-browser close # Close browser
|
||
|
|
\`\`\`
|
||
|
|
|
||
|
|
### Snapshot (page analysis)
|
||
|
|
\`\`\`bash
|
||
|
|
agent-browser snapshot # Full accessibility tree
|
||
|
|
agent-browser snapshot -i # Interactive elements only (recommended)
|
||
|
|
agent-browser snapshot -c # Compact output
|
||
|
|
agent-browser snapshot -d 3 # Limit depth to 3
|
||
|
|
agent-browser snapshot -s "#main" # Scope to CSS selector
|
||
|
|
\`\`\`
|
||
|
|
|
||
|
|
### Interactions (use @refs from snapshot)
|
||
|
|
\`\`\`bash
|
||
|
|
agent-browser click @e1 # Click
|
||
|
|
agent-browser dblclick @e1 # Double-click
|
||
|
|
agent-browser focus @e1 # Focus element
|
||
|
|
agent-browser fill @e2 "text" # Clear and type
|
||
|
|
agent-browser type @e2 "text" # Type without clearing
|
||
|
|
agent-browser press Enter # Press key
|
||
|
|
agent-browser press Control+a # Key combination
|
||
|
|
agent-browser keydown Shift # Hold key down
|
||
|
|
agent-browser keyup Shift # Release key
|
||
|
|
agent-browser hover @e1 # Hover
|
||
|
|
agent-browser check @e1 # Check checkbox
|
||
|
|
agent-browser uncheck @e1 # Uncheck checkbox
|
||
|
|
agent-browser select @e1 "value" # Select dropdown
|
||
|
|
agent-browser scroll down 500 # Scroll page
|
||
|
|
agent-browser scrollintoview @e1 # Scroll element into view
|
||
|
|
agent-browser drag @e1 @e2 # Drag and drop
|
||
|
|
agent-browser upload @e1 file.pdf # Upload files
|
||
|
|
\`\`\`
|
||
|
|
|
||
|
|
### Get information
|
||
|
|
\`\`\`bash
|
||
|
|
agent-browser get text @e1 # Get element text
|
||
|
|
agent-browser get html @e1 # Get innerHTML
|
||
|
|
agent-browser get value @e1 # Get input value
|
||
|
|
agent-browser get attr @e1 href # Get attribute
|
||
|
|
agent-browser get title # Get page title
|
||
|
|
agent-browser get url # Get current URL
|
||
|
|
agent-browser get count ".item" # Count matching elements
|
||
|
|
agent-browser get box @e1 # Get bounding box
|
||
|
|
\`\`\`
|
||
|
|
|
||
|
|
### Check state
|
||
|
|
\`\`\`bash
|
||
|
|
agent-browser is visible @e1 # Check if visible
|
||
|
|
agent-browser is enabled @e1 # Check if enabled
|
||
|
|
agent-browser is checked @e1 # Check if checked
|
||
|
|
\`\`\`
|
||
|
|
|
||
|
|
### Screenshots & PDF
|
||
|
|
\`\`\`bash
|
||
|
|
agent-browser screenshot # Screenshot to stdout
|
||
|
|
agent-browser screenshot path.png # Save to file
|
||
|
|
agent-browser screenshot --full # Full page
|
||
|
|
agent-browser pdf output.pdf # Save as PDF
|
||
|
|
\`\`\`
|
||
|
|
|
||
|
|
### Video recording
|
||
|
|
\`\`\`bash
|
||
|
|
agent-browser record start ./demo.webm # Start recording (uses current URL + state)
|
||
|
|
agent-browser click @e1 # Perform actions
|
||
|
|
agent-browser record stop # Stop and save video
|
||
|
|
agent-browser record restart ./take2.webm # Stop current + start new recording
|
||
|
|
\`\`\`
|
||
|
|
Recording creates a fresh context but preserves cookies/storage from your session.
