要点
Live browser interaction on scraped pages using natural language prompts or code.
- Control interactions via natural language prompts ("click login button", "fill email field") or direct code execution in bash, Python, or Node
- Persist browser state across sessions using profiles to maintain authentication, cookies, and localStorage
- Supports form filling, button clicks, pagination navigation, infinite scroll handling, and multi-step flow completion
- Always requires a prior
firecrawl scrapecall; scrape ID is saved automatically for subsequent interact commands - Use
firecrawl interact stopto free resources when done with a session
SKILL.md
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"