browser-use
Use Browser Use cloud API to spin up cloud browsers for Clawdbot and run autonomous browser tasks. Primary use is creating browser sessions with profiles (persisted logins/cookies) that Clawdbot can control. Secondary use is running task subagents for fast autonomous browser automation. Docs at docs.browser-use.com and docs.cloud.browser-use.com.
Why use this skill?
Power your OpenClaw agent with cloud-based browser automation. Manage persistent logins, run headless tasks, and automate complex web workflows with Browser Use API.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/shawnpana/browser-useWhat This Skill Does
The browser-use skill for OpenClaw integrates the Browser Use cloud API, providing you with high-performance, cloud-hosted browser sessions that the AI agent can control directly. This skill enables autonomous browser interactions, allowing Clawdbot to navigate complex websites, perform data extraction, interact with web-based platforms, and maintain persistent login states through browser profiles. By leveraging headless or headful cloud browsers, the agent can perform tasks that require authentication, such as interacting with dashboards, social media, or private internal tools.
Installation
To begin, ensure you have the required CLI access. Run the following command in your terminal:
clawhub install openclaw/skills/skills/shawnpana/browser-use
After installation, you must configure your API key. Obtain your key from cloud.browser-use.com and set it using:
clawdbot config set skills.entries.browser-use.apiKey "bu_your_key_here"
If you encounter a missing key error, the agent will prompt you to complete this configuration step before proceeding with browser tasks.
Use Cases
- Automated Research: Have the agent browse multiple websites, extract data, and synthesize findings into a report.
- Persistent Task Automation: Use Profiles to log into a service once, save the session, and perform recurring tasks without re-authenticating.
- Agentic Workflows: Hand off specific navigation tasks to a cloud browser instance, allowing the agent to "see" and act on the web in real-time.
- Cloud Scaling: Offload resource-intensive browsing tasks from your local machine to the browser-use cloud infrastructure.
Example Prompts
- "Create a new browser profile named 'research' and use it to log into the analytics dashboard at app.example.com to export the last 30 days of data."
- "Spin up a fresh cloud browser session and navigate to the open positions page of the company portal, then list all new engineering job openings."
- "Using my existing 'work' profile, go to the project management tool and update the status of the ticket tagged with #BU-101 to 'Done'."
Tips & Limitations
- Persistent Profiles: Always use profiles for sites requiring logins. This saves significant time and avoids triggers for 2FA or bot-detection systems.
- Cost Management: Sessions are billed per minute and unused time is refunded. Ensure you stop your sessions explicitly using the PATCH command or by instructing the agent to terminate them once the task is complete.
- Duration: Individual sessions are capped at 4 hours. For long-running automated jobs, design your workflows to be idempotent or save state frequently.
Metadata
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 skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-shawnpana-browser-use": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, external-api