2

    Open Browser Use

    by Leo Li

    Automate real Chrome profiles with a professional CLI, SDK, and MCP-ready automation stack for AI agents.

    Updated Jun 2026
    2 installs
    93 views
    5.0 (1)

    Free

    Included in download

    • Downloadable skill package
    • Works with Codex, Claude Code
    • 1 permission declared
    • Instant install

    Sample input

    Research the OBU documentation on GitHub and check the current pull requests, then give me a summary of the active tabs in my research session.

    Sample output

    Session ID: obu-research-20231027 [Active Tabs]

    • [ID: 45] GitHub - Pull Requests (Current)
    • [ID: 47] Documentation - OBU (Claimed)

    Action: Page Info Title: Open Browser Use Documentation URL: https://docs.browser-use.com Status: DOMContentLoaded Handoff: 1 tab preserved in 'Task - OBU' group.

    About This Skill

    The Professional Grade Browser Automation Stack

    Open Browser Use (OBU) is a powerful, platform-neutral automation framework designed to let AI agents control a real Chrome profile. Unlike sandboxed environments, this skill allows your agent to interact with the user’s actual browser sessions, including saved logins, extensions, and local files, while maintaining strict security and session management.

    What it does

    This skill provides your agent with a comprehensive toolkit to navigate the web just like a human. It supports:

    • Multi-Profile Management: Detects and switches between work, personal, and side-account Chrome profiles.
    • Unified CLI & SDK: Native CLI and SDKs for JavaScript, Python, and Go for flexible integration.
    • Session Persistence: Managed "task groups" that group tabs by project, with built-in cleanup routines.
    • Advanced Interaction: Direct CDP command support, file chooser interception for uploads, download monitoring, and clipboard management.
    • MCP Support: Plugs directly into agent runtimes like Claude Code or Cursor via a local Model Context Protocol server.

    Why use this skill?

    Standard AI-browser tools often struggle with authentication, CAPTCHAs, or complex multi-tab workflows. Open Browser Use leverages a real Chrome instance and a native messaging host to bypass these limitations. It includes sophisticated "tab lifecycle" logic that automatically cleans up research tabs while preserving deliverable results, ensuring the user's browser doesn't become a graveyard of abandoned AI windows.

    Use Cases

    • Automate repetitive form filling across multiple Chrome profiles
    • Sync data between internal web tools and local development environments
    • Extract research data from authenticated sessions without re-logging in
    • Orchestrate multi-tab workflows via Python, Node.js, or Go SDKs

    Reviews

    5.0
    1 review
    5
    1
    4
    0
    3
    0
    2
    0
    1
    0
    Verified Download
    29 days ago
    Samuel Rose

    Security Scanned

    Passed automated security review

    Permissions

    Browser

    Allowed Hosts

    example.com
    github.com
    docs.browser-use.com

    File Scopes

    references/**
    agents/**

    Works with the open SKILL.md standard. Best with Codex CLI/Codex, Claude Code, and compatible agent runtimes. The underlying Open Browser Use runtime also exposes MCP, CLI, and JavaScript/Python/Go SDKs.

    Creator

    Frequently Asked Questions

    More Premium Skills

    Free