firecrawl-download

Downloads entire websites as local markdown, screenshot, and multi-format files.

Updated Apr 18, 2026
One-click install
npx skills add https://github.com/webdevarif/claude-skills --skill firecrawl-download-webdevarif
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: firecrawl-download
Source: https://github.com/webdevarif/claude-skills/tree/main/firecrawl-download
Command: npx skills add https://github.com/webdevarif/claude-skills --skill firecrawl-download-webdevarif

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Saving an entire website or documentation set for offline use normally requires manually visiting and copying each page. This Skill automates that by mapping a site's URLs and scraping every page into organized local directories under .firecrawl/. ## Core Features & Use Cases - Full-site download: Combines site mapping and scraping to save every discovered page as local files in nested directories. - Multiple output formats per page: Save markdown, links, and screenshots as separate files for each page (e.g., index.md + links.txt + screenshot.png). - Path filtering: Include or exclude specific URL paths, such as downloading only /features and /sdks while skipping translated versions like /zh or /ja. - Use Case: You need offline access to a product's documentation before a flight. Run the download command with a page limit and screenshots enabled, and the entire docs site is saved locally in an organized folder structure. ## Quick Start Ask the AI to download https://docs.example.com as local markdown files with screenshots, limited to 20 pages, using the firecrawl download command.

Frequently Asked Questions about firecrawl-download

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

FAQPage Schema
How do I download an entire website as local files?

Run firecrawl download followed by the site URL, for example firecrawl download https://docs.example.com. It maps the site to discover pages, then scrapes each one into nested directories under .firecrawl/. Always pass -y to skip the confirmation prompt in automated flows.

How to save website pages as markdown with screenshots?

Use the --screenshot flag together with --format to control output, such as firecrawl download URL --format markdown,links --screenshot. Each page then produces separate files: index.md, links.txt, and screenshot.png.

Can I download only specific sections of a website?

Yes, use --include-paths to limit downloads to matching paths like /features or /sdks, and --exclude-paths to skip sections such as translated pages (/zh, /ja). You can also set --limit to cap the number of pages.

What is the difference between firecrawl download, crawl, and scrape?

Download saves pages as local files in directories, crawl extracts bulk content as JSON rather than local files, and scrape handles individual pages. Map only discovers URLs without downloading any content.

Does firecrawl download work with subdomains?

Subdomain pages are excluded by default. Pass the --allow-subdomains flag to include pages from subdomains of the target site in the download.