AgentHubAgentHub

agent-desktop Skill Install & Guide

SkillClawHub

io.clawhub.lahfir/agent-desktop · v0.1.32

Reliable computer use via native OS accessibility trees. Use when an AI agent needs to see and operate 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 59 command names (55 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", "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 interaction task. Supports the macOS Phase 1 adapter, with Windows and Linux planned against the same core contracts.

View on ClawHub ↗

Copy the install config on this page first, then verify docs and permissions upstream.

Popularity

Downloads3.4k
Installs52

Overview

Reliable computer use via native OS accessibility trees. Use when an AI agent needs to see and operate 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 59 command names (55 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", "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 interaction task. Supports the macOS Phase 1 adapter, with Windows and Linux planned against the same core contracts. 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.

AccessibilityCLIDesktop AutomationGui Automation

Use cases

Browser automationDesign & creative

AgentHub Verified AvailabilityTested & Ready

Automated pipeline validated install commands, protocol & client compatibility

Verified At2026-09-30
Install Snippets TestedCLI & JSON config syntax verified
Protocol Handshake ReadyComplies with JSON-RPC 2.0 specifications
Origin Registry ActiveSourced from clawhub
Verified Clientsopenclaw、Claude Code、Claude Desktop 等
Security Tier: A+ 级 · 零权限本地沙盒 (A+)·Scanned for high-risk vulnerabilities. Recommended to run with project-scoped permissions.

Send this prompt to your AI to install the Skill

Recommended
Target client (auto-optimizes prompt):
PROMPT >

Follow 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

Click to copy snippet
# 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 -y

Setup tutorial

  1. Open the agent-desktop page and confirm the source is ClawHub.
  2. Copy the install command for Trae, Lingma, Cursor, Claude Code, or universal CLI.
  3. Run it, or place SKILL.md under .trae/skills/, .lingma/skills/, or .cursor/skills/.
  4. 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 -y

One-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=0.1.32" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d .cursor/skills/agent-desktop

Cursor

AgentHub CLI (change --ai)

curl -fsSL "https://myagenthub.cn/cli/agenthub-skill.mjs" | node --input-type=module - init lahfir/agent-desktop --ai cursor -y

One-click API download

mkdir -p .cursor/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.32" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d .cursor/skills/agent-desktop

ClawHub 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.md

Trae (ByteDance)

  1. Trae natively supports Skill specs: project-level in .trae/skills/<name>/, global in ~/.trae/skills/
  2. Copy and run the command in your project terminal to download SKILL.md
  3. 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 -y

One-click API download

mkdir -p .trae/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.32" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d .trae/skills/agent-desktop

User directory

mkdir -p ~/.trae/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.32" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d ~/.trae/skills/agent-desktop

Tongyi Lingma (Alibaba)

  1. Tongyi Lingma supports skills in project .lingma/skills/<name>/ or global ~/.lingma/skills/
  2. Run the command to install SKILL.md
  3. 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 -y

One-click API download

mkdir -p .lingma/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.32" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d .lingma/skills/agent-desktop

User directory

mkdir -p ~/.lingma/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.32" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d ~/.lingma/skills/agent-desktop

WorkBuddy / CodeBuddy (Tencent)

  1. WorkBuddy reads skills only from .workbuddy/skills/<name>/ (user-level ~/.workbuddy/skills/); .codebuddy/skills/ belongs to CodeBuddy
  2. The Skills CLI command installs with -a codebuddy and appends a copy step into .workbuddy/skills
  3. 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 -y

One-click API download

mkdir -p .workbuddy/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.32" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d .workbuddy/skills/agent-desktop

User directory

mkdir -p ~/.workbuddy/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.32" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d ~/.workbuddy/skills/agent-desktop

Claude 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 -y

One-click API download

mkdir -p ~/.claude/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.32" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d ~/.claude/skills/agent-desktop

ClawHub 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-desktop

Kimi Code (Moonshot AI)

  1. Kimi Code supports standard Agent Skills: project-level in .agents/skills/<name>/, global in ~/.agents/skills/
  2. Run the command to install
  3. 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 -y

One-click API download

mkdir -p .agents/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.32" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d .agents/skills/agent-desktop

User directory

mkdir -p ~/.agents/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.32" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d ~/.agents/skills/agent-desktop

Qwen Code (Alibaba)

  1. Qwen Code supports project .qwen/skills/<name>/ and global ~/.qwen/skills/
  2. Run the command to deploy SKILL.md
  3. 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 -y

One-click API download

mkdir -p .qwen/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.32" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d .qwen/skills/agent-desktop

User directory

mkdir -p ~/.qwen/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.32" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d ~/.qwen/skills/agent-desktop

Windsurf

  1. Windsurf supports project-level .windsurf/skills/<name>/ or global ~/.codeium/windsurf/skills/
  2. Run the install command and refresh Cascade
  3. 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 -y

One-click API download

mkdir -p .windsurf/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.32" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d .windsurf/skills/agent-desktop

User directory

mkdir -p ~/.codeium/windsurf/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.32" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d ~/.codeium/windsurf/skills/agent-desktop

Cline

  1. Cline supports standard .agents/skills/<name>/ structure
  2. Run the command to install the skill
  3. 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 -y

One-click API download

mkdir -p .agents/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.32" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d .agents/skills/agent-desktop

Cherry Studio

  1. Use this skill as an Assistant system prompt in Cherry Studio
  2. Copy the command to view SKILL.md text
  3. 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=0.1.32" -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 -y

One-click API download

curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.32" -o /tmp/agent-desktop.zip
mkdir -p .github/skills/agent-desktop
unzip -o /tmp/agent-desktop.zip -d .github/skills/agent-desktop

OpenAI 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 -y

One-click API download

mkdir -p ~/.codex/skills/agent-desktop
curl -sL "https://clawhub.ai/api/v1/download?slug=agent-desktop&version=0.1.32" -o /tmp/agent-desktop.zip
unzip -o /tmp/agent-desktop.zip -d ~/.codex/skills/agent-desktop

ClawHub 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.md

OpenClaw — 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-desktop

Troubleshooting & 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.

