mac-computer-use: Enable any LLM to control your computer with cross-platform support, featuring 3D modeling examples and live

Last updated: 2026-09-24 · Indexed by AgentSkillsHub · Auto-synced every 8h

How to install mac-computer-use

git clone https://github.com/To3akaRin/mac-computer-use.git

Taken from the project's README on GitHub. Check the security audit before running it.

Security audit verdict: SAFE · quality 68/100

None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

agent-skillscdpcodexcomputer-usemacosswift

Quick Facts

Stars	960
Forks	16
Language	JavaScript
Category	Codex Skill
License	MIT
Quality Score	68/100
Open Issues	4
Last Updated	2026-09-24
Created	2026-09-08
Platforms	codex, node
Est. Tokens	~14k

About mac-computer-use

mac-computer-use 让大模型自己操控电脑完成任务。让 Agent 看见窗口、主动操控电脑，替你完成相应的操作。基于开放的 Agent Skills 协议。一份技能包，接入多种 Agent。 Claude Code · Codex ·WorkBuddy · 豆包 · 千问 · Kimi Code · Cursor · OpenClaw · ZCode 全平台可用！支持读取完整技能文件并执行 macOS 本机命令的 runtime 可接入；具体安装方式与实测状态见兼容表。快速上手 · 核心能力 · 验收记录 · 命令接口 · 下载从参考照片，走到能旋转的 3D 展区，全程没有人碰鼠标，12 分钟。实战案例：中央展区 3D 建模。中央柱体、顶部圆环、弧形柜体、门架、终端和收银台，组成一个可以在浏览器中转动、检查的三维空间。 3,388 个三角面 · 117...

Compatible Skills

These tools work well together with mac-computer-use for enhanced workflows:

meshy-3d-agent — semantic(0.35)+complementary+same_lang+similar_pop+shared_platform (62%)
HiCAD — semantic(0.29)+complementary+same_lang+similar_pop+shared_platform (60%)
open-codex-computer-use — semantic(0.54)+complementary+similar_pop+shared_platform (59%)
agent-skills — semantic(0.21)+complementary+same_lang+similar_pop+shared_platform (57%)
hanzi-browse — semantic(0.20)+complementary+same_lang+similar_pop+shared_platform (57%)

mac-computer-use alternative? Top 6 similar tools

Looking for a mac-computer-use alternative? If you're comparing mac-computer-use with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

ghost-os by ghostwright · ⭐ 1.7k
Full computer-use for AI agents. Self-learning workflows. Native macOS. No screenshots required.
claude-code-apple-skills by rshankras · ⭐ 606
Claude Code skills for Apple platform development (iOS, macOS, iPadOS) — product validation, code generation,
mcp-linker by milisp · ⭐ 345
Manage MCP servers, skills and plugins across Claude Code, Codex, Cursor and more. Built-in marketplace, one-c
pilot-shell by maxritter · ⭐ 2.1k
Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software
Swift-Concurrency-Agent-Skill by AvdLee · ⭐ 1.6k
Add expert Swift Concurrency guidance to your AI coding tool (Agent Skills open format): safe concurrency, per
claude-workflow-v2 by CloudAI-X · ⭐ 1.4k
Universal Claude Code workflow plugin with agents, skills, hooks, and commands

More Codex Skill Tools

Explore other popular codex skill tools:

superset ⭐ 15.5k
humanizer ⭐ 57.5k
refly ⭐ 7.5k
nano-banana-pro-prompts-recommend-skill ⭐ 1.9k
pi-skills ⭐ 2.5k
skillkit ⭐ 1.5k
ai-maestro ⭐ 835
upskill ⭐ 762
Claude-to-IM-skill ⭐ 2.9k
learning-opportunities ⭐ 2.4k

View all Codex Skill tools →

Popular JavaScript Agent Tools

XHS-Downloader ⭐ 13.1k · MCP Server
xiaozhi-esp32-server ⭐ 11.0k · MCP Server
firecrawl-mcp-server ⭐ 7.7k · MCP Server
deep-research ⭐ 4.7k · MCP Server
brightdata-mcp ⭐ 2.7k · MCP Server

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Codex Skill tools