Agent skill

macOS Control Skill

当用户要求 AI 直接操作他的 macOS 桌面时触发：打开某个 App、点击某个按钮、填写窗口里的表单、读取当前屏幕内容、自动化本地 GUI 流程。典型说法"帮我在访达里…"、"帮我在某 App 里点一下…"、"看看我屏幕上显示的是什么"。仅在 OpenLoaf Desktop（macOS）中可用；非桌面端会返回 desktop-only 错误，应改用 BrowserAct…

AGPL-3.0Auto-check passed

Install macOS Control Skill

skills CLI

$ npx skills add OpenLoaf/OpenLoaf --skill macos-control-skill -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install OpenLoaf/OpenLoaf macos-control-skill --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/OpenLoaf/OpenLoaf.git skills-src && mkdir -p .claude/skills && cp -r skills-src/apps/server/src/ai/builtin-skills/macos-control .claude/skills/macos-control-skill && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "macos-control-skill" agent skill from https://github.com/OpenLoaf/OpenLoaf/tree/main/apps/server/src/ai/builtin-skills/macos-control into .claude/skills/macos-control-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "macos-control-skill", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/OpenLoaf/OpenLoaf/tree/main/apps/server/src/ai/builtin-skills/macos-control

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add OpenLoaf/OpenLoaf --skill macos-control-skill -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install OpenLoaf/OpenLoaf macos-control-skill --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/OpenLoaf/OpenLoaf.git skills-src && mkdir -p .agents/skills && cp -r skills-src/apps/server/src/ai/builtin-skills/macos-control .agents/skills/macos-control-skill && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "macos-control-skill" agent skill from https://github.com/OpenLoaf/OpenLoaf/tree/main/apps/server/src/ai/builtin-skills/macos-control into .agents/skills/macos-control-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "macos-control-skill", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add OpenLoaf/OpenLoaf --skill macos-control-skill -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install OpenLoaf/OpenLoaf macos-control-skill --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/OpenLoaf/OpenLoaf.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/apps/server/src/ai/builtin-skills/macos-control .cursor/skills/macos-control-skill && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "macos-control-skill" agent skill from https://github.com/OpenLoaf/OpenLoaf/tree/main/apps/server/src/ai/builtin-skills/macos-control into .cursor/skills/macos-control-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "macos-control-skill", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/OpenLoaf/OpenLoaf.git --path apps/server/src/ai/builtin-skills/macos-control

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add OpenLoaf/OpenLoaf --skill macos-control-skill -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install OpenLoaf/OpenLoaf macos-control-skill --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/OpenLoaf/OpenLoaf.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/apps/server/src/ai/builtin-skills/macos-control .gemini/skills/macos-control-skill && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "macos-control-skill" agent skill from https://github.com/OpenLoaf/OpenLoaf/tree/main/apps/server/src/ai/builtin-skills/macos-control into .gemini/skills/macos-control-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "macos-control-skill", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install OpenLoaf/OpenLoaf macos-control-skill

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add OpenLoaf/OpenLoaf --skill macos-control-skill -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/OpenLoaf/OpenLoaf.git skills-src && mkdir -p .github/skills && cp -r skills-src/apps/server/src/ai/builtin-skills/macos-control .github/skills/macos-control-skill && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "macos-control-skill" agent skill from https://github.com/OpenLoaf/OpenLoaf/tree/main/apps/server/src/ai/builtin-skills/macos-control into .github/skills/macos-control-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "macos-control-skill", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add OpenLoaf/OpenLoaf --skill macos-control-skill -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install OpenLoaf/OpenLoaf macos-control-skill --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/OpenLoaf/OpenLoaf.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/apps/server/src/ai/builtin-skills/macos-control .opencode/skills/macos-control-skill && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "macos-control-skill" agent skill from https://github.com/OpenLoaf/OpenLoaf/tree/main/apps/server/src/ai/builtin-skills/macos-control into .opencode/skills/macos-control-skill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "macos-control-skill", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: macos-control-skill
GitHub stars: 108
Token cost: ~1.6k tokens
SKILL.md length: 362 words
Files: 1
Skills in repo: 33
Repo updated: May 14, 2026
First seen: Oct 7, 2026
Licence: AGPL-3.0

At a glance

Works in 4 steps: 看 Survey 的 Menu bar 段 —— 几乎所有 app… → 菜单项如果带 (⌘⇧X) 这种 shortcut，用 MacosAct… → 走不通再 observe 截图，按像素 coord click → …
SKILL.md covers 核心思维：先理解，再动手, 工具全景, 执行路径的优先级（由 Survey 告诉你） and Survey 返回长什么样, plus 7 more sections
Reaches github.com

