Browser Automation

Browser-use automates browser interactions for web testing, form filling, screenshots, and data extraction. It provides a persistent browser session CLI that supports headless Chromium, real Chrome with login sessions, and cloud-hosted browsers for complex multi-step web automation workflows.

This skill provides a complete toolkit for testing local web applications using Playwright. It includes helper scripts for managing server lifecycles, capturing browser console logs, discovering page elements, and automating interactions with both dynamic web apps and static HTML files.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Agent Browser automates browser interactions through a CLI interface. It can navigate websites, fill forms, take screenshots, extract content, record videos, and manage authentication sessions. The skill uses a ref-based element targeting system for efficient AI agent interaction.

Agent Browser provides instructions for using Vercel's agent-browser CLI tool for headless browser automation. It enables web page interaction including navigation, form filling, clicking elements, taking screenshots, and scraping data using ref-based element selection from accessibility snapshots.

Use this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded, citation-backed answers from Gemini. Browser automation, library management, persistent auth. Drastically reduced hallucinations through document-only responses.

Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.

BrowserWing Executor enables browser automation through a comprehensive HTTP API. It provides capabilities for page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshots, and JavaScript execution. The skill integrates with AI tools via MCP and Skills protocols.

This skill automates downloading books from Anna's Archive and uploading them to Google NotebookLM for AI-powered reading. It uses browser automation to navigate download pages, extract files, and handle format conversion automatically. While it includes a legal disclaimer, its primary use case involves accessing copyrighted materials.