PluginBench
Skill
Official
Review
Audit score 70

firecrawl-download

firecrawl/cli

Download entire websites as local markdown, screenshots, or multiple formats organized in directories.

What is firecrawl-download?

Firecrawl download combines site mapping and scraping to save complete websites locally. Use it when you need offline access to documentation, want to bulk-save pages as files, or need an organized local copy of a site.

  • Maps entire site to discover all pages, then scrapes each into nested local directories
  • Saves pages in multiple formats per file (markdown, links, HTML, etc.) with optional screenshots
  • Filters downloads by path patterns, search queries, or subdomain inclusion
  • Supports all scrape options including main-content-only, tag filtering, and language selection
  • Organizes output under `.firecrawl/` with per-page subdirectories for each format

How to install firecrawl-download

npx skills add null --skill firecrawl-download
Prerequisites
  • Firecrawl CLI installed and configured with API key
Claude Code
Cursor
Windsurf
Cline

How to use firecrawl-download

  1. 1.Run `firecrawl download <url>` with the website URL you want to save
  2. 2.Add `-y` flag to skip the confirmation prompt in automated workflows
  3. 3.Use `--limit <n>` to cap the number of pages downloaded
  4. 4.Use `--include-paths` and `--exclude-paths` to filter which sections to download (comma-separated)
  5. 5.Add `--screenshot` to capture visual snapshots of each page alongside content
  6. 6.Specify `--format markdown,links` or other formats to save multiple file types per page
  7. 7.Check `.firecrawl/` directory for organized output with nested folders per page

Use cases

Good for
  • Download documentation sites for offline reference or archival
  • Bulk extract a product's feature pages and SDK docs as local markdown files
  • Save a section of a website (e.g., `/features,/sdks`) while excluding translations
  • Create local snapshots of websites with screenshots for each page
  • Extract content from multiple pages into organized file structure for processing
Who it's for
  • Developers building tools that need offline content access
  • Documentation teams archiving or migrating site content
  • Researchers bulk-collecting web content for analysis
  • Anyone needing local backups of websites or documentation

firecrawl-download FAQ

What's the difference between download and crawl?

Download saves pages as local files (markdown, screenshots, HTML) in organized directories. Crawl extracts structured JSON data without creating local files.

Can I download only specific sections of a site?

Yes, use `--include-paths "/section1,/section2"` to download only matching paths, and `--exclude-paths` to skip sections like translations.

How do I get multiple formats per page?

Pass `--format markdown,links,html` to create separate files for each format. Each page gets its own subdirectory with all requested formats.

Do I need to confirm before downloading starts?

By default yes, but use `-y` flag to skip confirmation—required for automated/scripted workflows.

What happens with subdomains?

By default only the main domain is downloaded. Add `--allow-subdomains` to include pages from subdomains.

Full instructions (SKILL.md)

Source of truth, from firecrawl/cli.


name: firecrawl-download description: | Download an entire website as local files — markdown, screenshots, or multiple formats per page. Use this skill when the user wants to save a site locally, download documentation for offline use, bulk-save pages as files, or says "download the site", "save as local files", "offline copy", "download all the docs", or "save for reference". Combines site mapping and scraping into organized local directories. allowed-tools:

  • Bash(firecrawl *)
  • Bash(npx firecrawl *)

firecrawl download

Experimental. Convenience command that combines map + scrape to save an entire site as local files.

Maps the site first to discover pages, then scrapes each one into nested directories under .firecrawl/. All scrape options work with download. Always pass -y to skip the confirmation prompt.

When to use

  • You want to save an entire site (or section) to local files
  • You need offline access to documentation or content
  • Bulk content extraction with organized file structure

Quick start

# Interactive wizard (picks format, screenshots, paths for you)
firecrawl download https://docs.example.com

# With screenshots
firecrawl download https://docs.example.com --screenshot --limit 20 -y

# Multiple formats (each saved as its own file per page)
firecrawl download https://docs.example.com --format markdown,links --screenshot --limit 20 -y
# Creates per page: index.md + links.txt + screenshot.png

# Filter to specific sections
firecrawl download https://docs.example.com --include-paths "/features,/sdks"

# Skip translations
firecrawl download https://docs.example.com --exclude-paths "/zh,/ja,/fr,/es,/pt-BR"

# Full combo
firecrawl download https://docs.example.com \
  --include-paths "/features,/sdks" \
  --exclude-paths "/zh,/ja" \
  --only-main-content \
  --screenshot \
  -y

Download options

OptionDescription
--limit <n>Max pages to download
--search <query>Filter URLs by search query
--include-paths <paths>Only download matching paths
--exclude-paths <paths>Skip matching paths
--allow-subdomainsInclude subdomain pages
-ySkip confirmation prompt (always use in automated flows)

Scrape options (all work with download)

-f <formats>, -H, -S, --screenshot, --full-page-screenshot, --only-main-content, --include-tags, --exclude-tags, --wait-for, --max-age, --country, --languages

See also