Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add L-LesterYu/OpenClaw-hot-skills-zh --skill desktop-control-zhgit clone --depth 1 https://github.com/L-LesterYu/OpenClaw-hot-skills-zhWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/l-lesteryu/openclaw-hot-skills-zh/desktop-control-zh)<a href="https://agentmods.dev/skills/l-lesteryu/openclaw-hot-skills-zh/desktop-control-zh"><img src="https://agentmods.dev/badge/skills/l-lesteryu/openclaw-hot-skills-zh/desktop-control-zh/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/l-lesteryu/openclaw-hot-skills-zh/desktop-control-zh"><img src="https://agentmods.dev/badge/skills/l-lesteryu/openclaw-hot-skills-zh/desktop-control-zh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00033 | $0.04254 |
| Opus 5 | $0.00016 | $0.02127 |
| Sonnet 5 | $0.00007 | $0.00851 |
| Haiku 4.5 | $0.00003 | $0.00425 |
Grade A, and why
desktop-control-zh scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 624 lines — stays where its author put it; the contents beside it link to each section on GitHub.
桌面控制技能
OpenClaw 最先进的桌面自动化技能。 提供像素级精确的鼠标控制、闪电般的键盘输入、屏幕截图、窗口管理和剪贴板操作。
🎯 功能特性
鼠标控制
- ✅ 绝对定位 - 移动到精确坐标
- ✅ 相对移动 - 从当前位置移动
- ✅ 平滑移动 - 自然、拟人的鼠标路径
- ✅ 点击类型 - 左键、右键、中键、双击、三击
- ✅ 拖放操作 - 从 A 点拖动到 B 点
- ✅ 滚动 - 垂直和水平滚动
- ✅ 位置追踪 - 获取当前鼠标坐标
键盘控制
- ✅ 文本输入 - 快速、准确的文本输入
- ✅ 快捷键 - 执行键盘快捷键（Ctrl+C、Win+R 等）
- ✅ 特殊按键 - Enter、Tab、Escape、方向键、F 键
- ✅ 组合键 - 多键同时按下
- ✅ 按住与释放 - 手动控制按键状态
- ✅ 输入速度 - 可配置的 WPM（从瞬间到拟人化）
屏幕操作
- ✅ 截图 - 捕获整个屏幕或指定区域
- ✅ 图像识别 - 在屏幕上查找元素（通过 OpenCV）
- ✅ 颜色检测 - 获取指定坐标的像素颜色
- ✅ 多显示器 - 支持多个显示器
窗口管理
- ✅ 窗口列表 - 获取所有打开的窗口
- ✅ 激活窗口 - 将窗口置于前台
- ✅ 窗口信息 - 获取位置、大小、标题
- ✅ 最小化/最大化 - 控制窗口状态
安全特性
- ✅ 故障保护 - 将鼠标移到角落以中止
- ✅ 暂停控制 - 紧急停止机制
- ✅ 批准模式 - 操作前需要确认
- ✅ 边界检查 - 防止超出屏幕的操作
- ✅ 日志记录 - 追踪所有自动化操作
🚀 快速开始
安装
首先，安装所需的依赖：
pip install pyautogui pillow opencv-python pygetwindow
基本使用
from skills.desktop_control import DesktopController
# 初始化控制器
dc = DesktopController(failsafe=True)
# 鼠标操作
dc.move_mouse(500, 300) # 移动到坐标
dc.click() # 在当前位置左键点击
dc.click(100, 200, button="right") # 在指定位置右键点击
# 键盘操作
dc.type_text("Hello from OpenClaw!")
dc.hotkey("ctrl", "c") # 复制
dc.press("enter")
# 屏幕操作
screenshot = dc.screenshot()
position = dc.get_mouse_position()
📋 完整 API 参考
鼠标函数
move_mouse(x, y, duration=0, smooth=True)
将鼠标移动到绝对屏幕坐标。
参数：
x(int): X 坐标（距离左边的像素数）y(int): Y 坐标（距离顶部的像素数）duration(float): 移动时间（秒）（0 = 瞬间，0.5 = 平滑）smooth(bool): 使用贝塞尔曲线进行自然移动
示例：
# 瞬间移动
dc.move_mouse(1000, 500)
# 平滑的 1 秒移动
dc.move_mouse(1000, 500, duration=1.0)
move_relative(x_offset, y_offset, duration=0)
相对于当前位置移动鼠标。
参数：
x_offset(int): 水平移动像素（正数 = 向右）y_offset(int): 垂直移动像素（正数 = 向下）duration(float): 移动时间（秒）
示例：
# 向右移动 100px，向下移动 50px
dc.move_relative(100, 50, duration=0.3)
click(x=None, y=None, button='left', clicks=1, interval=0.1)
执行鼠标点击。
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 624 lines · 33 tokens per session scan A 153df09a7ee9
desktop-control-zh is a skill published in the GitHub repository L-LesterYu/OpenClaw-hot-skills-zh (54 stars, last pushed 5mo ago), licensed MIT. It adds 33 tokens to every session and 4,254 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…