← Back to Skills Marketplace
39
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install firecrawl-interact
Description
Control and interact with a live browser session on any scraped page — click buttons, fill forms, navigate flows, and extract data using natural language pro...
README (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.
When to use
- Content requires interaction: clicks, form fills, pagination, login
scrapefailed because content is behind JavaScript interaction- You need to navigate a multi-step flow
- Last resort in the workflow escalation pattern: search → scrape → map → crawl → interact
- Never use interact for web searches — use
searchinstead
Quick start
# 1. Scrape a page (scrape ID is saved automatically)
firecrawl scrape "\x3Curl>"
# 2. Interact with the page using natural language
firecrawl interact --prompt "Click the login button"
firecrawl interact --prompt "Fill in the email field with [email protected]"
firecrawl interact --prompt "Extract the pricing table"
# 3. Or use code for precise control
firecrawl interact --code "agent-browser click @e5" --language bash
firecrawl interact --code "agent-browser snapshot -i" --language bash
# 4. Stop the session when done
firecrawl interact stop
Options
| Option | Description |
|---|---|
--prompt \x3Ctext> |
Natural language instruction (use this OR --code) |
--code \x3Ccode> |
Code to execute in the browser session |
--language \x3Clang> |
Language for code: bash, python, node |
--timeout \x3Cseconds> |
Execution timeout (default: 30, max: 300) |
--scrape-id \x3Cid> |
Target a specific scrape (default: last scrape) |
-o, --output \x3Cpath> |
Output file path |
Profiles
Use --profile on the scrape to persist browser state (cookies, localStorage) across scrapes:
# Session 1: Login and save state
firecrawl scrape "https://app.example.com/login" --profile my-app
firecrawl interact --prompt "Fill in email with [email protected] and click login"
# Session 2: Come back authenticated
firecrawl scrape "https://app.example.com/dashboard" --profile my-app
firecrawl interact --prompt "Extract the dashboard data"
Read-only reconnect (no writes to profile state):
firecrawl scrape "https://app.example.com" --profile my-app --no-save-changes
Tips
- Always scrape first —
interactrequires a scrape ID from a previousfirecrawl scrapecall - The scrape ID is saved automatically, so you don't need
--scrape-idfor subsequent interact calls - Use
firecrawl interact stopto free resources when done - For parallel work, scrape multiple pages and interact with each using
--scrape-id
See also
- firecrawl-scrape — try scrape first, escalate to interact only when needed
- firecrawl-search — for web searches (never use interact for searching)
- firecrawl-agent — AI-powered extraction (less manual control)
Usage Guidance
Review this skill before installing. Use it only for sites and accounts where you are comfortable letting an agent navigate, click, type, and reuse browser session state. Confirm before any login, purchase, submission, deletion, account change, or other action that could affect real data.
Capability Assessment
Purpose & Capability
The stated purpose is interactive browser control, so navigation, clicking, form entry, and profile/session use are broadly aligned with the skill's function.
Instruction Scope
The activation and runtime guidance appear broad for a tool that can click, submit forms, log in, and reuse browser state; the artifacts do not clearly require confirmation before state-changing actions.
Install Mechanism
No malicious install behavior or deceptive package mechanism was evidenced in the supplied scan context.
Credentials
Using persistent browser profiles and authenticated sessions is high-impact for a general browsing skill, especially without clear limits on sensitive accounts, submissions, purchases, deletions, or cleanup.
Persistence & Privilege
Persistent profile/session behavior is expected for interactive browser automation, but users should understand that cookies or logged-in access may remain available to later actions.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install firecrawl-interact - After installation, invoke the skill by name or use
/firecrawl-interact - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of firecrawl-interact.
- Control and interact with live browser sessions on any scraped page.
- Supports natural language prompts and code for clicking, filling forms, navigation, and data extraction.
- Designed for use cases where interaction is required (pagination, login, multi-step flows, JavaScript content).
- Allows authenticated scraping by persisting browser state with profiles.
- Provides options for execution timeout, output, code language, and targeting specific scrapes.
Metadata
Frequently Asked Questions
What is Firecrawl Interact?
Control and interact with a live browser session on any scraped page — click buttons, fill forms, navigate flows, and extract data using natural language pro... It is an AI Agent Skill for Claude Code / OpenClaw, with 39 downloads so far.
How do I install Firecrawl Interact?
Run "/install firecrawl-interact" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Firecrawl Interact free?
Yes, Firecrawl Interact is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Firecrawl Interact support?
Firecrawl Interact is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Firecrawl Interact?
It is built and maintained by eohmig (@eohmig); the current version is v1.0.0.
More Skills