An advanced browser automation skill that enables persistent sessions, multi-step workflows, and AI agent integration for seamless web interaction.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install browser-use-1-0-2
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install browser-use-1-0-2 using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is browser-use?
browser-use is a powerful automation framework designed to give AI agents deep control over web browsers. Unlike standard automation scripts, it maintains persistent sessions across commands, allowing for complex, multi-step operations such as authenticated navigation and stateful data extraction. This Openclaw Skills integration supports multiple browser modes, including headless Chromium, real local Chrome instances with existing profiles, and remote cloud-based browsers.
By leveraging the capability to keep sessions alive, developers can build workflows that mimic human behavior more accurately than stateless alternatives. Whether you are performing routine web maintenance or building complex research agents, this skill provides the necessary interface to interact with the modern web programmatically.
browser-use Use Cases
- Automating end-to-end web testing and form submissions.
- Extracting structured data and taking screenshots from dynamic web pages.
- Performing authenticated actions using real Chrome profiles and synced cookies.
- Running autonomous subagents in the cloud for parallel research tasks.
- Exposing local development servers to remote browsers using built-in tunneling.
How browser-use Works
- Initialize the browser session using a specific mode like chromium, real, or remote.
- Navigate to a target URL to begin the automation workflow.
- Use the state command to inspect the page and retrieve clickable element indices for high-precision targeting.
- Execute interactions such as clicking, typing, or scrolling based on the discovered indices.
- Verify the results through screenshots, HTML snapshots, or DOM evaluation before proceeding.
- Maintain the session for subsequent commands or close it to clean up system resources.
browser-use Setup
Before utilizing this skill, ensure your environment is ready by running the diagnostics tool:
browser-use doctor
To start a basic navigation session within the Openclaw Skills ecosystem, use:
browser-use open <url>
For remote cloud execution with an AI agent, use:
browser-use --browser remote run "your task description"
browser-use Data Schema & Taxonomy
The skill organizes data through sessions and profiles, utilizing a structured approach for element interaction and state management.
| Entity | Description |
|---|---|
| Element Indices | Unique numeric IDs generated by the state command for interaction targets. |
| Sessions | Persistent browser instances (local or remote) identified by unique IDs. |
| Profiles | Collections of cookies, logins, and extensions for authenticated browsing. |
| Tasks | Specific automation jobs with associated logs, statuses, and reasoning steps. |
| Tunnels | Secure URLs mapping local ports to the public web for remote access. |
browser-use Advanced Features
- Persistent Python execution environment to maintain variables and logic across browser commands.
- Integrated Cloudflare tunneling to allow remote AI agents to interact with local development environments.
- Sophisticated cookie management including domain-specific syncing between local and cloud profiles.
- Multi-agent support for running parallel autonomous tasks with structured JSON output and judge modes.
- Fine-grained wait conditions for selectors, text, and specific element states to handle complex SPA behaviors.
SKILL.md
Loading
Related Openclaw Skills
Cross-Border E-Commerce Listing Generator
An automated AI agent skill for generating high-converting, platform-specific product listings for Amazon and AliExpress.
Email Marketing & Intelligent Auto-Reply
A robust automation skill for personalized bulk email marketing and intelligent, FAQ-driven automated replies.
WeChat Publisher
Automate the publication of articles and management of drafts on WeChat Official Accounts using these Openclaw Skills.
Feishu Agent Integration
A comprehensive framework for creating custom AI agents and integrating them into Feishu messaging environments using Openclaw Skills.
claw-shell
A terminal execution skill that allows AI agents to run shell commands within a dedicated, persistent tmux session.
Reliable Tool Context
A sophisticated skill designed to capture large CLI command outputs as artifacts, allowing AI agents to query and transform data via Python without bloating the context window.
Featured*
