Browser Automation

videodb helps you ingest video and audio from local files, URLs, RTSP/RTMP live feeds, or desktop capture; search moments with timestamps and playable evidence; and act with clips, overlays, transcription, alerts, and timeline editing. It is a practical videodb guide for VideoDB for Video Editing and live-stream analysis.

The e2e-testing skill is a Playwright-focused guide for stable end-to-end test automation, with patterns for file organization, Page Object Model usage, configuration, CI readiness, artifact debugging, and flaky-test handling.

data-scraper-agent helps build a repeatable public-data pipeline for web scraping, enrichment, and storage. It is designed for monitoring jobs, prices, news, repos, sports, and listings on a schedule using GitHub Actions, with outputs to Notion, Sheets, or Supabase. Best for ongoing tracking, not one-off extractions.

canary-watch is a post-deploy monitoring skill for checking a live URL for regressions after releases, merges, or dependency updates across staging or production.

browser-qa is a browser QA skill for post-deploy visual testing, interaction checks, responsive screenshots, and accessibility review using browser automation. It helps frontend developers and QA teams verify staging or preview pages with a repeatable browser-qa guide instead of a generic prompt.

automation-audit-ops is an evidence-first automation inventory and overlap audit skill for Workflow Automation. Use it to identify which jobs, hooks, connectors, MCP servers, or wrappers are live, broken, redundant, or missing before fixing anything.

webapp-testing is a skill for testing local web apps with Python Playwright. It helps agents start servers with scripts/with_server.py, inspect rendered UI, discover selectors, capture screenshots and console logs, and validate frontend behavior with a reconnaissance-first workflow.

browse is a fast headless browser skill for QA, dogfooding, and browser automation. Use it to open pages, interact with elements, verify state, compare before and after actions, capture screenshots, and check responsive layouts, forms, uploads, dialogs, and element states. Install browse when you need browser evidence instead of a generic prompt.

remote-browser helps sandboxed agents control a headless browser for Browser Automation. Use it to open pages, inspect state, click indexed elements, type input, take screenshots, and connect to local apps or CDP-backed browser sessions.

browser-use is a browser automation skill for opening pages, inspecting state, clicking indexed elements, typing into fields, taking screenshots, and reusing a persistent browser session. Use it for reliable form filling, navigation, and logged-in workflows with the browser-use CLI.

The cloud skill helps you install and use Browser Use Cloud for Browser Automation, including quickstart setup, v2 and v3 APIs, SDK usage, sessions, profiles, CDP connections, proxies, webhooks, and live monitoring.

browser-testing-with-devtools helps agents test and debug real browser behavior through Chrome DevTools MCP. Use it to inspect the DOM, capture console errors, analyze network requests, profile performance, and verify fixes in a live browser.

baoyu-post-to-x automates posting to X with real Chrome and CDP. Publish text, images, videos, quote posts, and Markdown-based X Articles using bun scripts, preview mode, and browser-based execution.

playwright-cli is a browser automation skill for Playwright from the command line. It helps with opening pages, inspecting elements, clicking through flows, filling forms, capturing screenshots, mocking requests, and generating test code from real interactions. Use it for repeatable browser automation and UI testing.

claude-in-chrome-troubleshooting helps diagnose and fix Claude in Chrome MCP connectivity issues on macOS. Use it when mcp__claude-in-chrome__* tools fail, the browser extension says “Browser extension is not connected,” or browser automation becomes flaky after an update or app switch. This skill is a practical repair guide for Claude Code and Claude.app conflicts.

burpsuite-project-parser searches and extracts data from Burp Suite project files (.burp) using Burp Suite Professional and the burpsuite-project-file-parser extension. Use it for security audit findings, proxy history, site map entries, and regex searches across captured HTTP traffic.

multi-search-engine is a web research skill with 17 search engines, advanced operators, time filters, privacy-focused options, and WolframAlpha queries. It helps agents build and run better search URLs without API keys.

web-access is a skill for live web work, combining search, page fetch, raw HTML inspection, and Chrome CDP browser automation for dynamic, login-gated, and interactive sites.

web-to-markdown is a Format Conversion skill that turns live web pages into clean Markdown through the local web2md CLI, using a Chromium-family browser for JS-rendered pages, interactive flows, and batch URL conversion. It only runs when explicitly invoked by name.

playwright-testing skill for writing and debugging Playwright end-to-end tests with page objects, cross-browser runs, CI-friendly setup, auth handling, and stable test structure.

Use the windows-vm skill to create, manage, and SSH into a headless Windows 11 VM in Docker with KVM acceleration. It fits desktop automation, Windows app setup, and repeatable agent workflows when you need a real Windows environment without manual RDP.

firecrawl-browser is a Firecrawl skill for interactive web automation. It is deprecated as a standalone browser command and now guides users to use firecrawl scrape plus firecrawl interact for clicks, forms, login flows, pagination, and JavaScript-heavy pages.

firecrawl skill for installing, authenticating, and using the official Firecrawl CLI for web scraping, search, crawling, and page interaction. Learn setup, `firecrawl --status`, login, safe file output to `.firecrawl/`, and practical usage patterns backed by the repo.

firecrawl-crawl helps agents bulk extract content from a website or docs section with path filters, depth limits, page caps, wait mode, and job status checks.