From george-setup
Use when automating Chrome browser interactions, taking screenshots, filling forms, or verifying UI visually. Triggers on browser automation, take screenshot, screenshot page, fill form, click button, navigate to URL, Chrome DevTools, use_browser, visual verification, desktop and mobile screenshot, OAuth flow in browser, email verification flow, extract page content, DOM inspection, multi-tab browsing, form submit, CSS selector, headless Chrome, browser profile, login flow, signup flow.
How this skill is triggered — by the user, by Claude, or both
Slash command
/george-setup:browser-agentThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Control Chrome via DevTools Protocol using the `use_browser` MCP tool.
Control Chrome via DevTools Protocol using the use_browser MCP tool.
ToolSearch: select:mcp__plugin_superpowers-chrome_chrome__use_browser
action (required): Operation to performtab_index (optional): Tab to operate on (default: 0)selector (optional): CSS selector for element operationspayload (optional): Action-specific datatimeout (optional): Timeout in ms (default: 5000)| Category | Action | Key Params |
|---|---|---|
| Navigate | navigate | payload: URL |
| Wait | await_element | selector, timeout |
| Wait | await_text | payload: text string |
| Click | click | selector |
| Type | type | selector, payload (append \n to submit) |
| Select | select | selector, payload: option value |
| Extract | extract | payload: 'markdown'|'text'|'html', selector (opt) |
| Attribute | attr | selector, payload: attribute name |
| JS | eval | payload: JavaScript code |
| Screenshot | screenshot | payload: file path |
| Tabs | list_tabs, new_tab, close_tab | tab_index |
| Mode | show_browser, hide_browser, browser_mode | -- |
| Profile | set_profile, get_profile | payload: profile name |
{"action": "navigate", "payload": "https://example.com"}
{"action": "await_element", "selector": "button.submit"}
{"action": "click", "selector": "button.submit"}
{"action": "type", "selector": "input[name=email]", "payload": "[email protected]"}
{"action": "type", "selector": "input[name=password]", "payload": "pass123\n"}
{"action": "await_text", "payload": "Welcome"}
{"action": "extract", "payload": "html"} to inspect rendered DOM{"action": "navigate", "payload": "https://myapp.com"}
{"action": "await_element", "selector": "main"}
{"action": "screenshot", "payload": "/tmp/desktop.png"}
{"action": "eval", "payload": "window.innerWidth = 375; window.innerHeight = 812;"}
{"action": "screenshot", "payload": "/tmp/mobile.png"}
{"action": "new_tab"} then navigate to email provider{"action": "await_text", "payload": "verified"}{"action": "list_tabs"}
{"action": "extract", "tab_index": 1, "payload": "text", "selector": ".content"}
button[type=submit] not buttonJSON.stringify() to avoid [object Object]{"timeout": 30000}\n to payload to submit forms: "password\n"| This (use_browser MCP) | Playwright (webapp-testing skill) |
|---|---|
| Authenticated sessions | Fresh browser instances |
| Quick interactions | Full E2E test suites |
| Existing browser tabs | PDF generation pipelines |
| Simple form fills | Complex multi-step tests |
npx claudepluginhub george11642/george-plugins --plugin george-setupControls Chrome via DevTools Protocol for navigating, clicking, typing, multi-tab management, and content extraction with auto-screenshots.
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
Automates headless browser tasks with Vercel's agent-browser CLI: navigate URLs, snapshot interactive elements with refs (@e1), click/fill/type, scroll, test web pages.