LaunchKit · 2026
Back to Skills

midscene-computer-automation

Vision-driven desktop automation using Midscene.

2
1.4k downloads
by @quanru

Setup & Installation

openclaw skills install @quanru/midscene-computer-automation

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install midscene-computer-automation

Version History

v1.0.3Mar 7, 2026 - Version note by skill developer:

Version 1.0.3 - Enforces a new requirement to proactively report automation results after task completion, summarizing actions, findings, screenshots, and files. - Adds an explicit "Report results" step to the workflow and documents it as best practice. - Updates example environment variable setup with new supported models (Qwen 3.5, Doubao Seed 2.0 Lite). - Minor naming update: skill is now "desktop-computer-automation". - Refines and clarifies documentation, especially around closing response loops and model selection.

What This Skill Does

Controls macOS, Windows, and Linux desktops with natural language using Midscene.js. Operates from screenshots, so it works with any visible UI without requiring DOM access or accessibility labels. Automates clicks, typing, window management, and app interactions across any application.

Unlike Selenium or AppleScript, it works with any app on any stack because it reads the screen directly rather than relying on DOM structure or accessibility APIs.

When to use it

  • Automating repetitive form entry in a legacy desktop app
  • Taking targeted screenshots of specific windows for documentation
  • Launching apps and navigating their menus via text commands
  • Extracting visible on-screen data from any GUI application
  • Running multi-step workflows across different desktop programs

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: Open Chrome, search for the weather in New York, and tell me the result

AGENT
  1. 1Connect to the desktop with `npx @midscene/computer@1 connect`
  2. 2Open Chrome using the system launcher (`open -a 'Google Chrome'` on macOS)
  3. 3Take a screenshot to confirm Chrome is in the foreground
  4. 4Run `act --prompt "search for weather in New York and read the current conditions from the page"` to perform the search and extract results
  5. 5Disconnect and report the weather information extracted from the screen
OUTPUT

Current weather conditions for New York, with a screenshot showing the search result page

Requirements

Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.

MIDSCENE_MODEL_API_KEY from a supported visual AI model provider (Google Gemini, Alibaba Dashscope, Doubao, or OpenRouter)MIDSCENE_MODEL_NAME, MIDSCENE_MODEL_BASE_URL, and MIDSCENE_MODEL_FAMILY set to match the chosen provider