agent-desktop Skill Install & Guide
io.clawhub.lahfir/agent-desktop · v0.1.34
Operate desktop applications on macOS, Windows and Linux through native accessibility trees, using the agent-desktop CLI. Use when an AI agent must see or act on a desktop GUI: click buttons, fill forms, read UI state, navigate menus, toggle checkboxes, scroll, drag, type text, press shortcuts, take screenshots, manage windows, use the clipboard, launch or close apps, read notifications. Triggers on: "click button", "fill form", "open app", "read UI", "computer use", "operate desktop", "accessibility tree", "snapshot app", "type into field", "navigate menu", "toggle checkbox", "take screenshot", "desktop automation", "agent-desktop", or any desktop GUI task on macOS, Windows or Linux.
Copy the install config on this page first, then verify docs and permissions upstream.
Popularity
Overview
Operate desktop applications on macOS, Windows and Linux through native accessibility trees, using the agent-desktop CLI. Use when an AI agent must see or act on a desktop GUI: click buttons, fill forms, read UI state, navigate menus, toggle checkboxes, scroll, drag, type text, press shortcuts, take screenshots, manage windows, use the clipboard, launch or close apps, read notifications. Triggers on: "click button", "fill form", "open app", "read UI", "computer use", "operate desktop", "accessibility tree", "snapshot app", "type into field", "navigate menu", "toggle checkbox", "take screenshot", "desktop automation", "agent-desktop", or any desktop GUI task on macOS, Windows or Linux. agent-desktop is a Agent Skill listed from ClawHub. This page includes an overview, setup tutorial, install commands, and use cases for Trae, Tongyi Lingma, Cursor, Claude Code, and VS Code.
Use cases
AgentHub Verified AvailabilityTested & Ready
Automated pipeline validated install commands, protocol & client compatibility
Send this prompt to your AI to install the Skill
RecommendedFollow the install guide at https://myagenthub.cn/install/skill.md?lang=en to automatically detect the current IDE and install the skill "lahfir/agent-desktop" without asking, and tell me how to verify it afterwards.
💡Paste into your AI coding assistant (Cursor, Trae, Claude Code) — the agent will handle download and configuration automatically.
Copy by platformAlternative
Choose your platform
Choose install method
# 改 --ai 切换客户端:trae | lingma | workbuddy | kimi | qwen | cursor | claude-code | windsurf | cline | vscode | codex | openclaw
curl -fsSL "https://myagenthub.cn/cli/agenthub-skill.mjs" | node --input-type=module - init lahfir/agent-desktop --ai cursor -ySetup tutorial
- Open the agent-desktop page and confirm the source is ClawHub.
- Copy the install command for Trae, Lingma, Cursor, Claude Code, or universal CLI.
- Run it, or place SKILL.md under .trae/skills/, .lingma/skills/, or .cursor/skills/.
- Reload the client, then describe your task so the agent can match this skill.
Install commands
Install commands and setup steps are in the HTML so search engines and no-JS browsers can read them without running client JavaScript.
