skilld
All skills
firecrawl avatar

/firecrawl-download

@509dd9c official
by firecrawlfirecrawl/cli643 stars
110

Save a site or section as local files (markdown, screenshots). Use for "download the site", offline docs, or a local copy for reference.

Ask your Agent

Use this Skill: https://skilld.dev/gh/firecrawl/cli/firecrawl-download

This session only. Nothing lands on disk.

SKILL.md

≈39 tokens always: the name and description. ≈446 when used: this file.

firecrawl download (invoked as firecrawl x download)

Experimental. download is available under the firecrawl x command group.

Prerequisite: download requires authentication (no keyless free tier); without credentials the CLI prompts an interactive login.

Maps the site origin first to discover pages, then scrapes each one into nested directories under .firecrawl/. Use --include-paths to scope a non-root URL to one section. Automated runs always pass -y — without it the command opens an interactive wizard that blocks on a prompt.

Quick start

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

# Multiple formats (each saved as its own file per page)
firecrawl x 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 x download https://docs.example.com --include-paths "/features,/sdks" -y

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

Run firecrawl x download --help for the full option list, including which scrape options download supports.

Done when: the command exits successfully and the expected files exist under .firecrawl/.

See also

Source: SKILL.md on GitHub

Third-party checks

1 warning16d5 checks · Risk SAFE
  • Gen Agent Trust Hub16d

    The skill is a legitimate tool provided by Firecrawl for downloading website content as local files. It uses the vendor's own CLI tools and performs standard file and network operations consistent with its stated purpose.

  • Socket16d

    No alerts

  • Snyk16d

    Risk: MEDIUM · 1 issue

  • Runlayer6mo

    1/1 file flagged

  • ZeroLeaks5mo

    Score: 93/100 · 2 sections analyzed

Provenance

Signed by skilld at 509dd9c. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 13 hours ago.

Activeupdated last month

Capability

What it can do
Runs commands
All 2 allowed tools
Bash(firecrawl *)Bash(npx firecrawl-cli *)

Topics

README badge

README badge for firecrawl/cli/firecrawl-download

What it does

Downloads an entire website to local files in markdown, HTML, or screenshot format, organized in nested directories. Use this when users need offline documentation copies, bulk site archival, or local backups — the skill combines site mapping and scraping with options to filter by path, limit pages, and capture multiple formats per page.

Generated from the current SKILL.md.

Frequently asked

Does this download the entire site or just a subset?
It discovers and downloads all mapped pages by default, but you can limit results with --limit <n>, --include-paths, or --exclude-paths to target specific sections or cap the page count.
What file formats can be saved per page?
Markdown, links, HTML, and screenshots. Use --format to specify multiple formats (e.g. markdown,links,html) and each will be saved as a separate file per page.
Where are downloaded files stored?
Files are organized in nested directories under .firecrawl/ that mirror the site structure.
Do I need to pass -y every time?
Yes, -y skips the interactive confirmation prompt and should always be used in automated or scripted flows.
Can I exclude translations or specific paths?
Yes, use --exclude-paths with a comma-separated list (e.g. --exclude-paths "/zh,/ja,/fr") to skip matching URL paths.

Generated from the current SKILL.md. These answers refresh after source changes.