← 返回 Skills 市场
matagul

Desktop Control

作者 matagul · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
59534
总下载
370
收藏
514
当前安装
1
版本数
在 OpenClaw 中安装
/install desktop-control
功能描述
Advanced desktop automation with mouse, keyboard, and screen control
安全使用建议
Install only if you intentionally want an agent to control your live desktop. Use it in a test or isolated session first, keep failsafe enabled, prefer require_approval=True where available, avoid running it while sensitive apps or secrets are visible, and do not use autonomous workflows for submissions, public posting, file operations, or clipboard handling without reviewing each action.
功能分析
Type: OpenClaw Skill Name: Developer: Version: Description: OpenClaw Agent Skill Suspicious High-Entropy/Eval files: 2 The skill bundle provides extensive desktop automation capabilities, including full control over mouse, keyboard, screen, window management, clipboard, and the ability to execute commands via the Windows Run dialog (Win+R) in `ai_agent.py`. While these are high-risk capabilities, they are plausibly needed for the stated purpose of 'advanced desktop automation' and the skill includes explicit safety features like failsafe and an approval mode. There is no clear evidence of intentional malicious behavior such as data exfiltration, persistence, or obfuscation. The AI agent's planning is currently rule-based, mitigating immediate prompt injection risk for arbitrary command generation, though the underlying `DesktopController` (in `__init__.py`) offers powerful primitives.
能力评估
Purpose & Capability
The capabilities match the desktop automation purpose, but the skill exposes high-impact primitives: mouse and keyboard control, screenshots, window enumeration/activation, clipboard read/write, file-saving screenshots, and launching applications through synthetic Win+R input.
Instruction Scope
Documentation discloses most capabilities, but examples normalize form submission, password-like typing, public social posting, screenshot capture, clipboard access, and failsafe disabling without strong up-front privacy or confirmation guidance.
Install Mechanism
Installation is a straightforward pip dependency instruction for pyautogui, pillow, opencv-python, pygetwindow, and pyperclip; no installer persistence or hidden setup behavior was found in the artifact.
Credentials
Full-desktop automation is inherently broad, and the AI agent can act autonomously across arbitrary focused applications; this is proportionate to the goal only when used in a controlled desktop session with explicit user supervision.
Persistence & Privilege
No background persistence, privilege escalation, or network exfiltration was found, but screenshots can be saved to caller-specified filenames and the AI agent captures before/after screenshots for each step by default, which may retain sensitive screen contents.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install desktop-control
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /desktop-control 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Version 1.0.0 - Initial release of the Desktop Control skill for OpenClaw. - Provides advanced automation: mouse movement/clicks, keyboard input, hotkeys, and typing speed control. - Supports screen capture, region-based screenshots, image/template matching, and pixel color detection. - Includes window management (list, activate, move, resize, minimize/maximize). - Safety features: failsafe abort, logging, approval mode, bounds checks, and emergency pause. - Detailed documentation with examples and complete API reference.
元数据
Slug desktop-control
版本 1.0.0
许可证
累计安装 1852
当前安装数 514
历史版本数 1
常见问题

Desktop Control 是什么?

Advanced desktop automation with mouse, keyboard, and screen control. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 59534 次。

如何安装 Desktop Control?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install desktop-control」即可一键安装,无需额外配置。

Desktop Control 是免费的吗?

是的,Desktop Control 完全免费(开源免费),可自由下载、安装和使用。

Desktop Control 支持哪些平台?

Desktop Control 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Desktop Control?

由 matagul(@matagul)开发并维护,当前版本 v1.0.0。

💬 留言讨论