AutoGineer
Generated banner for Firecrawl Download
Generated logo for Firecrawl Download

Firecrawl Download

FirecrawlOfficialPublished by Firecrawl

  • Skill
  • Workflow
  • Automation and integrations
  • ISC
  • No issues found
Download ZIP

From the author

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

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The firecrawl-download skill provides a command-line interface to crawl and save website content directly to your local file system. It maps a site to discover pages and then scrapes them into a structured directory, supporting multiple output formats including markdown and screenshots. This tool is designed for creating offline documentation, local archives, or reference copies of web content.

What it does

  • Downloads website content as local markdown files.
  • Captures screenshots of web pages during the crawl process.
  • Supports scoping downloads to specific URL paths using include and exclude filters.
  • Maps site structures to discover pages before downloading.
  • Saves output files into a structured local directory.
  • Automates the download process with non-interactive flags.

When to use it

  • When you need to create an offline copy of a documentation site.
  • When you want to archive specific sections of a website for local reference.
  • When you need to convert web pages into markdown for local processing or storage.
  • When you require visual snapshots of web pages alongside their text content.

Advantages

  • Enables offline access to web-based information.
  • Provides granular control over which parts of a site to download.
  • Supports multiple file formats for versatile local usage.
  • Automates repetitive scraping tasks through the command line.

Usage examples

“Download the first 20 pages of the documentation site including screenshots.”
The agent executes the download command with the specified limit and screenshot flag, saving the files to the local .firecrawl directory.
“Download only the features and SDK sections of the website.”
The agent uses the include-paths filter to restrict the crawl to the specified directories, saving only the relevant content.

Install

  1. Download the skill as a ZIP:

    https://mp-staging.autogineer.com/agent-skills/firecrawl/firecrawl-download/download

  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip firecrawl-download.zip -d .agents/skills

Documentation by Firecrawl

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

  • firecrawl-map — just discover URLs without downloading

  • firecrawl-scrape — scrape individual pages

  • firecrawl-crawl — bulk extract as JSON (not local files)

  • firecrawl-build-scrape — building bulk extraction into an app instead of running it here

Files

SKILL.md

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

  • firecrawl-map — just discover URLs without downloading

  • firecrawl-scrape — scrape individual pages

  • firecrawl-crawl — bulk extract as JSON (not local files)

  • firecrawl-build-scrape — building bulk extraction into an app instead of running it here

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Declares allowed tools

Security

No issues found by our static scan· No issues found

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by
Firecrawl
Publisher
Firecrawl (Official)
Source
firecrawl/skills · skills/core/firecrawl-download · commit 458d9d0
Licence
ISC License (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by Firecrawl.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download firecrawl-download.zip