What it does

macOS Control Skill is an agent skill from OpenLoaf/OpenLoaf. 当用户要求 AI 直接操作他的 macOS 桌面时触发：打开某个 App、点击某个按钮、填写窗口里的表单、读取当前屏幕内容、自动化本地 GUI 流程。典型说法"帮我在访达里…"、"帮我在某 App 里点一下…"、"看看我屏幕上显示的是什么"。仅在 OpenLoaf Desktop（macOS）中可用；非桌面端会返回 desktop-only 错误，应改用 BrowserAct 或让用户自己操作。不用于：网页内交互（→ browser-ops-skill）、本地文件读写（→ Read/Edit/Write）。

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with macOS. The repository describes itself as: 🍞Open-source, local-first AI workspace with Agents, multi-model chat (GPT/Claude/Gemini/DeepSeek), Notion-like docs, AI image & video generation, email, calendar & terminal…. The licence is AGPL-3.0.

Example prompts

“帮我在访达里…”
“帮我在某 App 里点一下…”
“看看我屏幕上显示的是什么”
“/macos-control-skill”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

看 Survey 的 Menu bar 段 —— 几乎所有 app 的菜单栏都可以 menu_click
菜单项如果带 (⌘⇧X) 这种 shortcut，用 MacosAct type="key" 更稳
走不通再 observe 截图，按像素 coord click
完全走不通时停下来告诉用户"这条路径我没找到安全做法"，别猜

What it can do on your machine

Read from SKILL.md and the folder at commit f7eccf6. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
- github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

macOS Control Skill loads about 1.6k tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 362 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~74
When it runs · the whole SKILL.md, loaded when a task matches: ~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from OpenLoaf/OpenLoaf at commit f7eccf6, republished under its AGPL-3.0 licence (© OpenLoaf). 362 words, ~1,623 tokens.

Download SKILL.mdSave it as .claude/skills/macos-control-skill/SKILL.md (or your agent's skills folder).

name: macos-control-skill
description: 当用户要求 AI 直接操作他的 macOS 桌面时触发：打开某个 App、点击某个按钮、填写窗口里的表单、读取当前屏幕内容、自动化本地 GUI 流程。典型说法"帮我在访达里…"、"帮我在某 App 里点一下…"、"看看我屏幕上显示的是什么"。**仅在 OpenLoaf Desktop（macOS）中可用**；非桌面端会返回 desktop-only 错误，应改用 `BrowserAct` 或让用户自己操作。**不用于**：网页内交互（→ `browser-ops-skill`）、本地文件读写（→ `Read`/`Edit`/`Write`）。
tools: MacosSurvey, MacosObserve, MacosAct, MacosListWindows, MacosCaptureWindow

macOS 桌面控制指南

核心思维：先理解，再动手

不要看到 app 就直接 click/type。人类操作一个陌生 app，会先"逛一圈"——看它长什么样、有哪些入口、哪里是关闭按钮、哪里是业务区。你也必须这样。

三阶段框架：

1. Survey（理解）  → MacosSurvey(app) 拿 app 心智模型
2. Plan（选路径）  → 按 Survey 给的"Recommended path order"挑一条路
3. Act + Verify   → MacosAct 执行；MacosObserve 确认结果

跳过 Survey 直接 Act 是最常见的失败。微信 / QQ / 飞书 / 钉钉这类自绘 UI 的 AX tree 只有 3 个窗口按钮（close / min / zoom），模型凭猜点 path=["0","0"] 就会命中红色关闭按钮，整个 app 被关掉。Survey 会把这类陷阱提前告诉你。

工具全景

工具	什么时候用
`MacosSurvey(app)`	每次接触某个 app 的第一步。返回 app 心智模型：已知 intent、AX 丰富度、菜单栏地图、窗口清单、推荐执行顺序。会话内缓存 5 分钟。
`MacosObserve(appFilter?)`	看当前具体 UI 状态——截图 + AX 树 + 窗口清单。Survey 之后用，以及每次 `MacosAct` 后用来验证结果。
`MacosAct`	执行动作。支持 `intent / launch_app / menu_click / applescript / key / click / type / scroll / drag / wait / ax_action`。
`MacosListWindows(appFilter?)`	仅枚举窗口（比 Observe 轻量）。多窗口场景里挑特定 window 用。
`MacosCaptureWindow(windowID)`	按 windowID 截特定窗口，可以截到被遮挡或最小化的窗口（Window Server 保留合成 buffer）。