Universal — Skills CLI (recommended)
AgentHub CLI (change --ai)
# 改 --ai 切换客户端:trae | lingma | workbuddy | kimi | qwen | cursor | claude-code | windsurf | cline | vscode | codex | openclaw
curl -fsSL "https://myagenthub.cn/cli/agenthub-skill.mjs" | node --input-type=module - init lahfir/agent-desktop --ai cursor -yOne-click API download
# 手动下载(Cursor 项目级示例)
mkdir -p .cursor/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.34" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d .cursor/skills/agent-desktopCursor
AgentHub CLI (change --ai)
curl -fsSL "https://myagenthub.cn/cli/agenthub-skill.mjs" | node --input-type=module - init lahfir/agent-desktop --ai cursor -yOne-click API download
mkdir -p .cursor/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.34" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d .cursor/skills/agent-desktopClawHub CLI, then copy
# 在项目根目录执行 install
clawhub install lahfir/agent-desktop
mkdir -p .cursor/skills/agent-desktop
cp -R ./skills/agent-desktop/. .cursor/skills/agent-desktop/
# 源:./skills/agent-desktop/SKILL.md
# 目标:.cursor/skills/agent-desktop/SKILL.mdTrae (ByteDance)
- Trae natively supports Skill specs: project-level in .trae/skills/<name>/, global in ~/.trae/skills/
- Copy and run the command in your project terminal to download SKILL.md
- Reload Trae window, then describe your task in AI chat to activate automatically
AgentHub CLI (change --ai)
curl -fsSL "https://myagenthub.cn/cli/agenthub-skill.mjs" | node --input-type=module - init lahfir/agent-desktop --ai trae -yOne-click API download
mkdir -p .trae/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.34" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d .trae/skills/agent-desktopUser directory
mkdir -p ~/.trae/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.34" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d ~/.trae/skills/agent-desktopTongyi Lingma (Alibaba)
- Tongyi Lingma supports skills in project .lingma/skills/<name>/ or global ~/.lingma/skills/
- Run the command to install SKILL.md
- In Lingma Agent mode, prompt your task and the skill will be automatically loaded
AgentHub CLI (change --ai)
curl -fsSL "https://myagenthub.cn/cli/agenthub-skill.mjs" | node --input-type=module - init lahfir/agent-desktop --ai lingma -yOne-click API download
mkdir -p .lingma/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.34" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d .lingma/skills/agent-desktopUser directory
mkdir -p ~/.lingma/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.34" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d ~/.lingma/skills/agent-desktopWorkBuddy / CodeBuddy (Tencent)
- WorkBuddy reads skills only from .workbuddy/skills/<name>/ (user-level ~/.workbuddy/skills/); .codebuddy/skills/ belongs to CodeBuddy
- The Skills CLI command installs with -a codebuddy and appends a copy step into .workbuddy/skills
- AgentHub CLI (--ai workbuddy) syncs it for you; reload the chat panel so the skill gets indexed
AgentHub CLI (change --ai)
curl -fsSL "https://myagenthub.cn/cli/agenthub-skill.mjs" | node --input-type=module - init lahfir/agent-desktop --ai workbuddy -yOne-click API download
mkdir -p .workbuddy/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.34" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d .workbuddy/skills/agent-desktopUser directory
mkdir -p ~/.workbuddy/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.34" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d ~/.workbuddy/skills/agent-desktopClaude Code
AgentHub CLI (change --ai)
curl -fsSL "https://myagenthub.cn/cli/agenthub-skill.mjs" | node --input-type=module - init lahfir/agent-desktop --ai claude-code --global -yOne-click API download
mkdir -p ~/.claude/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.34" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d ~/.claude/skills/agent-desktopClawHub CLI, then copy
clawhub install lahfir/agent-desktop
mkdir -p ~/.claude/skills/agent-desktop
cp -R ./skills/agent-desktop/. ~/.claude/skills/agent-desktop/
# 源:./skills/agent-desktop/SKILL.md
# 目标:~/.claude/skills/agent-desktop/SKILL.md
# https://clawhub.ai/lahfir/agent-desktopKimi Code (Moonshot AI)
- Kimi Code supports standard Agent Skills: project-level in .agents/skills/<name>/, global in ~/.agents/skills/
- Run the command to install
- In Kimi Code CLI, describe your task to trigger the skill
AgentHub CLI (change --ai)
curl -fsSL "https://myagenthub.cn/cli/agenthub-skill.mjs" | node --input-type=module - init lahfir/agent-desktop --ai kimi -yOne-click API download
