use my browser

    1

    Drive your local Chrome, Brave, or Chromium browser using Playwright to automate tasks within your active sessions.

    Free

    1 useSecurity scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    use my browser

    Example session with this skill installed

    Use my Chrome 'Default' profile to go to my GitHub notifications, click the first unread item, and tell me the title.

    • Read your context and instructions
    • Compiled the use my browser

    I have connected to your Chrome browser using the 'Default' profile and navigated to your GitHub notifications. I located the first unread notification and retrieved the thread title.

    GitHub Notification Detail

    ActionResult
    Current URLhttps://github.com/notifications
    Target Elementnotification-list-item (unread)
    Thread Titlechore: update playwright-core to v1.49.0
    StatusSuccessfully clicked and inspected

    Next steps

    • Would you like me to summarize the comments in this specific notification thread?
    • I can mark this notification as read or unsubscribe from the thread for you.
    • I can check for other unread notifications from specific repositories.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Automation scripts often fail when they can't access your existing sessions, cookies, or saved logins. This skill solves the "walled garden" problem by allowing an AI agent to drive your actual Chrome, Brave, or Chromium browser instance via the Chrome DevTools Protocol (CDP).

    What it does

    • Browser detection identifies installed Chromium-based browsers and available user profiles.
    • Session attachment connects to your live browser profile to use existing logins and cookies.
    • Batched execution groups multiple actions like clicks and form fills into a single execution to reduce latency.
    • Page inspection returns visible interactive controls and ARIA snapshots for element discovery.
    • Custom evaluation runs arbitrary JavaScript directly in the page context for fast data extraction.

    How it works

    1. Detect scans for local browser installations and checks if a debugging port is already open.
    2. Launch starts the chosen browser profile with remote debugging enabled.
    3. Connect attaches Playwright to the active session without creating a new isolated context.
    4. Execute runs specific scripts like batch.mjs for flows or eval.mjs for data scraping.

    Frameworks & tools

    The skill utilizes Node.js and Playwright Core. It communicates with browsers via the Chrome DevTools Protocol on port 9222.

    Why this beats prompting it yourself

    Generic agents struggle with authentication hurdles and multi-step UI interactions. This skill provides a structured driver system that handles CDP connection management, profile locking, and optimized execution loops that prevent the agent from getting stuck in slow "screenshot-and-think" cycles.

    Use cases

    • Authenticated scraping extract data from dashboards that require a login you already have.
    • Form automation fill out complex, multi-page wizards that use React or other heavy frameworks.
    • Visual auditing capture screenshots of specific UI components while they are in a logged-in state.
    • Workflow bridging move data between a web application and your local environment using your active session.

    Known limitations

    Requires a Chromium-based browser. Does not support Firefox or Safari. The host machine must allow port 9222 access and Node.js execution.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for APIs & Backend.

    Requires Chromium-based browsers (Chrome, Brave, Chromium). Only one driver script can run at a time. The browser process must remain open in the background to maintain the connection.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    1 use

    Times used to date

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 27 days ago

    • Free with an Agensi account

    Permissions

    Terminal / Shell
    Browser
    Network Access
    Listed27 days ago

    What's inside

    Frequently Asked Questions

    Drive your local Chrome, Brave, or Chromium browser using Playwright to automate tasks within your active sessions.

    This skill uses the open SKILL.md standard. Use it through an MCP-compatible agent connected to Agensi, and check the compatibility information on this page for confirmed agents and required capabilities.

    Connect your AI agent to Agensi through MCP, then ask it to use use my browser on your task. Your agent loads the latest approved version each time. Paid skills require a purchase or active subscription. Skill files are not available for download; your licence does not allow you to save, copy or export any part of a skill.

    New in APIs & Backend

    Free