extensions/computer-use-hybrid/skills/computer-use-hybrid/SKILL.md
Control native macOS, Windows, and Linux desktop apps through the `open-computer-use` MCP server. Use when the user asks to operate local apps with accessibility-tree context plus screenshots, inspect the screen, click UI, type text, press shortcuts, scroll, drag, or interact with OS-level GUI software.
npx skillsauth add qwenlm/qwen-code-examples computer-use-hybridInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use the MCP tools exposed by the open-computer-use server to operate the user's real local desktop through accessibility-tree context and screenshots.
This is a skill, not a subagent. Never invoke the Agent/Subagent tool with computer-use-hybrid as the subagent type. Stay in the current agent and call the open-computer-use MCP tools directly.
Do not use shell commands to start Playwright or a second desktop automation MCP server, and do not edit Qwen settings as a fallback. If the open-computer-use MCP tools are not available in the current tool list, stop and tell the user to restart Qwen Code or reconnect the extension.
Playwright is intentionally not part of this extension. For browser-only DOM automation, use whatever browser-specific extension or MCP server the user has separately enabled.
open-computer-use supports macOS, Windows, and Linux and is launched through npx -y open-computer-use mcp by default.
On macOS, the first run may require Accessibility and Screen Recording permissions. If a permission prompt or onboarding window appears, guide the user through granting the permission before continuing.
Ask for confirmation before destructive, privacy-sensitive, or externally visible actions, including deleting files, sending messages, submitting forms, making purchases, changing security settings, or entering credentials.
Do not assume the user wants the whole desktop automated. Operate only the app, window, or workflow they asked for.
content-media
Extracts timestamped transcripts from YouTube videos for translation, summarization, and content creation.
tools
帮助用户快速配置和使用微信通道功能。当用户想要"配置微信"、"连接微信"、"设置微信机器人"、"weixin setup"、"wechat channel"时使用此技能。
content-media
为开源项目生成专业宣传视频,传入 {owner}/{repo} 参数 Triggers on "生成开源视频", "宣传视频", "oss video", "remotion video".
testing
Image generation skill based on Alibaba Cloud DashScope, supporting the creation of high-quality hand-drawn or standard images from user descriptions.