skills.rest
iAziz786
iAziz786COMMUNITY
Explore all skills by this author →
Website𝕏@iAziz786GitHub

firecrawl-scrape

Extract clean Markdown from static and JavaScript-rendered URLs via self-hosted Firecrawl.

3|Updated Jul 5, 2021
Search Tags:#automation#markdown#cli#firecrawl#urls#web-scrape#js-rendering
One-click install
npx skills add https://github.com/iAziz786/dotfiles --skill firecrawl-scrape-iaziz786
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: firecrawl-scrape
Source: https://github.com/iAziz786/dotfiles/tree/main/.agents/skills/firecrawl-scrape
Command: npx skills add https://github.com/iAziz786/dotfiles --skill firecrawl-scrape-iaziz786

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Extract clean Markdown content from arbitrary URLs using a self-hosted Firecrawl instance at localhost:3002, enabling fast, readable outputs for downstream reasoning and knowledge capture.

Core Features & Use Cases

  • Handles static pages and JavaScript-rendered pages (SPA) and returns LLM-optimized Markdown.
  • Supports simultaneous scraping of multiple URLs with per-page outputs saved locally.
  • Ideal for knowledge-base creation, research summaries, and content curation workflows.

Quick Start

Run firecrawl scrape "<url>" -o path/to/output.md to generate Markdown for a single page.

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 web pages that require JavaScript rendering?▼

You can extract clean Markdown from JavaScript-rendered pages by running a self-hosted Firecrawl instance locally. It processes static and SPA pages concurrently and returns LLM-optimized Markdown outputs for downstream use.

Can I scrape multiple URLs concurrently and save the Markdown outputs locally?▼

Yes, you can scrape multiple URLs concurrently using the Firecrawl CLI. It supports simultaneous web-scraping with per-page Markdown outputs saved directly to local file paths for your knowledge-base workflows.

Do I need a local Firecrawl instance running to use this web scraping tool?▼

Yes, you need a self-hosted Firecrawl instance running at localhost:3002. The Skill invokes the scraping process locally via Bash commands like firecrawl scrape to ensure fast and private content extraction.

What is the best way to convert website content into LLM-optimized Markdown for research summaries?▼

The best way to convert website content into LLM-optimized Markdown is using a local Firecrawl instance. It handles arbitrary URLs, parses static and dynamic content, and outputs clean Markdown ideal for research and content curation.

How do I scrape a single URL and output the result to a specific Markdown file?▼

Run the command firecrawl scrape "<url>" -o path/to/output.md in your CLI. This invokes the local Firecrawl instance to extract the web page content and save the clean Markdown directly to your specified path.

Related Skills

Explore More Software Engineering Skills→
iAziz786iAziz786
3

firecrawl-search

Search via self-hosted Firecrawl and extract full-page content from results.

Community
Intermediate
Lucius646Lucius646

karpathy-llm-wiki

Manage Markdown-based knowledge bases with LLM-driven ingestion, querying, and maintenance.

Community
Intermediate
ironkid90ironkid90

firecrawl-scrape

Extract clean markdown from JavaScript-rendered URLs for LLM inputs.

Community
Advanced
stephanjstephanj
9

web-to-markdown

Convert JavaScript-rendered web pages into structured Markdown files.

Community
Intermediate