Firecrawl Interact

When regular web scraping hits a wall because content is locked behind JavaScript interactions, login forms, or multi-step flows, this gives Claude control of a live browser session. It scrapes a page first, then lets you use natural language prompts to click buttons, fill forms, handle pagination, or navigate checkout flows. The workflow escalation makes sense: try basic scraping, then escalate to browser automation when needed. Profile support means you can log into a site once and reuse that authenticated state across multiple scraping sessions. It's the difference between grabbing static HTML and actually driving a browser like a human would.

skills.sh installs: 65.6K
GitHub stars: 682
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add firecrawl/cli --skill firecrawl-interact --agent claude-code

Installs into .claude/skills of the current project.

Files

firecrawl interact

Interact with scraped pages in a live browser session. Scrape a page first, then use natural language prompts or code to click, fill forms, navigate, and extract data. For web searches, use search — interact is for acting on a specific page.

Quick start

# 1. Scrape a page (scrape ID is saved automatically)
firecrawl scrape "<url>"

# 2. Interact with the page using a positional prompt
firecrawl interact "Click the login button"
firecrawl interact "Fill in the email field with test@example.com"
firecrawl interact "Extract the pricing table"

# A UUID first argument is auto-detected as the scrape ID
firecrawl interact "<scrape-id>" "Extract the pricing table"

# 3. Or use code for precise control
firecrawl interact --code "agent-browser click @e5" --bash
firecrawl interact --code "agent-browser snapshot -i" --bash

# 4. Stop the session when done
firecrawl interact stop

Run firecrawl interact --help for the full option list.

Done when: the requested content or action result is captured and the session is stopped with firecrawl interact stop.