Skip to content
Agentmart
Submit a tool

desktop-computer-automation

Vision-driven desktop automation using Midscene.

Skill by shawnwong84

IndexedLicense unknown★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/shawnwong84-desktop-computer-automation

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Vision-driven desktop automation using Midscene. Control your desktop (macOS, Windows, Linux) with natural language commands. Operates entirely from screenshots — no DOM or accessibility labels required. Can interact with all visible elements on screen regardless of technology stack. Triggers: open app, press key, desktop, computer, click on screen, type text, screenshot desktop, launch application, switch window, desktop automation, control computer, mouse click, keyboard shortcut, screen capture, find on screen, read screen, verify window, close app, minimize window, maximize window Powered by Midscene.js (https://midscenejs.com)

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/desktop-computer-automation

What's inside

Skill name
desktop-computer-automation
Description
Vision-driven desktop automation using Midscene. Control your desktop (macOS, Windows, Linux) with natural language commands. Operates entirely from screenshots — no DOM or accessibility labels required. Can interact with all visible elements on screen regardless of technology stack. Triggers: open app, press key, desktop, computer, click on screen, type text, screenshot desktop, launch application, switch window, desktop automation, control computer, mouse click, keyboard shortcut, screen capture, find on screen, read screen, verify window, close app, minimize window, maximize window Powered by Midscene.js (https://midscenejs.com)
License
unknown
Instructions
170 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • name: "desktop-computer-automation" does not match folder "midscene-computer-automation"
  • allowed-tools: must be a space-separated string

Files (3)

  • origin.json · .clawhub/
  • SKILL.md
  • _meta.json

The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub

More from shawnwong84/openclaw-workspace

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Mar 8, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
License unknown
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from shawnwong84

Cite this page

desktop-computer-automation skill. Agent Mart. https://agentmart.dev/skills/shawnwong84-desktop-computer-automation (last updated 2026-10-24)