全部仅在 OpenLoaf Desktop（macOS） 可用。非桌面端工具不注册；会话里不要尝试调它们。

执行路径的优先级（由 Survey 告诉你）

MacosSurvey 返回里有一段 Recommended path order，顺序从高确定性到低：

1. Known intents       MacosAct type="intent"          确定性 100%
2. Menu navigation     MacosAct type="menu_click"      自绘 UI 也能用
3. Keyboard shortcut   MacosAct type="key"             读菜单栏的 shortcut 字段
4. AX path click       MacosAct type="click" ref=...   仅当 Survey 判定 ax-rich 时安全
5. Coord click         MacosAct type="click" point=... 最后手段，从截图读像素

严格按顺序下探。能用前面的就不走后面。Survey 判 self-drawn 的 app 上，第 4 步直接跳过——对窗口 chrome 按钮的 AX path click 会被拦下（返回 WINDOW_CHROME_BLOCKED 错误）。

Survey 返回长什么样

App: 微信 (WeChat.app) (com.tencent.xinWeChat, pid=86795)

AX profile: self-drawn — AXWindow children are only chrome buttons
  richness: 0.995 (203 nodes)
  windowChildRoles: [AXCloseButton, AXFullScreenButton, AXMinimizeButton]

Known intents (from registry):
  - id: open_moments    — 打开朋友圈 / Open Moments feed
  - id: open_chats      — 切换到聊天列表
  - id: open_discover   — 打开"发现"页
  ...

Menu bar (34 entries with shortcuts, sample):
  - 文件 > 锁定微信  (⌘L)
  - 视图 > 聊天  (⌘1)
  - 视图 > 朋友圈  (⌘⇧4)
  ...

Windows (2):
  - windowID=227474 visible 1060×859 "Weixin"  (main)
  - windowID=260481 hidden 710×831

Recommended path order:
  1. Known intents (highest confidence): MacosAct type="intent" — 5 registered
  2. Menu navigation: MacosAct type="menu_click" — 34 reachable entries
  3. Keyboard shortcut: MacosAct type="key"
  4. AX path click: **DO NOT USE** on this app.
  5. Coordinate click: last resort.

"Known intents" 就是别人已经替你踩过坑的路径。优先用。

典型场景

场景 A：打开微信朋友圈

1. MacosAct { type: "launch_app", app: "WeChat" }
2. MacosSurvey { app: "WeChat" }
   → 看到 Known intents 里有 open_moments
3. MacosAct { type: "intent", app: "WeChat", intent: "open_moments" }
4. MacosObserve { appFilter: "WeChat" } — 验证朋友圈已打开

不要调完 launch_app 就直接 observe + click AX tree。那是老路径，会命中关闭按钮。

场景 B：在 Safari 打开 github.com

1. MacosSurvey { app: "Safari" }
   → Known intents 里有 open_url（args: url required）
2. MacosAct { type: "intent", app: "Safari", intent: "open_url", args: { url: "https://github.com" } }
3. MacosObserve { appFilter: "Safari" } — 验证页面加载

场景 C：读屏幕

用户问「我屏幕上显示什么」、「当前 App 里 xx 是什么」：直接一次 MacosObserve，从截图 + AX 树提炼答案。不需要 Survey，不需要 Act。

场景 D：未注册的 intent / ax-rich app

Survey 返回 ax-rich 且没有对应 intent 时，优先 menu_click / key，其次 AX path click：

1. MacosSurvey { app: "Finder" } → ax-rich, 推荐 menu_click / AX path click
2. 要新建窗口 → 看菜单栏 "文件 > 新建 Finder 窗口 (⌘N)"
3. MacosAct { type: "key", keys: ["cmd", "n"] } — 用快捷键比 click 稳
4. MacosObserve 验证

场景 E：多窗口（微信主窗口 + 图片预览）

1. MacosSurvey { app: "WeChat" } → Windows: 2 个，windowID 分别 227474/260481
2. MacosCaptureWindow { windowID: 227474 } — 专截主窗口（即便被预览挡住）
3. 后续 MacosAct click 的坐标基准已更新为这个窗口的图

场景 F：填原生窗口表单（AppKit app）

Survey 看到 ax-rich，目标元素有 AX role=AXTextField：

1. MacosObserve { appFilter: "..." } 拿输入框 ref
2. MacosAct { type: "click", ref: { app, path: [...] } } 聚焦
3. MacosAct { type: "type", text: "..." }
4. MacosAct { type: "ax_action", ref: { app, path: [submit button] }, action: "AXPress" }
5. MacosObserve 验证

