skills.rest
ovisan
ovisanCOMMUNITY
Explore all skills by this author →
GitHub

firecrawl-interact

Control live browser sessions to click, fill forms, and extract data from scraped pages.

2|Updated Mar 29, 2015
Search Tags:#cli#browser automation#firecrawl#web scraping#form filling#pagination#authenticated scraping
One-click install
npx skills add https://github.com/ovisan/dotfiles --skill firecrawl-interact-ovisan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: firecrawl-interact
Source: https://github.com/ovisan/dotfiles/tree/main/.grok/skills/firecrawl-interact
Command: npx skills add https://github.com/ovisan/dotfiles --skill firecrawl-interact-ovisan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Standard web scraping fails when content sits behind JavaScript interactions like logins, form submissions, pagination, or infinite scroll. This Skill opens a live browser session on a scraped page so you can interact with it using natural language prompts or code. ## Core Features & Use Cases - Interactive Browser Control: Click buttons, fill forms, and navigate multi-step flows using natural language prompts or code in bash, python, or node. - Authenticated Scraping with Profiles: Persist cookies and localStorage across sessions with named profiles, so you can log in once and return authenticated later. - Session Management: Scrape IDs are saved automatically, sessions can be targeted with --scrape-id for parallel work, and stopped to free resources. - Use Case: You need pricing data behind a login wall. Scrape the login page with a profile, interact to fill credentials and submit, then 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 the page by clicking the login button and extracting the resulting data.

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 webpage that requires clicking or form filling?▼

First run firecrawl scrape on the URL, then use firecrawl interact with --prompt for natural language instructions like clicking a button, or --code with a language flag for precise control. The scrape ID is saved automatically for subsequent interact calls.

How to scrape a website that requires login?▼

Use the --profile flag on your scrape to persist cookies and localStorage. Scrape the login page with a named profile, interact to fill credentials and submit, then scrape authenticated pages with the same profile to retain the session.

When should I use interact instead of scrape or search?▼

Use interact only as a last resort in the escalation pattern: search, scrape, map, crawl, then interact. It is for content behind JavaScript interaction, never for web searches, which should use the search command instead.

Can I run multiple browser sessions in parallel with firecrawl?▼

Yes. Scrape multiple pages first, then target each session using the --scrape-id option on interact calls. Without --scrape-id, interact defaults to the most recent scrape.

Why does firecrawl interact fail with no scrape ID?▼

Interact requires a scrape ID from a previous firecrawl scrape call in the same workflow. Always scrape the target page first; the ID is saved automatically, or pass one explicitly with --scrape-id.

Related Skills

Explore More Software Engineering Skills→
firecrawlfirecrawl
616

firecrawl-interact

Drive a live browser session to click, fill forms, and extract data from scraped pages.

Official
Intermediate
KaranKathur06KaranKathur06

data-pipeline

Build scheduled ETL workflows that extract, transform, and load data into analytics destinations.

Community
Intermediate
orthogonal-shorthogonal-sh
12

notte

Automate browser sessions, scraping, and page actions via a unified API.

Official
Advanced
SethyPagnaSethyPagna

scrapling

Extract web content from static, dynamic, and protected pages.

Community
Advanced