Skip to content
Agentmart
Submit a tool

desktop_automation

Vision-driven desktop automation loop for inspecting screens, locating UI elements, typing, and clicking.

Skill by ParisNeo

IndexedApache-2.0★ 13
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/parisneo-desktop-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 loop for inspecting screens, locating UI elements, typing, and clicking.

Use cases: design

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 and code. 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-automation

What's inside

Skill name
desktop_automation
Description
Vision-driven desktop automation loop for inspecting screens, locating UI elements, typing, and clicking.
License
Apache-2.0
Instructions
9 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • name: only lowercase letters, digits and single hyphens allowed

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Desktop Automation Skill

## Operating Loop
1. **OBSERVE**: Call `tool_computer_screenshot` to see the current screen. Never act blind.
2. **LOCATE**: Identify coordinates from the visual image or use natural-language element descriptions.
3. **ACT**: Click (`tool_computer_click`), type (`tool_computer_type`), or press hotkeys (`tool_computer_key`). Click into input fields before typing.
4. **VERIFY**: Always capture a follow-up screenshot to confirm the action succeeded before proceeding to the next step.
5. **TERMINATE**: When the target state is reached, describe the outcome and emit `<done/>`.

From ParisNeo/lollms_client, Apache-2.0.

More from ParisNeo/lollms_client

Signals

Stars
13
Forks
5
Open issues
0
Last commit (this folder)
Sep 28, 2026 (1 month ago)
Last release
Mar 5, 2025 (1 year ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

Same skill elsewhere

Copies of this SKILL.md published by others; search shows only one of them.

More from ParisNeo

Cite this page

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