Automate browser navigation and UI interactions with Chromium or Google Chrome.
npx skills add https://github.com/openbotx/openbotx --skill browser-openbotx
Please help me install this Agent Skill. Skill: browser Source: https://github.com/openbotx/openbotx/tree/main/openbotx/skills/browser Command: npx skills add https://github.com/openbotx/openbotx --skill browser-openbotx
Automates browser interactions to perform tasks that require a real browser context such as scraping rendered content, interacting with dynamic UIs, capturing screenshots, and testing web flows without manual browsing.
Navigate to https://example.com, inspect the page to find the login form selectors, type the username and password into the appropriate fields, press Enter, wait 2 seconds, and then snapshot the page to extract the rendered text.
High-intent search queries and answers about installing and using this skill.
To automate web scraping for JavaScript-rendered pages, you navigate to a URL and use actions like evaluate or snapshot to extract the fully rendered DOM content. This approach captures text generated by dynamic UIs that standard HTTP requests miss.
Yes, you can capture screenshots for end-to-end UI testing using headless Chrome. The tool supports capturing visual snapshots during automated web flows, allowing you to verify UI interactions and page states without launching a visible browser window.
To run browser automation tasks for form submission, you need a Chromium or Google Chrome binary installed on your host system. Once configured, you navigate to the page, inspect for selectors, type into fields, and press keys to submit.
You find CSS selectors during web automation by using the inspect action. It discovers interactive elements on the page, allowing you to identify the correct input fields or buttons before executing click or type actions.
Yes, this tool supports executing custom JavaScript during web scraping flows via the evaluate action. You can run custom scripts in the browser context to manipulate the DOM or extract specific data from rendered pages.
Limitations when taking snapshots of dynamic web pages include a configurable max snapshot size and the need for explicit wait actions. You must configure wait times to ensure dynamic content fully loads before extracting the rendered DOM text.
tysonthomas9Run agent-browser with headless Chrome inside ephemeral Vercel Sandbox microVMs.
jackandkingScrape Kuaishou Creator Platform task lists and performance statistics with CSV/JSON export.
Casper-StudiosAutomate browser interactions for web testing and data scraping.
otrebuBatch-convert JavaScript-rendered web pages to a timestamped Markdown file.