当 Survey 没有你要的 intent 怎么办

看 Survey 的 Menu bar 段 —— 几乎所有 app 的菜单栏都可以 menu_click
菜单项如果带 (⌘⇧X) 这种 shortcut，用 MacosAct type="key" 更稳
走不通再 observe 截图，按像素 coord click
完全走不通时停下来告诉用户"这条路径我没找到安全做法"，别猜

Show full SKILL.md (163 more words)Show less

铁律

第一次接触某 app，先 Survey。不 Survey 就 Act 是最常见的失败，特别是对自绘 UI。
优先走 Survey 推荐的第一条路（Known intents）。自己另辟蹊径多半翻车。
每次 MacosAct 后 MacosObserve。UI 是有状态的，你无法预测结果。例外：intent / menu_click 成功后如果不需要二次动作，可以跳过 verify。
AX path click 只在 Survey 判 ax-rich 的 app 上用。mixed 谨慎，self-drawn 禁止——chrome 按钮会被硬拦（WINDOW_CHROME_BLOCKED）。
坐标点击是最后手段。必须先 observe 看到截图像素位置；连续 2 次 coord click 后 UI 没变化，立即停止并告知用户定位失败。
敏感 app 前台（密码管理器 / 银行 / Keychain）立即停止，让用户自己操作。
缺权限时：系统设置面板已自动弹出，用自然语言告诉用户去启用 OpenLoaf，等用户确认再继续。不要重试。
非 macOS 桌面端：立即返回 desktop-only，改用 BrowserAct 或交回用户。

权限

首次调用会提示缺权限。server 已自动打开对应系统设置面板。需要：

screen：屏幕录制（Survey / Observe / CaptureWindow 都要）
accessibility：辅助功能（AX 树读取 + 合成输入）

某些系统级 app 授权后仍需重启 OpenLoaf Desktop。

坐标空间（退化到 point 时）

point.{x,y} 就是最近一次 MacosObserve 或 MacosCaptureWindow 截图上的像素坐标——图上目标在哪个像素，就把那个像素塞给 click/scroll/drag。工具内部自动换算到屏幕坐标，你不用关心 retina 缩放、窗口偏移或多显示器。

observe/capture_window 返回里 Screenshot: window 2120×1718 px 的那个数字就是坐标范围
必须先调用过一次 observe 或 capture_window 才能用坐标动作；否则工具拒绝

安全与隐私

密码、银行、密钥链类 App 不要 Survey / Observe / Act。遇到 1Password / Keychain / 银行 app 前台，立即停止并让用户自己操作。
截图存会话附件目录，随会话清理；不上传云端、不训练。
不确定屏幕状态时先 observe 一次再判断；不要臆测。

错误诊断

permissionsMissing → 已自动开设置面板，提示用户授权 → 等确认
desktop-only → 当前非桌面端；告诉用户切到 OpenLoaf Desktop
WINDOW_CHROME_BLOCKED → 你点了窗口 chrome 按钮。按返回里的 4 个候选路径重新规划（menu_click / key / coord / URL）。不要傻乎乎加 confirm_window_chrome:true 强推，除非真的要关窗
intent 未找到 → 用 MacosSurvey 看一下可用 intent 列表；或降级到 menu_click
点击无反应 → 重新 observe，看目标节点是否真可点、是否被遮挡
中途前台切换 → observe 的 app 和 act 的 app 不一致，先 key cmd+tab 切回再 act

Files

Just SKILL.md in apps/server/src/ai/builtin-skills/macos-control of OpenLoaf/OpenLoaf.

Open the folder on GitHubat commit f7eccf6

Compare with similar skills

macOS Control Skill next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

macOS Control Skill compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
macOS Control Skill this skillOpenLoaf/OpenLoaf	108	—	~1.6k	Automated safety check: Pass	AGPL-3.0	4 mo ago
Site ArchitectureAvdLee/RocketSimApp	803	11 repos	~3.3k	Automated safety check: Pass	Custom licence	today
Engine Whats Newflutter/flutter	179k	—	~978	Automated safety check: Pass	BSD-3-Clause	today
macOS Spm App PackagingDimillian/Skills	4k	5 repos	~1.2k	Automated safety check: Pass	MIT	6 mo ago
Openclaw Live Updateropenclaw/openclaw	392k	—	~3.7k	Automated safety check: Pass	MIT	today
Orca iOS Simulator Controlstablyai/orca	87k	1 repos	~584	Automated safety check: Pass	Apache-2.0	today

