Web, Search & Scraping Agent Skills for Claude Desktop

Use this skill to automate visual testing and UI interaction verification using browser automation after deploying features.

Execute Bright Data production deployment checklist and rollback procedures.

Scrape web content as clean markdown/HTML/JSON via the Bright Data CLI (`bdata scrape`).

Automate Brightdata tasks via Rube MCP (Composio).

Fast headless browser for QA testing and site dogfooding. (gstack)

Automate Browseai tasks via Rube MCP (Composio).

Inject the cmux browser annotation overlay (draw, highlight DOM elements, copy selectors) into active cmux browser surfaces.

Use when the user asks to automate browser tasks, scrape websites, fill

Browser automation — navigate, click, fill, snapshot web pages.

Site-specific browser playbooks (domain-skills, interaction-skills) for Naver, GitHub, etc.

Use when opening or verifying any web page in Hermes.

Open a named, traced browser session into an RVF cognitive container with a ruvector trajectory recording every action

Record browser sessions using Playwright for web UI tutorials, converts

Automated browser testing and debugging using Browser DevTools MCP.

Automate Browser Tool tasks via Rube MCP (Composio).

Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.

Migrate browser-use (Python) browser-automation scripts to Stagehand v3 (TypeScript) on Browserbase.

Recon-first browser automation. Orchestrator explores the site first via chromux, saves a guide file with insights, then delegates…

Executes browser-based user workflows from /workflows/browser-workflows.md using Claude-in-Chrome MCP.

Use this skill when the user wants to retrieve a URL without a full browser session: fetch HTML or JSON from static pages, inspect status…

Automate Browserbase Tool tasks via Rube MCP (Composio).