构建 GUI 自动化 Agent、让 Agent 像人一样看屏幕并用鼠标键盘操作桌面或浏览器软件时使用。 覆盖感知-思考-行动循环、动作空间(GUI/bash/文件编辑)、视觉定位 Grounding 三条路线 (结构化元素索引、Set-of-Mark、纯坐标预测)、分辨率坐标缩放、关键帧观察接口、世界模型与移动端生态壁垒。 触发词:Computer Use、GUI 自动化、截图、Grounding、browser-use、Set-of-Mark、视觉定位、坐标缩放、OSWorld。
Install
npx skills add bojieli/ai-agent-book --skill computer-usenpx skills add bojieli/ai-agent-book --skill computer-use -a claude-code -gnpx skills add bojieli/ai-agent-book --skill computer-use -a codex -ggemini skills install https://github.com/bojieli/ai-agent-book.git --path skills/computer-usegh skill install bojieli/ai-agent-book computer-usegit clone --depth 1 https://github.com/bojieli/ai-agent-book /tmp/bojieli__ai-agent-book
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/bojieli__ai-agent-book/skills/computer-use ~/.claude/skills/computer-use # Claude Code
cp -R /tmp/bojieli__ai-agent-book/skills/computer-use ~/.agents/skills/computer-use # Codex, Cursor, Gemini CLI, Copilot, OpenCode