Web, Search & Scraping Agent Skills for DeepSeek Harness

Export a Reveal.js HTML presentation to a pixel-perfect PDF using Chrome CDP (no Puppeteer/Playwright dependency).

Deterministic deep research via RivalSearchMCP. 9 tools: 5-engine web search (DuckDuckGo/Bing/Yahoo/Mojeek/Wikipedia), 9-platform social…

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

This skill should be used when the user asks to "research a topic", "run-research", "last30", "what's happening with X", "what are people…

Run the WebBench browser agent benchmark — main entry point and orchestrator.

Web search and external knowledge lookup.

Automates complex web browser interactions and data extraction using the Vercel Agent Browser CLI.

Reference system prompt and tool schemas for Same.dev.

Expert capability for robust, stealthy, and efficient browser automation using Playwright Go.

Diagnose and fix Claude in Chrome MCP extension connectivity issues.

Automate cloud browsers using the Scrapfly Cloud Browser API with Python Playwright

Use the Scrapfly RPA API to run typed workflow graphs against managed cloud browsers, retrieve produced artifacts (HTML snapshots…

Capture web page screenshots using the Scrapfly Screenshot API with the Python SDK

Automate Scrapingant tasks via Rube MCP (Composio).

ScrapingDog integration. Manage data, records, and automate workflows. Use when the user wants to interact with ScrapingDog data.

Fetch websites and extract structured data with Scrapling for research and agency workflows.

Use when creating automated screen recordings, demo videos, or visual documentation of browser-based features.

This snippet should be used when reading, organizing, and naming screenshots with date prefixes.

Browser automation with Puppeteer CLI scripts.

Use when the user wants to SEE the browser act — visible Chrome window with mouse movements, clicks, scrolling.

Automate Serpapi tasks via Rube MCP (Composio).