skills.rest
ZJU-REAL
ZJU-REALOFFICIAL
Explore all skills by this author →
GitHub

firecrawl-scrape

Extract clean Markdown content from webpages and JavaScript-rendered applications via Firecrawl CLI.

195|12|Updated Jul 19, 2026
Search Tags:#markdown#firecrawl#web research#web scraping#content retrieval#javascript rendering#url extraction
One-click install
npx skills add https://github.com/ZJU-REAL/HugAgentOS --skill firecrawl-scrape-zju-real
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: firecrawl-scrape
Source: https://github.com/ZJU-REAL/HugAgentOS/tree/main/src/backend/plugin_bundles/marketplace/firecrawl/skills/scrape
Command: npx skills add https://github.com/ZJU-REAL/HugAgentOS --skill firecrawl-scrape-zju-real

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the difficulty of extracting reliable content from webpages, including JavaScript-rendered applications, by converting URLs into clean, LLM-optimized Markdown.

Core Features & Use Cases

  • Webpage Extraction: Retrieve readable Markdown from static pages and JavaScript-rendered SPAs.
  • Flexible Scraping: Extract main content, links, HTML, screenshots, or structured responses with configurable wait times and tag filters.
  • Multi-URL Workflows: Scrape multiple URLs concurrently for research, documentation, monitoring, and content analysis.
  • Use Case: Provide a set of product documentation URLs to collect their main content into Markdown files for analysis or summarization.

Quick Start

Use the firecrawl scrape skill to extract the main content from the provided webpage and save it as clean Markdown.

Frequently Asked Questions about firecrawl-scrape

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

FAQPage Schema
How do I extract clean markdown from a webpage that requires JavaScript rendering?▼

To extract clean markdown from a webpage requiring JavaScript rendering, this Skill processes URLs through the Firecrawl CLI to handle SPAs and convert the rendered content into LLM-optimized Markdown.

Can I scrape multiple URLs concurrently for web research?▼

Yes, you can scrape multiple URLs concurrently for web research. This Skill supports concurrent multi-page scraping workflows to retrieve documentation and content simultaneously.

What is the best way to retrieve main content and exclude navigation links during web scraping?▼

The best way to retrieve main content during web scraping is by applying configurable main-content filtering and tag filters, which isolates the readable text and excludes irrelevant navigation links.

Does this web scraping approach support extracting links and screenshots alongside markdown?▼

Yes, this web scraping approach supports extracting links and screenshots alongside markdown. You can configure the output formats to include HTML, URL extraction, and image captures.

How do I handle content retrieval from dynamic pages with slow loading elements?▼

To handle content retrieval from dynamic pages with slow loading elements, you can configure specific rendering wait times within the scraping parameters to ensure all JavaScript applications fully load.

Related Skills

Explore More Content & Communication Skills→
olostepolostep

batch

Scrape up to 10,000 URLs in parallel with configurable output formats.

Community
Intermediate
PavelHopsonPavelHopson
1

eclipse-claw

Fetch and extract structured data from bot-protected URLs.

Community
Advanced
brandon-frysliebrandon-fryslie
4

firecrawl-scrape

Extract markdown content from web URLs, including JavaScript-rendered pages.

Community
Advanced
daanteijema-beepdaanteijema-beep

firecrawl-scrape

Extract clean markdown from static and JavaScript-rendered URLs.

Community
Intermediate