skills.rest
webdevarif
webdevarifCOMMUNITY
Explore all skills by this author →
Website𝕏@webdevarifGitHub

firecrawl-scrape

Extract clean markdown from URLs including JavaScript-rendered single-page applications.

Updated Apr 18, 2026
Search Tags:#firecrawl#web scraping#content extraction#spa#javascript rendering#url scraping#markdown extraction
One-click install
npx skills add https://github.com/webdevarif/claude-skills --skill firecrawl-scrape-webdevarif
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: firecrawl-scrape
Source: https://github.com/webdevarif/claude-skills/tree/main/firecrawl-scrape
Command: npx skills add https://github.com/webdevarif/claude-skills --skill firecrawl-scrape-webdevarif

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Fetching webpage content often fails on JavaScript-rendered pages or returns cluttered HTML full of navigation and boilerplate. This Skill converts any URL into clean, LLM-optimized markdown ready for reading, searching, or analysis. ## Core Features & Use Cases - Markdown Extraction: Scrape one or more URLs concurrently and save clean markdown output to local files. - JS Rendering Support: Handle single-page applications by waiting for JavaScript to render before extraction. - Content Filtering: Strip nav, footer, and sidebar with --only-main-content, or include/exclude specific HTML tags. - Use Case: You need to research a competitor's documentation spread across several pages. Scrape all URLs concurrently into .firecrawl/ as markdown files, then grep and read them locally. ## Quick Start Ask the AI to scrape a specific URL with firecrawl and save the main content as markdown to a local file.

Frequently Asked Questions about firecrawl-scrape

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

FAQPage Schema
How do I scrape a webpage and get clean markdown?▼

Run firecrawl scrape with the URL and an output path, such as firecrawl scrape "<url>" -o .firecrawl/page.md. Add --only-main-content to strip navigation, footers, and sidebars so only the main content is saved.

How to scrape JavaScript-rendered pages or SPAs?▼

Use the --wait-for option to delay extraction until JavaScript finishes rendering, for example firecrawl scrape "<url>" --wait-for 3000. Firecrawl handles JS-rendered single-page applications without extra configuration.

Can I scrape multiple URLs at once with firecrawl?▼

Yes, pass multiple URLs to a single firecrawl scrape command and they are scraped concurrently, with each saved to the .firecrawl/ directory. Check firecrawl --status to see your account's concurrency limit.

When should I use scrape instead of interact or crawl?▼

Use scrape when you have a specific URL and only need its content, whether static or JS-rendered. Escalate to interact only when you need clicks, form fills, or pagination, and use crawl or download for entire sites.

What output formats does firecrawl scrape support?▼

Supported formats include markdown, html, rawHtml, links, screenshot, and json via the --format option. A single format outputs raw content, while multiple formats such as markdown,links produce JSON output.

Related Skills

Explore More Software Engineering Skills→
The-Focus-AIThe-Focus-AI

firecrawl-map

Discover and list all URLs on a website using the Firecrawl CLI.

Official
Basic
kreuzberg-devkreuzberg-dev
9.2k

chunking

Split extracted text into sized chunks for LLM context windows and RAG ingestion.

Official
Intermediate
ovisanovisan
2

firecrawl-download

Downloads entire websites as local markdown, screenshot, and link files via Firecrawl.

Community
Basic
firecrawlfirecrawl
616

firecrawl-interact

Drive a live browser session to click, fill forms, and extract data from scraped pages.

Official
Intermediate