Control browser, automate browser interactions, navigate to URLs, click on webpages, fill forms, take screenshots, inspect webpages, web scraping with browser, test websites manually, or interact with web pages programmatically using ATR browser server mode.
Automates browser interactions including navigation, clicking, form filling, and capturing screenshots.
/plugin marketplace add imyousuf/agentic-test-runner/plugin install atr-skills@atr-marketplaceThis skill is limited to using the following tools:
references/commands-reference.mdThis skill provides browser automation capabilities through ATR's browser server mode. The browser server runs as a daemon process and accepts CLI commands for browser control.
Claude Code --> atr CLI (client) --> ATR Server + Browser
The browser runs in visible (non-headless) mode by default for debugging and verification.
Before any browser operations, verify the browser server is running:
atr browser status
If the server is not running, start it:
atr browser start
The server stores state at ~/.atr/browser.state which allows subsequent commands to discover the endpoint automatically.
Once running, use navigation and interaction commands to control the browser.
| Command | Description |
|---|---|
atr browser start [--port PORT] | Start browser daemon (default port: 9333) |
atr browser stop | Stop browser daemon |
atr browser status | Check if browser is running |
| Command | Description |
|---|---|
atr browser navigate <url> | Navigate to URL |
atr browser back | Go back in history |
atr browser forward | Go forward in history |
atr browser reload | Reload current page |
| Command | Description |
|---|---|
atr browser new-page [url] | Open new tab |
atr browser list-pages | List all tabs |
atr browser select-page <index> | Switch to tab (0-based) |
atr browser close-page <index> | Close tab |
| Command | Description |
|---|---|
atr browser click <target> [--double] | Click element (use --double for double-click) |
atr browser fill <target> <value> | Type into input field |
atr browser hover <target> | Hover over element |
atr browser press-key <key> | Press keyboard key (e.g., Enter, Tab, Control+A) |
atr browser drag <from> <to> | Drag element |
| Command | Description |
|---|---|
atr browser snapshot [--verbose] | Get page elements with UIDs |
atr browser screenshot --file [--full] | Capture screenshot (saves to /tmp/) |
atr browser html | Get page HTML |
atr browser url | Get current URL |
atr browser title | Get page title |
atr browser eval <script> | Execute JavaScript |
Screenshot Note: Use --file to save screenshots to /tmp/ with a timestamped filename (e.g., /tmp/atr-screenshot-20240105-103045.png). No need to specify a file path. Add --full for full-page screenshots. Without --file, returns base64-encoded image data.
| Command | Description |
|---|---|
atr browser console [--limit N] | Get console messages (default: 50) |
atr browser network [--limit N] | Get network requests (default: 50) |
atr browser errors | Get failed requests |
Follow this workflow for browser automation tasks:
Ensure Server Running
atr browser status || atr browser start
Navigate to Target
atr browser navigate https://example.com
Inspect Page Elements
atr browser snapshot
This returns elements with unique IDs (UIDs) like e0, e1, etc.
Interact with Elements Target elements by:
"Sign In"e5.submit-buttonVerify Results
atr browser url
atr browser title
atr browser screenshot --file
Cleanup When Done
atr browser stop
Add --json flag for structured output when parsing is needed:
atr browser snapshot --json
atr browser list-pages --json
atr browser network --json
The <target> parameter in click, fill, hover, and drag commands accepts:
e0, e5 (from snapshot output)"Sign In", "Submit Form"#login-button, .nav-linkBest practice: Use atr browser snapshot first to see available elements and their UIDs.
For press-key command:
Enter, Tab, Escape, BackspaceControl+a, Shift+Tab, Alt+EnterArrowUp, ArrowDown, ArrowLeft, ArrowRightBrowser won't start:
atr browser status
rm ~/.atr/browser.state # If stale state
atr browser start
Port already in use:
atr browser start --port 9334
Element not found:
atr browser snapshot --verbose --json
For complete command reference with all flags, see references/commands-reference.md.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.