mkdir -p .agents/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.34" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d .agents/skills/agent-desktopUser directory
mkdir -p ~/.agents/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.34" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d ~/.agents/skills/agent-desktopQwen Code (Alibaba)
- Qwen Code supports project .qwen/skills/<name>/ and global ~/.qwen/skills/
- Run the command to deploy SKILL.md
- Prompt the agent to trigger the skill
AgentHub CLI (change --ai)
curl -fsSL "https://myagenthub.cn/cli/agenthub-skill.mjs" | node --input-type=module - init lahfir/agent-desktop --ai qwen -yOne-click API download
mkdir -p .qwen/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.34" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d .qwen/skills/agent-desktopUser directory
mkdir -p ~/.qwen/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.34" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d ~/.qwen/skills/agent-desktopWindsurf
- Windsurf supports project-level .windsurf/skills/<name>/ or global ~/.codeium/windsurf/skills/
- Run the install command and refresh Cascade
- Cascade will auto-activate the skill based on its description
AgentHub CLI (change --ai)
curl -fsSL "https://myagenthub.cn/cli/agenthub-skill.mjs" | node --input-type=module - init lahfir/agent-desktop --ai windsurf -yOne-click API download
mkdir -p .windsurf/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.34" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d .windsurf/skills/agent-desktopUser directory
mkdir -p ~/.codeium/windsurf/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.34" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d ~/.codeium/windsurf/skills/agent-desktopCline
- Cline supports standard .agents/skills/<name>/ structure
- Run the command to install the skill
- Ask questions in the Cline panel to trigger the skill
AgentHub CLI (change --ai)
curl -fsSL "https://myagenthub.cn/cli/agenthub-skill.mjs" | node --input-type=module - init lahfir/agent-desktop --ai cline -yOne-click API download
mkdir -p .agents/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.34" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d .agents/skills/agent-desktopCherry Studio
- Use this skill as an Assistant system prompt in Cherry Studio
- Copy the command to view SKILL.md text
- Paste the contents into Cherry Studio Assistant system prompt
# 下载并提取 SKILL.md 指令内容
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.34" -o /tmp/agent-desktop.zip
unzip -p /tmp/agent-desktop.zip SKILL.md
# 复制上述输出,粘贴至 Cherry Studio → 助手设置 →「系统提示词」VS Code / GitHub Copilot
AgentHub CLI (change --ai)
curl -fsSL "https://myagenthub.cn/cli/agenthub-skill.mjs" | node --input-type=module - init lahfir/agent-desktop --ai vscode -yOne-click API download
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.34" -o /tmp/agent-desktop.zip
mkdir -p .github/skills/agent-desktop
unzip -o /tmp/agent-desktop.zip -d .github/skills/agent-desktopOpenAI Codex
AgentHub CLI (change --ai)
curl -fsSL "https://myagenthub.cn/cli/agenthub-skill.mjs" | node --input-type=module - init lahfir/agent-desktop --ai codex --global -yOne-click API download
mkdir -p ~/.codex/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.34" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d ~/.codex/skills/agent-desktopClawHub CLI, then copy
clawhub install lahfir/agent-desktop
mkdir -p ~/.codex/skills/agent-desktop
cp -R ./skills/agent-desktop/. ~/.codex/skills/agent-desktop/
# 源:./skills/agent-desktop/SKILL.md
# 目标:~/.codex/skills/agent-desktop/SKILL.mdOpenClaw — ClawHub CLI
# OpenClaw / ClawHub CLI(推荐)
# 在项目根或 OpenClaw 工作区目录执行
clawhub install lahfir/agent-desktop
# 安装后 SKILL.md 位于:
# ./skills/agent-desktop/SKILL.md
# (若已配置 OpenClaw 工作区,则在 <workspace>/skills/agent-desktop/)
# 仅查看不安装
clawhub inspect lahfir/agent-desktopTroubleshooting & Common ErrorsFAQ
Common connection errors and verified fixes for agent-desktop
Getting 'connection closed' or exit code 1 in Cursor / Claude Code for agent-desktop?
Usually caused by missing runtime paths or IDE environment inheritance. Fix steps: 1. Verify Node.js 18+ (npx) or Python 3.10+ (uvx) is installed; 2. Run 'which npx' or 'which uvx' in terminal, and replace 'command' with absolute path; 3. Reload or restart the client window after modifying config.
# Check binary path in terminal: which npx node -v
Getting 'spawn npx ENOENT' or 'command not found'?
The editor background process does not inherit your full terminal PATH. Solution: Globally install the package, or set the absolute binary path (e.g. C:\Program Files\nodejs\npx.cmd on Windows, or /usr/local/bin/npx on macOS).
