firecrawl-download Skill: Save a Website as Local Files

Makes your coding assistant save a website or one section of it as local markdown files and screenshots.

Installs: 80.1K; on skills.sh
Stars: 676; on GitHub
Updated: Oct 2026; last repo commit

firecrawl-download teaches your assistant to run firecrawl x download <url>. It maps the site first to find pages, then scrapes each one into nested folders under .firecrawl/. Each page can come out as markdown, a links file and a screenshot.

The command is marked experimental, and it needs a Firecrawl account because it has no keyless free tier. The skill tells the assistant to always pass -y, so no confirmation wizard blocks the run.

Good for

Developers who want offline copies of docs to read or search
Teams archiving a site section as files
Anyone who wants screenshots of each page

Install firecrawl-download

Claude Code

Copy this prompt.

Install the firecrawl-download skill in Claude Code. Run this command:

npm install -g firecrawl-cli@latest
firecrawl login --browser
npx skills add https://github.com/firecrawl/cli --skill firecrawl-download -a claude-code

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js, A Firecrawl account (or the keyless free tier).

The skill only gives your assistant instructions. The Firecrawl command line tool does the work, so install it and sign in first. Download needs an account: the skill says there is no keyless free tier, and without credentials the CLI prompts for a login. The one-command route installs the CLI, signs you in through the browser and adds the core and workflow skills for every editor it detects, not just this skill.

From the vendor's docs. Source.

What's in the skill

When it loads

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

Sections in SKILL.md

Quick start
See also

Key facts

Author: firecrawl org
Repo: firecrawl/cli
Installs on skills.sh: 80,141 as of 2026-11-02
GitHub stars: 676 for the whole firecrawl/cli repo, 2026-11-02
License: ISC (package.json of the CLI repo)
Last commit to the repo: 2026-10-28
What is inside: 1 file (SKILL.md)
Needs: The Firecrawl CLI (npm package firecrawl-cli), Node.js and a Firecrawl account. The SKILL.md says download has no keyless free tier.
Related skills: firecrawl-map, firecrawl-scrape, firecrawl-crawl
skills.sh audits: Gen Agent Trust Hub pass, Socket pass, Snyk warn (2026-11-02)

What it includes

Downloads a site into folders under .firecrawl/
Maps the site origin, then scrapes each page into nested directories. -y skips the interactive wizard.
Try: “Download the docs at docs.example.com, 20 pages, with screenshots.”
Runs code · firecrawl x download <url> --limit 20 -y
Adds a screenshot of each page
With --format markdown,links it creates index.md, links.txt and screenshot.png for every page.
Write · --screenshot
Keeps the download inside chosen sections
Takes a comma-separated list such as "/features,/sdks".
Network · --include-paths
Skips sections such as translations
The skill's example excludes /zh, /ja, /fr, /es and /pt-BR.
Network · --exclude-paths

From the official docs

Permissions

Medium risk

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

It writes many files
Each mapped page is scraped and saved under .firecrawl/. The SKILL.md gives no credit cost. Set --limit and --include-paths so a download stays small. github.com
The command is experimental
The skill marks download as experimental, so check its options with firecrawl x download --help. github.com
Web pages can try to steer your assistant
The skill's own security note calls fetched web content untrusted and says it may contain prompt injection. Do not let the assistant follow instructions it finds on a page. github.com
Setup installs a global npm package
The CLI is installed with npm install -g. The one-command setup also adds skills to every coding editor it detects, so use the single-skill route if you want only this one. github.com
The CLI sends anonymous usage data
The README says it collects the CLI version, OS, Node.js version and which dev tools it detects during sign-in. Set FIRECRAWL_NO_TELEMETRY=1 to turn it off. github.com

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details

Turning on read-only	No read-only mode. The skill runs CLI commands that spend credits and write files.
Talks to	Firecrawl's API, or your own server if you set --api-url. Web pages the CLI fetches. Page content the assistant reads goes to your AI provider as part of the chat
Sign-in and keys	Browser sign-in stores credentials in the CLI. You can set FIRECRAWL_API_KEY instead.
Scopes	Runs firecrawl commands in your shell (the skill allows Bash(firecrawl ) and Bash(npx firecrawl-cli ))

Questions

What does firecrawl-download do?

It makes your assistant save a site or section as local files with firecrawl x download. Pages come out as markdown, and you can add links and screenshots.

How do I install firecrawl-download?

Use the install box at the top of this page. You need the Firecrawl CLI and a sign-in as well as the skill. The one-command route installs the whole core skill set.

Do I need a Firecrawl account?

Yes. The SKILL.md says download needs authentication, has no keyless free tier, and prompts an interactive login without credentials.

Is the download command stable?

The SKILL.md marks it experimental and puts it under the firecrawl x command group. Run firecrawl x download --help to see which options your installed version supports.

Is firecrawl-download safe to use?

It writes many files under .firecrawl/, one folder per page, and scrapes every page it maps. The SKILL.md does not state a credit cost. Set --limit and --include-paths before you approve a run, and add .firecrawl/ to .gitignore.

firecrawl-download or firecrawl-crawl?

Download saves local files per page. The SKILL.md describes crawl as bulk extraction to JSON, not local files.

Skill or Firecrawl MCP server?

They are two routes to Firecrawl. firecrawl-download is a SKILL.md that tells the assistant to run the Firecrawl CLI in your shell. The skill only allows Bash(firecrawl *) and Bash(npx firecrawl-cli *), so it needs an assistant that can run shell commands. The Firecrawl MCP server and the local Firecrawl MCP server give your client Firecrawl as tools it calls directly, with no skill involved. The README describes firecrawl setup mcp for adding the MCP server to your editors. You can use either route, or both.

Information

updated Nov 2, 2026

Repository: firecrawl/cli
Folder: skills/firecrawl-download

firecrawl/cli skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 5

Firecrawl CLI install rules · github.com
firecrawl/cli README · github.com
skills CLI commands · github.com
firecrawl-download SKILL.md · github.com
Firecrawl security rules · github.com