scrape

Orchestrate Firecrawl, Apify, and APIs to extract structured web data.

1|Updated Jun 16, 2026
One-click install
npx skills add https://github.com/Mattyreed1/fractal-agent-skills --skill scrape-mattyreed1
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: scrape
Source: https://github.com/Mattyreed1/fractal-agent-skills/tree/main/scrape
Command: npx skills add https://github.com/Mattyreed1/fractal-agent-skills --skill scrape-mattyreed1

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires firecrawl-mcp, @apify/mcpc, youtube-transcript-api, and includes references (resource) components.

What problem does it solve?

This skill solves the challenge of extracting structured data from complex, anti-bot protected, or JavaScript-heavy websites by providing a robust, multi-layered execution strategy.

Core Features & Use Cases

  • Multi-Method Extraction: Orchestrates Firecrawl for LLM-ready content, Apify for high-scale or protected targets, and direct API calls for public JSON endpoints.
  • Lead Enrichment: Automates professional background research by combining Firecrawl Agent, Perplexity, and web search to build comprehensive contact profiles.
  • Use Case: When you need to research a list of LinkedIn profiles for meeting prep, this skill automatically navigates auth walls, aggregates career history and company intel, and formats the data for your CRM.

Quick Start

Use the scrape skill to research the LinkedIn profile at the provided URL and enrich the contact with company background and recent activity.

Frequently Asked Questions about scrape

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
What is the best way to extract web data from JavaScript-heavy or anti-bot protected websites?

Web data extraction from anti-bot protected or JavaScript-heavy sites is handled by orchestrating Firecrawl for LLM-ready content and Apify for high-scale targets, ensuring reliable structured extraction without triggering blocks.

How do I automate lead enrichment using LinkedIn profiles for meeting prep?

Lead enrichment automates professional background research by combining Firecrawl Agent, Perplexity, and web search to build comprehensive contact profiles, navigating authentication walls to aggregate career history and format company intelligence for CRM integration.

Can I use Firecrawl and Apify together in a single scraping pipeline?

Firecrawl and Apify are orchestrated together within a multi-layered execution strategy, where Firecrawl extracts LLM-ready content while Apify handles high-scale or protected targets to enable complex multi-source research workflows.

Does this web scraping approach support direct API calls for public JSON endpoints?

The extraction strategy includes direct API integrations for public JSON endpoints alongside Firecrawl and Apify orchestration, providing a multi-method approach to satisfy high-fidelity data extraction requirements.

When do I need production-grade pipelines for web scraping and data extraction?

Production-grade pipelines are needed for scalable web scraping tasks involving anti-bot protection, JavaScript rendering, and multi-source research workflows, ensuring high-fidelity data extraction and automated browser interaction at scale.

What are the limitations of relying solely on Firecrawl for web scraping?

Relying only on Firecrawl limits extraction when facing high-scale or heavily protected targets, where orchestration with Apify and direct API calls provides a robust multi-layered strategy to overcome complex anti-bot protections.