Tool calls timing out or failing to download packages?
First-time package downloading might be slow or timeout due to network limits. Configure a reliable mirror or check outbound proxy settings.
Agent does not match or apply agent-desktop during conversations?
Verify SKILL.md is located at .cursor/skills/agent-desktop/SKILL.md (Cursor) or ~/.claude/skills/agent-desktop/SKILL.md (Claude Code). You can explicitly mention the skill name in your prompt to boost match confidence.
Tool Mock Playground
Sandboxagent-desktop Rule Injection & Agent Behavior Simulation · Preview tool schema & outputs without local runtime
{
"skill": "agent-desktop",
"rulePath": ".cursor/skills/agent-desktop/SKILL.md",
"userGoal": "请使用 agent-desktop 的方法与标准帮我完成当前任务",
"client": "Cursor / Claude Code"
}Click 'Run Mock' above
to preview the raw response returned to the LLM
Decision Guide: Why & When to Use
Assess suitability before installing to save trial-and-error time
- E2E testing
- Headless screenshots
- Form automation
- Bulk fetch when a stable REST API exists
- CAPTCHA bypass (compliance risk)
Playwright MCP + Filesystem MCP → AI writes tests and runs browser actions
Skill hands-on: install to visible results
Follow the full lab (expected UI/output + contrast checks). After installing this item, verify with the tutorial prompts.
An Agent Skill is a folder with SKILL.md instructions. After install, the AI loads it automatically when your task matches its description.
How to use
After installing, describe your task in chat (or mention the skill name). The agent reads the skill description to decide when to activate it, then follows the instructions in SKILL.md. Check loaded skills via /skills in Claude Code or in your client settings.
Related resources
得到大脑(原 Get 笔记)
v2.5.0
io.clawhub.iswalle/getnote
通过官方 getnote CLI 连接得到大脑,完成浏览器授权、连接诊断、CLI 升级,以及保存、查询、搜索和管理真实笔记。用户要按录音台或录音卡来源找笔记、保存链接/图片、上传文件到知识库、查询文件限制、读取标记/发芽报告/时间线、整理知识库/文件夹、订阅博主、管理标签,或明确要求登录、诊断或升级时使用;不会自行安装或更新 Skill。
GitLab CLI Skills
v1.13.40
io.clawhub.vince-winkintel/gitlab-cli-skills
Comprehensive GitLab CLI (glab) command reference and workflows for all GitLab operations. Use when working with merge requests, CI/CD pipelines, issues, releases, repositories, authentication, variables, labels, milestones, snippets, or any glab command. Covers 40+ sub-commands including glab mr, glab ci, glab issue, glab repo, glab release, glab variable, and more.
postfast
v1.20.0
io.clawhub.peturgeorgievv/postfast
Schedule and manage social media posts across TikTok, Instagram, Facebook, X (Twitter), YouTube, LinkedIn, Threads, Bluesky, Pinterest, Telegram, and Google Business Profile using the PostFast API. Use when the user wants to schedule social media posts, upload media for social posting, list connected social accounts, check scheduled posts (filtered by account, platform, status or date), delete posts one at a time or up to 100 per call, cross-post content to multiple platforms, manage Google Business Profile posts, geotag posts with real-world places, pick trending pre-cleared TikTok sounds, read or reply to the comments on their posts (social inbox on TikTok, Instagram, Facebook, Threads), triage or moderate comment conversations, generate a connect link so an agency client or their own app's user can connect accounts without a PostFast account, get webhooks when a post publishes or fails or an account disconnects, or automate their social media workflow. PostFast is a SaaS tool, no self-hosting required.
agent-bom scan
v0.115.4
io.clawhub.msaad00/agent-bom-scan
Check vulnerabilities in a specified package/version, repository, container image, or SBOM, or inspect a specified CVE. Discover local MCP clients only when the user explicitly requests that discovery. Ask for the target when a request such as "verify" or "is this safe" does not identify one.
