Automate browser interactions for AI agents to navigate, fill forms, and extract data.
npx skills add https://github.com/kevinslin/skills --skill agent-browser-kevinslin
Please help me install this Agent Skill. Skill: agent-browser Source: https://github.com/kevinslin/skills/tree/main/active/agent-browser Command: npx skills add https://github.com/kevinslin/skills --skill agent-browser-kevinslin
Browser automation for AI agents enables programmatic control of web tasks such as navigation, form filling, data extraction, and testing across sites.
Open a target webpage with agent-browser, snapshot the page to generate element refs, then fill fields and perform actions using those refs.
High-intent search queries and answers about installing and using this skill.
Browser automation for AI agents enables programmatic control of web tasks such as navigation, form filling, and data extraction. You can open URLs, snapshot pages to identify element refs, and execute interactive actions like clicks and inputs using those refs.
Automated login flows for protected sites are a primary use case. You navigate to the login page, snapshot the form fields to generate element refs, fill credentials using those refs, and then extract mass data from the authenticated dashboard.
End-to-end UI testing of web applications is supported by navigating to target URLs, snapshotting pages to capture element refs, and executing interactive actions like click, fill, and wait commands to verify application behavior and capture content.
Session isolation for parallel workflows is fully supported. This allows multiple browser automation tasks to run concurrently without interfering with each other, enabling efficient mass data extraction and independent UI testing simultaneously.
Content capture during web automation allows you to extract text, URLs, screenshots, and PDFs from pages. After navigating to a target URL and snapshotting the page, you can capture both data and visuals from the current state.
Browser automation for AI agents operates without external dependencies. It independently handles open, snapshot, click, fill, and wait commands, ref-based interactions, session isolation, and content capture directly within its environment.
Fl2vioAutomate web browser tasks using AI-optimized snapshots and element refs.
jleechanorgExtract text, Markdown, tables, and images from PDFs and scans.
vuxsoul-uiAutomate headless browser tasks using accessibility snapshots and ref-based element selection.
johnlindquistAutomate browser interactions for web testing and data extraction with Puppeteer or Playwright.
