Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Windows Click & Write — Desktop Automation & UI Control

    1

    Full desktop GUI automation for AI agents via MCP: click buttons, type into any app, send keyboard shortcuts, and discover UI elements.

    $5

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Windows Click & Write — Desktop Automation & UI Control

    Windows Click & Write — Desktop Automation & UI Control

    Example session with this skill installed

    Find the Notepad window, type 'Hello World' into the main editor, and save the file.

    • Read your context and instructions
    • Compiled the windows click

    I have identified the Notepad process, entered the text, and triggered the save dialog.

    Desktop Automation Log

    ActionTargetResult
    list_windowsDesktopFound "Untitled - Notepad" (process: notepad)
    list_elements"Untitled - Notepad"Found Edit control (automationId: "15")
    type_textEdit (ID: 15)Entered "Hello World"
    send_keysSystemSent "Ctrl+S"
    list_elements"Save As"Detected save dialog buttons

    Next steps

    1. Use type_text on the "File name" element to specify a path.
    2. Call click_element on the "Save" button to commit the file to disk.
    3. Use send_keys with "Alt+F4" if you want to close the application.

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

    About this skill

    Developers building desktop-capable AI agents often struggle to bridge the gap between LLM reasoning and local Windows execution. This skill provides a bridge using the Model Context Protocol to control any Windows application, whether it is a native Win32 app, a WPF interface, or a custom-drawn GUI.

    What it does

    • Window discovery lists all active top-level windows with their process names and titles.
    • Element inspection scans target windows for interactive controls like buttons, checkboxes, and tabs.
    • Targeted clicking executes mouse actions on specific UI elements using names or automation IDs.
    • Coordinate interaction performs raw clicks at absolute pixel positions for custom canvases or games.
    • Field input locates specific text fields and enters strings with optional clearing and Enter-key execution.
    • System shortcuts triggers complex keyboard combinations like Ctrl+S, Alt+F4, or Win+D.

    How it works

    1. Discovery involves running list_windows to identify the target application and its current state.
    2. Inspection uses list_elements to map out the UI tree and retrieve unique automation IDs for precision.
    3. Execution calls tools like click_element or type_text to drive the application UI through Windows UI Automation.

    Frameworks & tools

    This skill is built for Windows environments and requires the .NET runtime. It utilizes Windows UI Automation (UIA) patterns and the Model Context Protocol (MCP) for agent communication.

    Why this beats prompting it yourself

    Writing raw scripts for Windows automation is brittle and fails when windows resize or DPI scales change. This skill handles coordinate fallback and UIA pattern matching internally, allowing agents to navigate complex GUI hierarchies without manual coordinate mapping.

    Use cases

    • Automate data entry from a web browser into a legacy Win32 accounting application.
    • Orchestrate multi-step workflows across professional tools like Photoshop or Blender.
    • Build automated QA agents that verify UI state in native desktop software.
    • Trigger system-level actions and window management via keyboard shortcuts.

    Known limitations

    Requires the WindowsClickAndWriteMCP .NET tool installed locally. Interaction is limited to the active desktop session and visible windows.

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

    Requires .NET runtime and local installation of the windows-click-and-write global tool. Only supports Windows desktop environments.

    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

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 16 days ago

    Windows only

    Software
    WindowsClickAndWriteMCP.NET 10 Runtime

    Install the MCP with dotnet tool install -g WindowsClickAndWriteMCP.

    Permissions

    Terminal / Shell
    Write Files

    Requires desktop UI Automation access to interact with Windows applications and send keyboard/mouse input.

    Listed16 days ago

    What's inside

    Frequently Asked Questions

    This skill bridges the gap between LLM reasoning and the Windows OS by providing a standardized MCP interface to inspect UI trees, identify automation IDs, and execute precise mouse and keyboard actions.

    The skill is compatible with any AI agent or framework that supports the Model Context Protocol (MCP), such as Claude Desktop or custom agents built on the MCP SDK.

    It requires a Windows environment with the .NET runtime installed; you must install the WindowsClickAndWriteMCP .NET tool locally for the agent to communicate with your desktop.

    Yes, it utilizes Windows UI Automation (UIA) to interact with a wide range of architectures including legacy Win32 apps, modern WPF/UWP interfaces, and many custom-drawn GUIs.

    You receive the MCP server configuration details and the necessary documentation to connect your AI agent to the local .NET automation bridge.

    The skill is designed for the active desktop session and can only interact with windows that are reachable via the UI Automation tree; it cannot interact with secure system screens like the Windows UAC prompt.

    New in Agents & Orchestration