firecrawl-interact

Drives a live browser session on scraped pages to click, fill forms, and extract content.

Updated Aug 20, 2026
One-click install
npx skills add https://github.com/bittlinkm/claude-setup --skill firecrawl-interact-bittlinkm
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: firecrawl-interact
Source: https://github.com/bittlinkm/claude-setup/tree/main/skills/firecrawl-interact
Command: npx skills add https://github.com/bittlinkm/claude-setup --skill firecrawl-interact-bittlinkm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Static scraping fails when content sits behind logins, pagination, infinite scroll, or interactive elements. This Skill lets you act on a scraped page in a live browser session so you can reach content that a plain scrape cannot capture. ## Core Features & Use Cases - Live Browser Interaction: Click buttons, fill forms, log in, paginate, and scroll using natural language prompts or precise code commands against a scraped page. - Persistent Profiles: Save cookies and localStorage across sessions with --profile, so you can log in once and return authenticated later. - Session Management: Scrape IDs are saved automatically, sessions can be reconnected read-only, and firecrawl interact stop frees resources when done. - Use Case: You need pricing data behind a login wall. Scrape the login page with a profile, fill in credentials via an interact prompt, then re-scrape the dashboard with the same profile and extract the data. ## Quick Start Scrape the target page with firecrawl, then ask the agent to interact with it, for example: scrape https://example.com/login and fill in the email field and click the login button, then stop the session.

Frequently Asked Questions about firecrawl-interact

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I interact with a scraped page using firecrawl?

Run firecrawl scrape on the URL first, then use firecrawl interact with a natural language prompt like "Click the login button". The scrape ID is saved automatically, so subsequent interact calls reuse the same session.

How do I fill out a form or log in on a web page with firecrawl?

Scrape the page, then run firecrawl interact with a prompt such as "Fill in the email field with [email protected] and click login". Use --profile on the scrape to persist cookies and localStorage so later sessions stay authenticated.

When should I use firecrawl interact instead of scrape?

Try scrape first for static content. Escalate to interact only when content requires actions like clicking, form submission, pagination, or infinite scroll, or when a scrape returned incomplete results.

Why does my firecrawl interact session stop working?

Saved sessions expire after about 10 minutes. If the CLI warns that the session is stale, re-scrape the page to get a fresh scrape ID and continue interacting with the new session.

Can I run multiple firecrawl interact sessions in parallel?

Yes. Scrape multiple pages first, then interact with each one by passing its specific scrape ID via --scrape-id. Each session is independent, and you should stop each with firecrawl interact stop when finished.