跳到正文
cccskills
免费在 GitHub 公开

host-computer-use-macos

Control native macOS apps through named buttons, fields, and menus using accessibility data, which describes interface elements. The skill also guides window actions and checking fresh screenshots to confirm what actually changed.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Backend-specific macOS guidance for `computer_use_remote`. Load when a tool result reports backend_family/backend_id `macos` or Accessibility-tree features. Covers AX structural targeting, macOS window actions, and screenshot verification.

集成工具Docker
查看安装方法

适用场景

  • Press named buttons and menu items in macOS apps
  • Enter values into native app text fields
  • Hide or minimize a window and verify the result

包含的文件(1)

  • SKILL.md4.8 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Host Computer Use - macOS

Use this after host-computer-use when the connected A0 CLI reports the macOS computer-use backend.

Do not use this skill for Linux, Windows, Xpra, Docker, or browser-only tasks. If the backend is not macOS or does not advertise Accessibility-tree support, skip AX actions and follow the generic host computer-use rules.

macOS AX Targeting

macOS backends can advertise structural Accessibility features:

  • accessibility-tree-snapshot
  • accessibility-structural-targeting
  • accessibility-element-click

When these features are present, prefer structural targeting over pixel clicks for named controls such as buttons, menu items, text fields, sheets, alerts, toolbar items, and sidebar rows.

If the backend also advertises native-window-list, window-state, element-index-targeting, or background-dispatch, prefer the generic background loop from host-computer-use: list_windows -> get_window_state -> element_action. If those features are absent, use the AX snapshot/action flow below.

With app-scoped-semantic-targeting, element_action also accepts top-level pid or window_id to scope semantic matching, or target.app_name / target.bundle_id to select one app. Use identifiers from list_windows; app names and bundle IDs match exactly, ignoring case. Without this feature, use get_window_state and its top-level element_index for another app/window.

For example, replace the app identifier and control title with observed values:

{
  "tool_name": "computer_use_remote",
  "tool_args": {
    "action": "element_action",
    "target": {
      "bundle_id": "com.example.editor",
      "role": "AXButton",
      "title": "Save"
    },
    "operation": "press",
    "dispatch": "background"
  }
}

Use ax_snapshot to inspect the frontmost app's bounded Accessibility tree:

{
  "tool_name": "computer_use_remote",
  "tool_args": {
    "action": "ax_snapshot",
    "max_depth": 4,
    "max_nodes": 200
  }
}

The snapshot returns element paths, roles, labels, frames, enabled/focused state, actions, and child nodes. Use it to choose an element, not as final visual proof.

Use ax_action for a structural action:

{
  "tool_name": "computer_use_remote",
  "tool_args": {
    "action": "ax_action",
    "target": {
      "role": "AXButton",
      "title": "OK"
    },
    "operation": "press"
  }
}

Supported operations are:

  • press: activate a button, menu item, checkbox, or similar control
  • focus: focus a text field or focusable element
  • set_value: set a value; pass value or text

Targeting options:

  • Prefer a semantic target when the control has a stable title, description, value, identifier, role, or subrole.
  • Use a path returned by the latest ax_snapshot only while the UI is unchanged.
  • If an action reports ambiguity, take a fresh snapshot and narrow the target with role plus title/description/identifier.
  • If an action reports a missing target, take a fresh snapshot before trying coordinates.

AX actions are attempts, not proof. They attach a fresh screenshot after state-changing actions; inspect that image before saying the requested outcome happened.

Do not assume macOS work happened in the background unless the tool result explicitly says actual_dispatch=background. If the result says background_unavailable, use foreground dispatch only when foreground control is acceptable.

macOS Window Actions

For active-app window tasks, macOS shortcuts are usually:

  • Command+H: hide the active app
  • Command+M: minimize the active window

Treat these as attempts. After any hide or minimize shortcut, inspect the fresh screenshot. If the target window is still visible, say the attempt failed or switch strategy; do not type follow-up text into the focused app unless the screenshot clearly shows the intended target.

When a visible close/minimize/full-screen button or menu item is accessible in the AX tree, prefer ax_snapshot plus ax_action over a small coordinate click.

Permissions

macOS Screen Recording affects screenshots. Accessibility/Input Monitoring affect structural targeting and input. If computer_use_remote returns COMPUTER_USE_REARM_REQUIRED, COMPUTER_USE_APPROVAL_REQUIRED, or status=rearm required, stop immediately and ask the user to run /computer-use on in the A0 Launcher chat when using Launcher Host access, or in A0 CLI otherwise, and approve the macOS prompt if shown.

Do not bypass a permission failure with server screenshots, Docker commands, linux-desktop, or browser fallbacks.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Create specialized Agent Zero profiles by defining their roles, working methods, and delegation criteria. The skill prepares configuration files and instructions, with optional custom tools, extensions, and model preset selection when needed.

中文简介正在准备中。当前显示英语简介。

  • Create a specialist agent for data analysis
  • Define when to delegate work to an agent
  • Customize an agent's workflow and response format
agent0ai/agent-zero2万2026年10月15日 更新

Build, improve, review, or troubleshoot Agent Zero plugins for local use or community distribution. Follow plugin structure and installation rules, verify behavior in the target runtime, and prepare repository and Plugin Index contributions when requested.

中文简介正在准备中。当前显示英语简介。

  • Building an Agent Zero plugin for local use
  • Reviewing an existing plugin's structure and behavior
  • Investigating plugins that fail to load or run
agent0ai/agent-zero2万2026年10月15日 更新

Operate Agent Zero projects, chats, and tasks, or develop new tools, extensions, and API features. The skill guides work through existing APIs, relevant documentation, current source code, and checks appropriate to the change.

中文简介正在准备中。当前显示英语简介。

  • Manage Agent Zero projects and chats
  • Develop custom tools and extensions
  • Add API endpoints or WebUI features
agent0ai/agent-zero2万2026年10月15日 更新

Find Agent Zero plugins that match a task, compare candidates and their requirements, and manage installation, updates, settings, activation, and removal. It also supports security scans and checks the resulting plugin state through framework management APIs.

中文简介正在准备中。当前显示英语简介。

  • Find and compare plugins for a specific task
  • Review service, credential, and cost requirements before installation
  • Scan, install, or update a plugin
agent0ai/agent-zero2万2026年10月15日 更新

Automate web page tasks such as clicking, filling forms, uploading and downloading files, and taking screenshots. Work across tabs using a browser on the connected host machine or inside a Docker container.

中文简介正在准备中。当前显示英语简介。

  • Filling web forms and selecting options
  • Uploading or downloading files through websites
  • Capturing screenshots to inspect page appearance
agent0ai/agent-zero2万2026年10月15日 更新

Create, edit, and install extensions for Agent Zero Browser, including extensions from Chrome Web Store. It guides permission reviews and checks for suspicious behavior, with new extensions built as readable files that users can inspect.

中文简介正在准备中。当前显示英语简介。

  • Create a browser extension for a specific website
  • Modify an existing extension
  • Install an extension from Chrome Web Store
agent0ai/agent-zero2万2026年10月15日 更新

查看 agent0ai 的全部技能

报告此技能的问题