firecrawl-interact Skill: Click, Fill Forms and Log In on a Page

Makes your coding assistant click, fill forms, log in and scroll on a page in a live browser session through Firecrawl.

Installs: 65.4K; on skills.sh
Stars: 676; on GitHub
Updated: Oct 2026; last repo commit

firecrawl-interact teaches your assistant to scrape a page first, then drive it with prompts such as "Click the login button" or "Extract the pricing table". It can fill forms, log in, paginate and infinite-scroll. For exact control it can run code with agent-browser commands.

You must install the Firecrawl CLI. Interact needs a scrape ID from an earlier firecrawl scrape, and saved sessions may expire after about 10 minutes.

Good for

Developers who need data behind a login, a form or pagination
Testers who want a page driven with plain-English prompts
Anyone whose scrape came back empty or incomplete

Install firecrawl-interact

Claude Code

Copy this prompt.

Install the firecrawl-interact 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-interact -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. Interact 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

Drive a live browser on a scraped page: click, fill forms, log in, paginate, infinite-scroll. Use when content requires interaction or a scrape failed or returned incomplete content.

Sections in SKILL.md

Quick start
Profiles
Tips
See also

Key facts

Author: firecrawl org
Repo: firecrawl/cli
Installs on skills.sh: 65,383 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) and Node.js. Interact works without an account on a rate-limited free tier, according to the install rules.
Related skills: firecrawl-scrape, firecrawl-search, firecrawl-agent
skills.sh audits: Gen Agent Trust Hub pass, Socket pass, Snyk warn (2026-11-02)

What it includes

Drives the scraped page with a plain-English prompt
Scrape the page first. The scrape ID is saved automatically, so later interact calls can skip it. Examples: click a button, fill in a field, extract a table.
Try: “Scrape example.com/login, then click the login button and fill in the email field.”
Runs code · firecrawl interact "<prompt>"
Runs exact browser commands
For precise control, such as agent-browser click @e5 or agent-browser snapshot -i.
Runs code · interact --code "agent-browser ..." --bash
Ends the session and frees resources
The skill's "done when" check is that the session is stopped.
Runs code · interact stop
Keeps cookies and localStorage between scrapes
Log in once and come back authenticated. --no-save-changes reconnects without writing to the profile.
Write · --profile <name>
Interacts with several scraped pages
Scrape multiple pages and pass each one's ID with --scrape-id.
Network · Parallel pages

From the official docs

Permissions

Medium risk

This skill lets your assistant click, fill in forms and log in on live web pages. Use test accounts and stop the session when you are done.

What it can do

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

Watch out for

It can click, submit forms and log in
Prompts such as "Click the login button" or "Fill in the email field" act on live pages. Use test accounts and review what the assistant plans to submit. github.com
Profiles keep login state
A --profile keeps cookies and localStorage between scrapes. Do not reuse a profile for a real account you care about. 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-interact do?

It makes your assistant drive a scraped page in a live browser session. It can click, fill forms, log in, paginate and scroll, then extract what appears.

How do I install firecrawl-interact?

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?

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

Can it log in to my accounts?

Yes, that is one of its uses. A profile keeps cookies and localStorage between scrapes so you come back signed in. Use test or throwaway accounts, and do not store a real production login in a profile.

Is firecrawl-interact safe to use?

It can click buttons and submit forms for you, so watch what it does on live sites. Page text is untrusted and can carry prompt injection. Stop the session with firecrawl interact stop when you are done.

firecrawl-interact or firecrawl-agent?

The SKILL.md describes agent as AI-powered extraction with less manual control. Interact gives you step-by-step control of one page. Try scrape first, and interact only when scrape misses content.

Skill or Firecrawl MCP server?

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

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-interact SKILL.md · github.com
Firecrawl security rules · github.com