Skip to content
Back to skills

Deskuse

ASecurity

Top-level cross-platform computer-use skill that bundles standalone macOS, Windows, and Linux runtimes with zero local Claude dependency and selects the correct platform payload at install/use time.

  • 3 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 9, 2026
toolspythonrustshellbashnoderails

Works with

  • cli
  • mcp

Security analysis

A96/100
  • mediumInstalls packages at runtime which could introduce malicious dependencies

Pro shows the line behind each finding and how to fix it

Scanned September 9, 2026

npx -y skills add Lord1Egypt/awesome-skill-forge --skill deskuse --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Deskuse?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Deskuse
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/lord1egypt-deskuse/badge)](https://www.skillsdirectory.com/skills/lord1egypt-deskuse)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: deskuse
version: 0.1.0
description: Top-level cross-platform computer-use skill that bundles standalone macOS, Windows, and Linux runtimes with zero local Claude dependency and selects the correct platform payload at install/use time.
tags:
  - skill
  - computer-use
  - automation
  - mcp
  - macos
  - windows
  - linux
---

# Cross-Platform Computer-Use Skill

Use this skill when the task needs a top-level portable computer-use skill that works across macOS, Windows, and Linux without depending on any local Claude installation, private native modules, or extracted app assets.

## What this skill does

- bundles standalone platform runtimes for `macOS`, `Windows`, and `Linux`
- installs one top-level skill that contains all three platform payloads
- selects the correct project for the current host platform
- preserves the standalone bootstrap model: each platform runtime creates its own virtualenv and installs public Python dependencies on first real run
- keeps platform-specific limitations explicit instead of pretending the hosts behave identically

## Installed layout

After installation, assume the top-level skill lives at:

```bash
~/.codex/skills/deskuse
```

The bundled projects are stored under:

```bash
~/.codex/skills/deskuse/project/platforms/macos
~/.codex/skills/deskuse/project/platforms/windows
~/.codex/skills/deskuse/project/platforms/linux
```

## Platform selection

Use the helper script from the installed skill root to resolve the active platform project:

```bash
bash ~/.codex/skills/deskuse/scripts/current-project.sh
```

On PowerShell:

```powershell
powershell -ExecutionPolicy Bypass -File $HOME/.codex/skills/deskuse/scripts/current-project.ps1
```

## Build

Always build the selected platform project, not all three at once:

```bash
cd "$(bash ~/.codex/skills/deskuse/scripts/current-project.sh)"
npm install
npm run build
```

## Run

```bash
cd "$(bash ~/.codex/skills/deskuse/scripts/current-project.sh)"
node dist/cli.js
```

## Validation notes

- `macOS` has been real-device validated in this workspace, including GUI typing round-trip through the MCP `type` tool.
- `Windows` and `Linux` are implemented, built, packaged, and published, but still need end-to-end runtime validation on real hosts.
- `Linux` currently targets `X11` first; Wayland can restrict screenshots, focus inspection, clipboard, and synthetic input.

## Guardrails

- Treat this host as trusted-local only.
- Do not tell the user to search a local Claude install for binaries or hidden assets.
- Be explicit about the current host platform and its validation status before claiming something is verified.
- Mention that current runtimes report `screenshotFiltering: none`, so action gating is handled at the MCP layer.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in tools →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.