Fix Snippet
# 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.

Still not connecting? Read the MCP troubleshooting guide →

Tool Mock Playground

Sandbox

agent-desktop Rule Injection & Agent Behavior Simulation · Preview tool schema & outputs without local runtime

Sandbox Ready
fn: agent_skill_runtimeInject system prompt guidelines & workflow constraints from agent-desktop
Request ArgumentsJSON Schema
{
  "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"
}
💡Parameters generated dynamically by Agent runtime
Agent Tool Output

Click 'Run Mock' above

to preview the raw response returned to the LLM

Env: AgentHub Virtual SandboxJSON-RPC 2.0

Decision Guide: Why & When to Use

Assess suitability before installing to save trial-and-error time

Best Suited For
  • E2E testing
  • Headless screenshots
  • Form automation
When NOT to Use
  • Bulk fetch when a stable REST API exists
  • CAPTCHA bypass (compliance risk)
Recommended Workflow Pairing:View Scenario →

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.

Open tutorial →

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

微信小程序开发 · WeChat Mini Program Development

v1.28.65

SkillClawHub5k

io.clawhub.binggg/miniprogram-development

WeChat Mini Program development skill for building, debugging, previewing, testing, publishing, and optimizing mini program projects (小程序开发、调试、预览、发布). Covers project structure and config (`project.config.json`, `appid`, `miniprogramRoot`, `tabBar`, routing/navigation, icon assets), WeChat Developer Tools Nightly workflows (`wechatide` CLI, WeChat IDE Skills/MCP), `miniprogram-ci` preview/upload, console/network debugging, message push (消息推送) and customer-service auto-reply (客服消息), mini program SEO / search indexing (小程序搜索优化、页面收录、搜索推广、mpcrawler), and CloudBase integration (`wx.cloud`, 腾讯云开发, 云开发) when explicitly used. Use when users create, develop, modify, debug, preview, deploy, publish, or promote WeChat Mini Programs. NOT for Web frontend (use web-development), pure backend services (use cloudrun-development / cloud-functions), or UI-design-only tasks (use ui-design).

source
View on ClawHub

mt5-httpapi

v4.15.0

SkillClawHub4.8k

io.clawhub.psyb0t/mt5-httpapi

HTTP client for a user-deployed mt5-httpapi MetaTrader 5 bridge. Use ONLY when the user has explicitly installed and configured mt5-httpapi AND provided MT5_API_URL. Read endpoints (account, symbols, rates, ticks, server-side technical-analysis enrichment via the wickworks sidecar, history, backtest report fetching) are safe to invoke. Trade-mutating endpoints on /orders and /positions require explicit per-action confirmation showing symbol, side, volume, and SL/TP; terminal shutdown/restart also require explicit confirmation naming the target terminal and operation. Never invoke mutations on inferred intent. Do not use this skill for generic market-data, charting, or trading questions where the user hasn't named mt5-httpapi.

source
View on ClawHub

Often paired with

Keep exploring AgentHub

Most people compare similar tools or check scenario guides before installing—start here.

Browse more like thisSearch similarPick by scenarioPrompt playbooksSkill hands-onReviews & comparisons

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.

PreviewListed on AgentHub: agent-desktop
HTML
<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>
Markdown (GitHub README)
[![Listed on AgentHub: agent-desktop](https://myagenthub.cn/badge/io.clawhub.lahfir/agent-desktop?lang=en)](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": "0.1.32",
  "displayName": "agent-desktop",
  "description": "Reliable computer use via native OS accessibility trees. Use when an AI agent needs to see and operate 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 59 command names (55 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\", \"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 interaction task. Supports the macOS Phase 1 adapter, with Windows and Linux planned against the same core contracts.",
  "author": {
    "name": "lahfir",
    "url": "https://clawhub.ai/lahfir"
  },
  "homepage": "https://clawhub.ai/lahfir/agent-desktop",
  "distribution": {
    "packages": [
      {
        "registryType": "source",
        "identifier": "lahfir/agent-desktop",
        "version": "0.1.32",
        "runtimeHint": "clawhub install"
      }
    ],
    "remotes": []
  },
  "dependencies": [],
  "installTargets": [
    "openclaw",
    "claude-code",
    "claude-desktop",
    "cursor",
    "codex",
    "vscode"
  ],
  "keywords": [
    "downloads:3366",
    "stars:0",
    "installs:52",
    "Accessibility",
    "CLI",
    "Desktop Automation",
    "Gui Automation"
  ],
  "provenance": {
    "origin": "clawhub",
    "originalId": "lahfir/agent-desktop",
    "originalUrl": "https://clawhub.ai/lahfir/agent-desktop",
    "isOfficial": false,
    "status": "active"
  }
}