|
||
|
|
|
||
|
|
### Wait
|
||
|
|
\`\`\`bash
|
||
|
|
agent-browser wait @e1 # Wait for element
|
||
|
|
agent-browser wait 2000 # Wait milliseconds
|
||
|
|
agent-browser wait --text "Success" # Wait for text
|
||
|
|
agent-browser wait --url "**/dashboard" # Wait for URL pattern
|
||
|
|
agent-browser wait --load networkidle # Wait for network idle
|
||
|
|
agent-browser wait --fn "window.ready" # Wait for JS condition
|
||
|
|
\`\`\`
|
||
|
|
|
||
|
|
### Mouse control
|
||
|
|
\`\`\`bash
|
||
|
|
agent-browser mouse move 100 200 # Move mouse
|
||
|
|
agent-browser mouse down left # Press button
|
||
|
|
agent-browser mouse up left # Release button
|
||
|
|
agent-browser mouse wheel 100 # Scroll wheel
|
||
|
|
\`\`\`
|
||
|
|
|
||
|
|
### Semantic locators (alternative to refs)
|
||
|
|
\`\`\`bash
|
||
|
|
agent-browser find role button click --name "Submit"
|
||
|
|
agent-browser find text "Sign In" click
|
||
|
|
agent-browser find label "Email" fill "user@test.com"
|
||
|
|
agent-browser find first ".item" click
|
||
|
|
agent-browser find nth 2 "a" text
|
||
|
|
\`\`\`
|
||
|
|
|
||
|
|
### Browser settings
|
||
|
|
\`\`\`bash
|
||
|
|
agent-browser set viewport 1920 1080 # Set viewport size
|
||
|
|
agent-browser set device "iPhone 14" # Emulate device
|
||
|
|
agent-browser set geo 37.7749 -122.4194 # Set geolocation
|
||
|
|
agent-browser set offline on # Toggle offline mode
|
||
|
|
agent-browser set headers '{"X-Key":"v"}' # Extra HTTP headers
|
||
|
|
agent-browser set credentials user pass # HTTP basic auth
|
||
|
|
agent-browser set media dark # Emulate color scheme
|
||
|
|
\`\`\`
|
||
|
|
|
||
|
|
### Cookies & Storage
|
||
|
|
\`\`\`bash
|
||
|
|
agent-browser cookies # Get all cookies
|
||
|
|
agent-browser cookies set name value # Set cookie
|
||
|
|
agent-browser cookies clear # Clear cookies
|
||
|
|
agent-browser storage local # Get all localStorage
|
||
|
|
agent-browser storage local key # Get specific key
|
||
|
|
agent-browser storage local set k v # Set value
|
||
|
|
agent-browser storage local clear # Clear all
|
||
|
|
agent-browser storage session # Get all sessionStorage
|
||
|
|
agent-browser storage session key # Get specific key
|
||
|
|
agent-browser storage session set k v # Set value
|
||
|
|
agent-browser storage session clear # Clear all
|
||
|
|
\`\`\`
|
||
|
|
|
||
|
|
### Network
|
||
|
|
\`\`\`bash
|
||
|
|
agent-browser network route <url> # Intercept requests
|
||
|
|
agent-browser network route <url> --abort # Block requests
|
||
|
|
agent-browser network route <url> --body '{}' # Mock response
|
||
|
|
agent-browser network unroute [url] # Remove routes
|
||
|
|
agent-browser network requests # View tracked requests
|
||
|
|
agent-browser network requests --filter api # Filter requests
|
||
|
|
\`\`\`
|
||
|
|
|
||
|
|
### Tabs & Windows
|
||
|
|
\`\`\`bash
|
||
|
|
agent-browser tab # List tabs
|
||
|
|
agent-browser tab new [url] # New tab
|
||
|
|
agent-browser tab 2 # Switch to tab
|
||
|
|
agent-browser tab close # Close tab
|
||
|
|
agent-browser window new # New window
|
||
|
|
\`\`\`
|
||
|
|
|
||
|
|
### Frames
|
||
|
|
\`\`\`bash
|
||
|
|
agent-browser frame "#iframe" # Switch to iframe
|
||
|
|
agent-browser frame main # Back to main frame
|
||
|
|
\`\`\`
|
||
|
|
|
||
|
|
### Dialogs
|
||
|
|
\`\`\`bash
|
||
|
|
agent-browser dialog accept [text] # Accept dialog
|
||
|
|
agent-browser dialog dismiss # Dismiss dialog
|
||
|
|
\`\`\`
|
||
|
|
|
||
|
|
### JavaScript
|
||
|
|
\`\`\`bash
|
||
|
|
agent-browser eval "document.title" # Run JavaScript
|
||
|
|
\`\`\`
|
||
|
|
|
||
|
|
## Global Options
|
||
|
|
|
||
|
|
| Option | Description |
|
||
|
|
|--------|-------------|
|
||
|
|
| \`--session <name>\` | Isolated browser session (\`AGENT_BROWSER_SESSION\` env) |
|
||
|
|
| \`--profile <path>\` | Persistent browser profile (\`AGENT_BROWSER_PROFILE\` env) |
|
||
|
|
| \`--headers <json>\` | HTTP headers scoped to URL's origin |
|
||
|
|
| \`--executable-path <path>\` | Custom browser binary (\`AGENT_BROWSER_EXECUTABLE_PATH\` env) |
|
||
|
|
| \`--args <args>\` | Browser launch args (\`AGENT_BROWSER_ARGS\` env) |
|
||
|
|
| \`--user-agent <ua>\` | Custom User-Agent (\`AGENT_BROWSER_USER_AGENT\` env) |
