记忆

agent-desktop

Desktop automation via native OS accessibility trees using the agent-desktop CLI. Use when an AI agent needs to observe, interact with, or automate desktop applications (click buttons, fill forms, navigate menus, read UI state, toggle checkboxes, scroll, drag, type text, take screenshots, manage windows, use clipboard, manage notifications). Covers 58 command names (54 operational; four held-input names fail closed until daemon ownership exists) across observation, interaction, keyboard/mouse, app lifecycle, notifications (macOS), clipboard, wait, session lifecycle, and a `skills` command that bundles docs straight from the binary. Triggers on: "click button", "fill form", "open app", "read UI", "automate desktop", "accessibility tree", "snapshot app", "type into field", "navigate menu", "toggle checkbox", "take screenshot", "desktop automation", "agent-desktop", or any desktop GUI interaction task. Supports the macOS Phase 1 adapter, with Windows and Linux planned against the same cor

它能做什么

Desktop automation via native OS accessibility trees using the agent-desktop CLI. Use when an AI agent needs to observe, interact with, or automate desktop applications (click buttons, fill forms, navigate menus, read UI state, toggle checkboxes, scroll, drag, type text, take screenshots, manage windows, use clipboard, manage notifications). Covers 58 command names (54 operational; four held-input names fail closed until daemon ownership exists) across observation, interaction, keyboard/mouse, app lifecycle, notifications (macOS), clipboard, wait, session lifecycle, and a `skills` command that bundles docs straight from the binary. Triggers on: "click button", "fill form", "open app", "read UI", "automate desktop", "accessibility tree", "snapshot app", "type into field", "navigate menu", "toggle checkbox", "take screenshot", "desktop automation", "agent-desktop", or any desktop GUI interaction task. Supports the macOS Phase 1 adapter, with Windows and Linux planned against the same core contracts.

技能文档

这个技能的完整文档还没被收录,可以先到原始来源页查看。

相关技能

改任何文件前先看 diff、备份、等用户确认,安全升级已安装的代理技能。

92 次安装6 星标

用 CLI 驱动浏览器,凭稳定元素引用以省 token 的方式跑自动化。

116 次安装1 星标

This skill should be used when the user asks about Google Workspace automation via gogcli — Docs, Sheets, Slides, Drive, or Classroom. Triggers on phrases like "edit this Google doc", "update the sheet", "find my slides", "grade this assignment", or any request involving Google Workspace documents, files, or classes. This is an umbrella skill — the 5 sibling packages (gogcli-mcp-docs, gogcli-mcp-sheets, gogcli-mcp-slides, gogcli-mcp-drive, gogcli-mcp-classroom) cover specific APIs.

54 次安装

产出可复用的工作流蓝图,包含触发器、步骤、依赖关系和可导出产物。

362 次安装11 星标

通过对话或预设创建、安装、发布独立的 AI 智能体人格技能包。

69 次安装1 星标

Two-pass code audits across security, perf, UX, DX, and edge.

83 次安装