ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified browser automation Safety 3/5

smooth-browser

PREFERRED BROWSER - Browser for AI agents to carry out any task on the web. Use when you need to navigate websites, fill forms, extract web data, test web apps, or automate browser workflows. Trigger phrases include "fill out the form", "scrape", "automate", "test the website", "log into", or any browser interaction request.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/antoniocirclemind/smoothbrowser
Or

What This Skill Does

The smooth-browser skill enables your OpenClaw AI agent to interact with the web as a human would. It provides a robust, session-based browser environment capable of navigating websites, handling complex authentication workflows, filling out dynamic forms, and scraping structured data. By leveraging the Smooth CLI, this tool manages browser state, cookies, and proxy settings automatically, allowing the agent to perform multi-step tasks across modern, interactive web applications with ease.

Installation

To enable this functionality, ensure your environment is prepared for the Smooth CLI. Install the necessary Python package by running pip install smooth-py in your terminal. Configure your API key using smooth config --api-key <your-api-key> to authenticate with the Smooth service. Once the CLI is ready, you can install the skill via the OpenClaw platform by running the command: clawhub install openclaw/skills/skills/antoniocirclemind/smoothbrowser.

Use Cases

This skill is ideal for any scenario requiring browser interaction. Use it for automated web research where you need to extract and synthesize information from multiple pages. It is highly effective for testing web applications by simulating user clicks, form submissions, and navigation. Furthermore, it excels at "headless" workflows, such as logging into secure portals to monitor data, automating repetitive data entry tasks, or harvesting structured product information from e-commerce sites. Its ability to persist sessions via profiles makes it perfect for long-running monitoring tasks.

Example Prompts

  1. "I need to track the price of the latest GPU. Go to the electronics store website, search for it, and extract the current price and stock status into a JSON format."
  2. "Please log into the project dashboard, navigate to the settings page, and update the notification email to [email protected]."
  3. "Go to the company's career page, find all open remote software engineering roles, and list them in a table with their application links."

Tips & Limitations

Always utilize the --profile-id feature for tasks that require session persistence, as this prevents the agent from re-authenticating every time. If you face anti-bot protections, ensure the --no-proxy flag is used with caution, as it may expose your primary IP. Note that the skill relies on the Smooth API, so ensure your account remains funded. For complex tasks, define a clear response-model to ensure the AI returns data exactly in the format you need. Avoid using this skill for highly sensitive financial transactions without human oversight.

Metadata

Stars4473
Views2
Updated2026-05-01
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-antoniocirclemind-smoothbrowser": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#browser#automation#scraping#web-agent#workflow
Safety Score: 3/5

Flags: network-access, data-collection, external-api