firecrawl-download

Downloads websites as local markdown files and screenshots using the Firecrawl CLI.

Updated Aug 20, 2026

Search Tags:#markdown #screenshots #cli #firecrawl #web scraping #download #offline docs

Ready to run

npx skills add https://github.com/bittlinkm/claude-setup --skill firecrawl-download-bittlinkm

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: firecrawl-download
Source: https://github.com/bittlinkm/claude-setup/tree/main/skills/firecrawl-download
Command: npx skills add https://github.com/bittlinkm/claude-setup --skill firecrawl-download-bittlinkm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It saves an entire website or a specific section as local files (markdown, links, screenshots) so you can keep offline documentation or a local reference copy without manually scraping each page. ## Core Features & Use Cases - Site-wide download: Maps the site origin to discover pages, then scrapes each one into nested directories under `.firecrawl/`. - Multiple output formats: Saves markdown, link lists, and screenshots as separate files per page. - Path filtering: Uses `--include-paths` and `--exclude-paths` to scope downloads to specific sections or skip translations. - Use Case: Download a product's documentation site with screenshots to build an offline, searchable local copy of the docs for reference while working without internet access. ## Quick Start Ask the assistant to download a documentation site locally with screenshots, for example by requesting to save https://docs.example.com as local markdown files using firecrawl download.

Frequently Asked Questions about firecrawl-download

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

FAQPage Schema

How do I download a website as local markdown files?▼

Run firecrawl x download with the site URL, for example firecrawl x download https://docs.example.com --screenshot --limit 20 -y. The command maps the site, scrapes each page, and saves files into nested directories under .firecrawl/.

How do I download only one section of a documentation site?▼

Use the --include-paths flag to scope the download, such as --include-paths "/features,/sdks". You can also use --exclude-paths to skip sections like translated pages, for example --exclude-paths "/zh,/ja,/fr".

Does firecrawl download require an API key or login?▼

Yes, the download command requires authentication and has no keyless free tier. Without credentials, the CLI prompts an interactive login before it can proceed.

Why does firecrawl download hang or block during automated runs?▼

Without the -y flag, the command opens an interactive wizard that waits on a prompt. Always pass -y in automated or scripted runs so the command executes non-interactively.

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

Download saves pages as local files (markdown, screenshots) under .firecrawl/. Scrape handles individual pages, while crawl bulk-extracts content as JSON rather than writing local files.