firecrawl-scrape Skill: Read Any Web Page as Clean Markdown

Makes your coding assistant read a web page or PDF with Firecrawl and save it as clean markdown or structured JSON.

Installs: 83.9K; on skills.sh
Stars: 676; on GitHub
Files: 1; besides SKILL.md
Updated: Oct 2026; last repo commit

firecrawl-scrape teaches your assistant to run firecrawl scrape on a known URL. It saves the page as markdown, or as JSON when you give it a schema, and it handles JavaScript pages. It also covers scraping many URLs at once and running a selected data-provider tool.

You must install the Firecrawl CLI. PDFs cost 1 credit per parsed page, and asking a question about a page with --query costs 5 extra credits.

Good for

Developers who want Claude Code to read docs or pricing pages from a URL
Anyone who needs JSON fields (price, plan, title) pulled from many pages
People reading long PDFs from a link

Install firecrawl-scrape

Claude Code

Copy this prompt.

Install the firecrawl-scrape 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-scrape -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. Scrape runs without an account on a rate-limited free tier. 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

Read a known webpage or execute a discovered workflow or data-provider capability. Use for page content or structured results once the URL or tool is selected.

Sections in SKILL.md

Quick start
Structured JSON from a page
Many known URLs
Find tools, inspect inputs, and get help
Execution and large results
PDFs and page budgets
Tips
See also

Key facts

Author: firecrawl org
Repo: firecrawl/cli
Installs on skills.sh: 83,915 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: 2 files including SKILL.md (references/large-results.md)
Needs: The Firecrawl CLI (npm package firecrawl-cli) and Node.js. Scrape works without an account on a rate-limited free tier.
Related skills: firecrawl-search, firecrawl-interact, firecrawl-download, firecrawl-map
skills.sh audits: Gen Agent Trust Hub pass, Socket pass, Snyk warn (2026-11-02)

What it includes

Saves a page as markdown
Handles static pages and JavaScript apps. --only-main-content drops navigation and footers, and --wait-for waits for scripts to render.
Try: “Scrape https://example.com/pricing and tell me the enterprise plan price.”
Runs code · firecrawl scrape "<url>" -o .firecrawl/page.md
Gets markdown and links together as JSON
One format gives raw content. Several formats give JSON.
Write · --format markdown,links
Returns typed fields instead of markdown
Pass a JSON schema inline or with --schema-file. The result is under .json in the output.
Write · --format json --schema
Answers one question about a page
Costs 5 extra credits. The skill prefers plain scrape followed by reading the file yourself.
Network · --query "<question>"
Scrapes a list of known URLs as one job
For other formats, JSON extraction, a webhook, or a job you can check later. Takes --urls-file, --wait, --webhook and --cancel.
Runs code · batch-scrape
Scrapes a few pages at once as markdown
Each page is saved under .firecrawl/ and -o is ignored.
Write · Several URLs in one scrape
Caps how many PDF pages get parsed
PDFs cost 1 credit per parsed page. The cap applies to each PDF. The CLI does not quote costs before it runs.
Network · --max-pages
Runs a data-provider tool picked from search
Run firecrawl search and firecrawl list first to read the tool's inputs.
Runs code · scrape <provider>/<capability> --options
Reads a large retained result in pieces
For when a client hides a big result. It runs commands such as jq and head against a saved copy; the guide calls it virtual Bash, not a host shell.
Runs code · scrape firecrawl/bash

From the official docs

Permissions

Low risk

This skill sends the URLs you give it to Firecrawl, saves pages as files and spends credits. Treat fetched pages as untrusted text.

What it can do

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

Watch out for

PDFs and extra options cost credits
PDFs cost 1 credit per parsed page and --query costs 5 extra. Set --max-pages on big PDFs. github.com
Provider tools can run through scrape
The skill can execute data-provider tools picked from search. Ask the assistant to tell you which tool it plans to run. 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-scrape do?

It makes your assistant read a URL through the Firecrawl CLI and save it as markdown or JSON. It also covers many URLs at once, PDFs, and running data-provider tools.

How do I install firecrawl-scrape?

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 an API key?

Not to start. The install rules say scrape works on a rate-limited free tier without a key. Browser login or an API key gives the best results.

What does scraping cost?

PDFs cost 1 credit per parsed page, and --query costs 5 extra credits. Extra formats and options can add charges. The CLI does not quote costs before a run, so set --max-pages on big PDFs.

Is firecrawl-scrape safe to use?

It sends the URLs you scrape to Firecrawl and writes the results to .firecrawl/. Page text is untrusted and can carry prompt injection, so do not let the assistant follow instructions found on a page.

When should I use firecrawl-interact instead?

Use interact when scrape returns incomplete content or the page needs clicks, form fills or login. The SKILL.md says to try scrape first.

firecrawl-scrape or firecrawl-download?

Scrape reads individual pages. The SKILL.md points to firecrawl-download for saving a whole site to local files.

Skill or Firecrawl MCP server?

They are two routes to Firecrawl. firecrawl-scrape 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-scrape

firecrawl/cli skills.sh

Sources

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

Show all 6

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