hands-off: drive Windows apps without your mouse

    1

    Let your AI agent click buttons, fill in fields, pick menus and read windows in Windows desktop programs while you keep working. No cursor moves and no focus is stolen, even on a covered window or another monitor.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    hands-off: drive Windows apps without your mouse

    Example session with this skill installed

    Open Calculator on my second monitor and work out 12 + 30 without touching my mouse or taking my focus. I'm still typing in my editor.

    • Read your context and instructions
    • Compiled the hands-off

    Summary

    Calculator opened on monitor 2 without focus, 12 + 30 entered by AutomationId, result read back:

    42. Your editor kept the focus the whole time.

    What I did

    StepToolTargetResult
    1launchcalc.exe, monitor=2Calculator opened on monitor 2, focus stayed on your editor
    2treeCalculator, filter "Button"buttons found by id: num1Button, num2Button, plusButton, num3Button, num0Button, equalButton
    3invokeid=num1Button, id=num2Button12 entered
    4invokeid=plusButton+
    5invokeid=num3Button, id=num0Button30 entered
    6invokeid=equalButton=
    7readid=CalculatorResults"Display is 42"

    Check

    • The result was read from the Calculator display itself, not assumed from the clicks.
    • No cursor movement and no foreground change during the actions.

    Next steps

    • Want this again later? I can save it as recipes/calculator_add.json with ${a} and ${b} as inputs, so it runs in one call (or from a scheduled task with no agent).
    • Say close and I'll close the Calculator I opened (only that one).

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

    About this skill

    Most desktop automation borrows your mouse and keyboard: the cursor jumps, the window you were typing in loses focus, and you have to sit still until the agent is done. hands-off does it the other way. It talks to programs through Windows UI Automation and window messages (never SendInput), so the agent can work on monitor 2 while you keep working on monitor 1.

    This skill teaches the agent when and how to use the free, open-source hands-off MCP server (MIT).

    What the agent learns

    • The order of choice: the program's own API first (bpy, COM, CDP, a CLI), hands-off second, the real mouse only after asking you.
    • The flow: list_windows → tree (buttons, fields, ids) → invoke / type_text / menu / keys / click_xy → always check with read or capture.
    • Recipes: explore a task once, freeze it into a JSON recipe, then run it in one call (or with no agent at all, from a scheduler).
    • The measured traps: WinUI/UWP apps that grab focus, repeated ids in Open/Save dialogs, black captures, modal dialogs that block, Ctrl/Alt shortcuts that read the real keyboard.

    What works (measured)

    ProgramResult
    Win32/MFCfull tree, menus by WM_COMMAND, fields, buttons
    WinUI (new Notepad)write, read, File > Save
    UWP (Calculator)buttons and display by AutomationId
    Chrome/Edge/Electronbrowser chrome by UIA; page clicks by click_xy without moving the cursor
    Games, Photoshop canvas, Blender viewportno (they read the real mouse); use the app's API

    Measured with a person using the PC: 0 of 290 actions took the focus away from them.

    Requirements

    • Windows 10/11, uv, and the hands-off server registered once: claude mcp add -s user hands-off -- uvx --from git+https://github.com/MareAltaStudio/hands-off hands-off-mcp
    • Works with any agent that loads MCP servers (Claude Code, Cursor, Copilot...).

    Demo video, docs and source: https://github.com/MareAltaStudio/hands-off

    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.

    Windows 10/11 only. Programs that read the real mouse (games, the Photoshop canvas, the Blender viewport) can't be driven; use the app's own API. Web page content in Chrome/Edge is reached by click_xy, not by the UI tree. Minimized windows can't be captured (move them first). Ctrl/Alt shortcuts through keys fail in many programs. Requires the hands-off MCP server and uv.

    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

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 20 days ago

    • Free with an Agensi account

    Windows only

    Software
    hands-off MCPuv (Python tool runner)Python 3.10+Git

    Get the hands-off MCP server at github.com/MareAltaStudio/hands-off.

    Permissions

    Read Files
    Write Files
    Network Access
    Terminal / Shell

    The skill drives the hands-off MCP server, which reads and acts on the Windows desktop windows the agent names (UI Automation and window messages). Terminal: `launch` starts programs the agent asks for, and recipes can run a python step. Files: recipes are read from JSON files, captures can be saved as images, and every acting call is logged locally to %LOCALAPPDATA%\hands-off\actions.log. Network: only when installing (server from GitHub, packages from PyPI); the server itself makes no network calls.

    Listed20 days ago

    What's inside

    Frequently Asked Questions

    Unlike tools like PyAutoGUI that take over your cursor, this skill uses Windows UI Automation and window messages to interact with elements directly, allowing you to continue using your mouse and keyboard in other windows without interruption.

    The skill is compatible with any AI agent or platform that supports the Model Context Protocol (MCP), and it is specifically designed for Windows 10 and 11 environments.

    This listing is the skill: the SKILL.md that teaches your agent when and how to use hands-off. The hands-off MCP server itself is free and open source (MIT) on GitHub; you register it once with one command (see Requirements). Both are free.

    Measured: classic Win32/MFC apps (full tree, menus, fields, buttons), WinUI apps like the new Notepad, and UWP apps like Calculator. In Chrome/Edge/Electron the browser chrome is in the tree and page clicks go through click_xy. It can't drive programs that read the real mouse, such as games, the Photoshop canvas or the Blender viewport.

    Install uv, then run one command to register the server with your agent (claude mcp add ... for Claude Code, or the same command in your agent's MCP config). A built-in --selftest checks the install.

    WinUI/UWP apps try to take the focus on every action. While an action runs, hands-off marks the target window as non-activating, and a guard watches the foreground for 0.9 s and gives the focus back only if the target program took it. Measured with a person using the PC: 0 of 290 actions took their focus. A program that is just starting can still take it occasionally (2 of 18 launches, both Calculator).

    New in Agents & Orchestration

    Free