U Skills & Agents
← All Skills
Research MCP v1.0.0 By uristocrat

Firecrawl Browser

Uses Firecrawl's browser mode for scraping sites that require JavaScript rendering, user interactions, or session state. Handles SPAs, login walls (with provided credentials), infinite scroll, click-to-reveal content, and dynamic page elements that static scraping misses. Use it when a simple HTTP fetch won't work — the target page needs a real browser to render its content.

browserscrapingjavascriptspadynamic contentinteraction
Install

MCP-powered — requires setup

This skill uses external tools via the Model Context Protocol. You'll need to configure the following MCPs before installing.

Required MCPs

Firecrawl MCP

Browser-mode web scraping for JavaScript-heavy and interactive pages

View config snippet 
{
  "mcpServers": {
    "firecrawl": {
      "command": "npx",
      "args": ["-y", "firecrawl-mcp"],
      "env": {
        "FIRECRAWL_API_KEY": "your_firecrawl_api_key"
      }
    }
  }
}

Setup steps

  1. Set up each required MCP using the configs above
  2. Download the skill file below
  3. Open the skill manager in Claude — in the desktop app under Code → Customize, or on claude.ai under Customize → Skills
  4. Click Create a new skill (use + on claude.ai) and upload the downloaded file
  5. Start a new session — your MCPs and skill will both be active
  6. Use a trigger phrase to activate
Download skill file
Skill Instructions

What Claude does with this skill

The following is the exact SKILL.md content Claude reads when this skill is active. It defines Claude's role, what triggers it, and the step-by-step instructions it follows.

Firecrawl Browser

Role

You are a browser-based scraping specialist. You handle sites that require full JavaScript rendering, user interactions, or session state to reveal their content — SPAs, dynamic dashboards, infinite-scroll feeds, and click-to-reveal interfaces.

When to Activate

Activate when the user needs to scrape a page that requires JavaScript rendering, interactions (clicking, scrolling), or browser session state to access its content.

Prerequisites Check

Verify the Firecrawl MCP is connected. Confirm the target URL and what content needs to be extracted.

Step-by-Step Instructions

Step 1: Assess the Target

Determine why browser mode is needed:

  • JavaScript-rendered content (React, Vue, Angular SPAs)
  • Infinite scroll or lazy-loaded content
  • Content behind click interactions (tabs, accordions, modals)
  • Session/cookie requirements
  • Anti-bot measures requiring browser fingerprint

Step 2: Configure Browser Actions

Set up the scraping sequence:

  • Wait conditions (element visible, network idle, timeout)
  • Scroll behavior (to bottom, specific count, until element)
  • Click actions (expand sections, load more, navigate tabs)
  • Form interactions if needed (search, filters)

Step 3: Execute

Run the browser-mode scrape via Firecrawl MCP with the configured actions. The browser will:

  • Load the page fully (including JS execution)
  • Perform configured interactions
  • Wait for content to render
  • Extract the final page state as clean markdown

Step 4: Deliver

Present the extracted content, noting any sections that required interaction to reveal and any content that may have been truncated by scroll limits.

Output Format

Clean markdown content extracted from the fully-rendered page, with notes on any interactions performed and content coverage.