Similar skills

Site Architecture
AvdLee/RocketSimApp
When the user wants to plan, map, or restructure their website's page hierarchy, navigation, URL structure, or internal linking.
803 GitHub starsUsed in 11 repos~3.3k tokens
Marketing & SEOAuto-check passed
Engine Whats New
flutter/flutter
Generates the "what's new" release summary and diff file for changes in the Flutter engine (//engine/src/flutter) between two releases (e.g., 3.47 vs 3.44).
179k GitHub stars~978 tokensUpdated today
MobileAuto-check passed
macOS Spm App Packaging
Dimillian/Skills
Scaffold, build, and package SwiftPM-based macOS apps without an Xcode project.
4k GitHub starsUsed in 5 repos~1.2k tokens
MobileAuto-check passed
Openclaw Live Updater
openclaw/openclaw
Maintain the canonical live OpenClaw main checkout, macOS LaunchAgent-managed Gateway, local macOS app, exact-head main CI, and recurring full release validation.
392k GitHub stars~3.7k tokensUpdated today
DevOps & CloudAuto-check passed
Orca iOS Simulator Control
stablyai/orca
iOS Simulator control from inside Orca, with the live device view in Orca's emulator pane. Use when driving a booted Apple Simulator on macOS: taps, gestures…
87k GitHub starsUsed in 1 repo~584 tokens
MobileAuto-check passed
Mole Bug Patterns
tw93/Mole
A catalog of recurring bug shapes in the Mole Mac cleaner, used to review safety-sensitive diffs for deletion safety, unbounded commands, shell traps and weak tests.
70k GitHub stars~2k tokensUpdated today
DevelopmentAuto-check passed

Questions about macOS Control Skill

What does macOS Control Skill do?

How do I install macOS Control Skill in Claude Code?

Run `npx skills add OpenLoaf/OpenLoaf --skill macos-control-skill -a claude-code`. Or copy the skill folder (apps/server/src/ai/builtin-skills/macos-control in OpenLoaf/OpenLoaf) into .claude/skills/macos-control-skill in your project. Claude Code loads it when a task matches its description.

How do I install macOS Control Skill in Codex?

Run `npx skills add OpenLoaf/OpenLoaf --skill macos-control-skill -a codex`. Or copy the skill folder (apps/server/src/ai/builtin-skills/macos-control in OpenLoaf/OpenLoaf) into .agents/skills/macos-control-skill in your project. Codex loads it when a task matches its description.

Can I use macOS Control Skill in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add OpenLoaf/OpenLoaf --skill macos-control-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/macos-control-skill, .gemini/skills/macos-control-skill, .github/skills/macos-control-skill and .opencode/skills/macos-control-skill in your project.

What does macOS Control Skill need to run?

SKILL.md names no scripts, command-line tools or credentials: macOS Control Skill is instructions for the agent only.

Does macOS Control Skill access the network?

SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is macOS Control Skill safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does macOS Control Skill use?

macOS Control Skill is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does macOS Control Skill use?

About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to macOS Control Skill?

Skills that share tags, products or a category with macOS Control Skill: Site Architecture (AvdLee/RocketSimApp, 803 stars), Engine Whats New (flutter/flutter, 179k stars), macOS Spm App Packaging (Dimillian/Skills, 4k stars) and Openclaw Live Updater (openclaw/openclaw, 392k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains macOS Control Skill?

OpenLoaf (a GitHub organization) maintains it in OpenLoaf/OpenLoaf, which has 108 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on May 14, 2026.

Source: OpenLoaf/OpenLoaf on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install macOS Control Skill

Facts

At a glance

What it does

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

macOS 桌面控制指南

核心思维：先理解，再动手

工具全景

执行路径的优先级（由 Survey 告诉你）

Survey 返回长什么样

典型场景

场景 A：打开微信朋友圈

场景 B：在 Safari 打开 github.com

场景 C：读屏幕

场景 D：未注册的 intent / ax-rich app

场景 E：多窗口（微信主窗口 + 图片预览）

场景 F：填原生窗口表单（AppKit app）

当 Survey 没有你要的 intent 怎么办

铁律

权限

坐标空间（退化到 point 时）

安全与隐私

错误诊断

Files

Compare with similar skills

Similar skills

More from OpenLoaf/OpenLoaf

Related

Questions about macOS Control Skill