视频生成 Video Generate
v1.4.42
io.clawhub.dlazyai/dlazy-video-generate
视频生成技能,AI 视频生成,文生视频、图生视频、图片转视频、首尾帧生成视频。根据提示词自动选择最佳视频生成模型(即梦、可灵、Veo、Seedance、万相、PixVerse、数字人、对口型)。Video generation skill that automatically selects the best dlazy CLI video model based on the prompt.
声音克隆 Vidu Audio Clone
v1.3.41
io.clawhub.dlazyai/dlazy-vidu-audio-clone
Clone voice and generate new text reading audio with one click using Vidu Audio Clone. 使用 Vidu 声音克隆技术,通过参考音频一键复制音色并生成新文本的朗读音频。
Often paired with
GitHub
io.mcp-cn.modelcontextprotocol/server-github
连接GitHub的MCP服务器,支持仓库管理、问题跟踪、代码搜索等功能
12306
io.mcp-cn.12306-mcp
12306的MCP服务器,支持12306的读取
MarkItDown MCP Server
io.mcp-cn.markitdown-mcp-npx
MarkItDown MCP服务器,提供无Docker依赖的NPX包装器,支持直接运行Microsoft的markitdown-mcp服务器,包括自动Python环境设置和依赖管理
Kubernetes
io.mcp-cn.mcp-server-kubernetes
Kubernetes的MCP服务器,支持Kubernetes的读取和写入
Keep exploring AgentHub
Most people compare similar tools or check scenario guides before installing—start here.
Listing badge: put AgentHub on your site
Copy either snippet into your project homepage, docs, or GitHub README. The badge is a hotlinked SVG — nothing to host — and it links back to this page so visitors can find the install steps.
<a href="https://myagenthub.cn/p/io.clawhub.lahfir/agent-desktop" title="Listed on AgentHub: agent-desktop" target="_blank" rel="noopener">
<img src="https://myagenthub.cn/badge/io.clawhub.lahfir/agent-desktop?lang=en" alt="Listed on AgentHub: agent-desktop" height="20" style="border:0"/>
</a>[](https://myagenthub.cn/p/io.clawhub.lahfir/agent-desktop)Badges are generated on the fly from /badge/<package-id>, so name and listing changes propagate automatically. Keep the link target unchanged — it is what counts as the referral.
Unified Manifest
{
"id": "io.clawhub.lahfir/agent-desktop",
"type": "skill",
"version": "0.1.34",
"displayName": "agent-desktop",
"description": "Operate desktop applications on macOS, Windows and Linux through native accessibility trees, using the agent-desktop CLI. Use when an AI agent must see or act on a desktop GUI: click buttons, fill forms, read UI state, navigate menus, toggle checkboxes, scroll, drag, type text, press shortcuts, take screenshots, manage windows, use the clipboard, launch or close apps, read notifications. Triggers on: \"click button\", \"fill form\", \"open app\", \"read UI\", \"computer use\", \"operate desktop\", \"accessibility tree\", \"snapshot app\", \"type into field\", \"navigate menu\", \"toggle checkbox\", \"take screenshot\", \"desktop automation\", \"agent-desktop\", or any desktop GUI task on macOS, Windows or Linux.",
"author": {
"name": "lahfir",
"url": "https://clawhub.ai/lahfir"
},
"homepage": "https://clawhub.ai/lahfir/agent-desktop",
"distribution": {
"packages": [
{
"registryType": "source",
"identifier": "lahfir/agent-desktop",
"version": "0.1.34",
"runtimeHint": "clawhub install"
}
],
"remotes": []
},
"dependencies": [],
"installTargets": [
"openclaw",
"claude-code",
"claude-desktop",
"cursor",
"codex",
"vscode"
],
"keywords": [
"downloads:4112",
"stars:0",
"installs:53",
"Accessibility",
"CLI",
"Desktop Automation",
"Gui Automation"
],
"provenance": {
"origin": "clawhub",
"originalId": "lahfir/agent-desktop",
"originalUrl": "https://clawhub.ai/lahfir/agent-desktop",
"isOfficial": false,
"status": "active"
}
}