|
||
|
|
| \`--proxy <url>\` | Proxy server (\`AGENT_BROWSER_PROXY\` env) |
|
||
|
|
| \`--proxy-bypass <hosts>\` | Hosts to bypass proxy (\`AGENT_BROWSER_PROXY_BYPASS\` env) |
|
||
|
|
| \`-p, --provider <name>\` | Cloud browser provider (\`AGENT_BROWSER_PROVIDER\` env) |
|
||
|
|
| \`--json\` | Machine-readable JSON output |
|
||
|
|
| \`--headed\` | Show browser window (not headless) |
|
||
|
|
| \`--cdp <port\\|wss://url>\` | Connect via Chrome DevTools Protocol |
|
||
|
|
| \`--debug\` | Debug output |
|
||
|
|
|
||
|
|
## Example: Form submission
|
||
|
|
|
||
|
|
\`\`\`bash
|
||
|
|
agent-browser open https://example.com/form
|
||
|
|
agent-browser snapshot -i
|
||
|
|
# Output shows: textbox "Email" [ref=e1], textbox "Password" [ref=e2], button "Submit" [ref=e3]
|
||
|
|
|
||
|
|
agent-browser fill @e1 "user@example.com"
|
||
|
|
agent-browser fill @e2 "password123"
|
||
|
|
agent-browser click @e3
|
||
|
|
agent-browser wait --load networkidle
|
||
|
|
agent-browser snapshot -i # Check result
|
||
|
|
\`\`\`
|
||
|
|
|
||
|
|
## Example: Authentication with saved state
|
||
|
|
|
||
|
|
\`\`\`bash
|
||
|
|
# Login once
|
||
|
|
agent-browser open https://app.example.com/login
|
||
|
|
agent-browser snapshot -i
|
||
|
|
agent-browser fill @e1 "username"
|
||
|
|
agent-browser fill @e2 "password"
|
||
|
|
agent-browser click @e3
|
||
|
|
agent-browser wait --url "**/dashboard"
|
||
|
|
agent-browser state save auth.json
|
||
|
|
|
||
|
|
# Later sessions: load saved state
|
||
|
|
agent-browser state load auth.json
|
||
|
|
agent-browser open https://app.example.com/dashboard
|
||
|
|
\`\`\`
|
||
|
|
|
||
|
|
### Header-based Auth (Skip login flows)
|
||
|
|
\`\`\`bash
|
||
|
|
# Headers scoped to api.example.com only
|
||
|
|
agent-browser open api.example.com --headers '{"Authorization": "Bearer <token>"}'
|
||
|
|
# Navigate to another domain - headers NOT sent (safe)
|
||
|
|
agent-browser open other-site.com
|
||
|
|
# Global headers (all domains)
|
||
|
|
agent-browser set headers '{"X-Custom-Header": "value"}'
|
||
|
|
\`\`\`
|
||
|
|
|
||
|
|
## Sessions & Persistent Profiles
|
||
|
|
|
||
|
|
### Sessions (parallel browsers)
|
||
|
|
\`\`\`bash
|
||
|
|
agent-browser --session test1 open site-a.com
|
||
|
|
agent-browser --session test2 open site-b.com
|
||
|
|
agent-browser session list
|
||
|
|
\`\`\`
|
||
|
|
|
||
|
|
### Persistent Profiles
|
||
|
|
Persists cookies, localStorage, IndexedDB, service workers, cache, login sessions across browser restarts.
|
||
|
|
\`\`\`bash
|
||
|
|
agent-browser --profile ~/.myapp-profile open myapp.com
|
||
|
|
# Or via env var
|
||
|
|
AGENT_BROWSER_PROFILE=~/.myapp-profile agent-browser open myapp.com
|
||
|
|
\`\`\`
|
||
|
|
- Use different profile paths for different projects
|
||
|
|
- Login once → restart browser → still logged in
|
||
|
|
- Stores: cookies, localStorage, IndexedDB, service workers, browser cache
|
||
|
|
|
||
|
|
## JSON output (for parsing)
|
||
|
|
|
||
|
|
Add \`--json\` for machine-readable output:
|
||
|
|
\`\`\`bash
|
||
|
|
agent-browser snapshot -i --json
|
||
|
|
agent-browser get text @e1 --json
|
||
|
|
\`\`\`
|
||
|
|
|
||
|
|
## Debugging
|
||
|
|
|
||
|
|
\`\`\`bash
|
||
|
|
agent-browser open example.com --headed # Show browser window
|
||
|
|
agent-browser console # View console messages
|
||
|
|
agent-browser errors # View page errors
|
||
|
|
agent-browser record start ./debug.webm # Record from current page
|
||
|
|
agent-browser record stop # Save recording
|
||
|
|
agent-browser connect 9222 # Local CDP port
|
||
|
|
agent-browser --cdp "wss://browser-service.com/cdp?token=..." snapshot # Remote via WebSocket
|
||
|
|
agent-browser console --clear # Clear console
|
||
|
|
agent-browser errors --clear # Clear errors
|
||
|
|
agent-browser highlight @e1 # Highlight element
|
||
|
|
agent-browser trace start # Start recording trace
|
||
|
|
agent-browser trace stop trace.zip # Stop and save trace
|
||
|
|
\`\`\`
|
||
|
|
|
||
|
|
---
|
||
|
|
Install: \`bun add -g agent-browser && agent-browser install\`. Run \`agent-browser --help\` for all commands. Repo: https://github.com/vercel-labs/agent-browser`,
|
||
|
|
allowedTools: ["Bash(agent-browser:*)"],
|
||
|
|
}
|