Bot Screen Control

    1

    Drives an X11 desktop with real mouse and keyboard: screenshots, clicks, drags, typing, no OCR.

    Free

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    About this skill

    Drive a headless X11 desktop (Xfce on Xvnc, or any X11/XWayland session) with real pointer and keyboard events from a single Python script. No AT-SPI, no accessibility tree, no OCR, no MCP server: look at a screenshot, click a coordinate, verify with another screenshot.

    Built for the case every vision-based approach breaks: SPA login walls, canvas apps, native windows and a desktop whose accessibility stack is missing or lying.

    Commands

    • shot — capture, with --grid N for a labelled coordinate grid and cursor crosshair
    • click / dclick / move — with eased pointer glides and --expect-change (reports whether the screen actually changed)
    • drag, scroll, type (Unicode via clipboard), fill X Y "text" (click, select-all, clear, type)
    • key, windows (list/raise/close/focus), wait-change, wait-stable
    • record / record-review — one frame per tick, lists frames where the screen changed
    • check — environment self-check before the first real action

    Method it enforces: screenshot → locate → act → verify with a new screenshot. Every command prints one line of JSON (--human for text), so results stay machine-readable inside an agent loop.

    Requires Linux with an X11 session (XWayland windows work, native Wayland windows do not), ffmpeg, xdotool, and Python 3.10+ with Pillow. xclip for clipboard-based Unicode typing, setxkbmap for layout switching.

    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 any payment.

    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 forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed today

    • Free with an Agensi account

    Requires

    Linux with X11 (XWayland ok)
    FFmpeg
    xdotool
    Python 3.10+ and Pillow
    xclip (recommended)
    setxkbmap (layout switching)

    Permissions

    Terminal / Shell
    Read Files
    Environment Variables
    Listedtoday

    What's inside

    Frequently Asked Questions

    Drives an X11 desktop with real mouse and keyboard: screenshots, clicks, drags, typing, no OCR.

    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 Bot Screen Control 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 Workflow Automation

    Free