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。
87%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
wait,不要盲点。chapter6/claude-computer-use-native/ — 实验 6-8(Anthropic 原生路径):容器化 Ubuntu 桌面中的官方 Computer Use Demo,computer / bash / 编辑器三类原生工具的真实运行与确定性验收记录。chapter6/computer-use-open-model/ — 实验 6-8/6-9(开放模型路径):同一"截图 → 结构化动作 → 浏览器执行"循环,默认 Qwen3-VL 32B Instruct 驱动 browser-use,可接 OpenRouter 或自托管 vLLM/SGLang;含端点合格性契约(收截图、产出 Browser Use 动作 schema、每步一个动作、不静默替换模型)。chapter6/end-to-end-speech/、chapter6/streaming-speech/、chapter6/controllable-tts/、chapter6/live-audio/、chapter6/phone-agent/。chapter6/gemini-xlerobot-navigation/、chapter6/rgb-sim2real-grasping/、chapter6/xlerobot-teleoperation/。chapter6/phone-agent/ 给出真实手机上的 Agent 驱动样例。book/chapter6.md「模态与触发时机的扩展」book/chapter6.md「Computer Use:GUI 自动化 Agent」chapter6/computer-use-open-model/ 与 chapter6/claude-computer-use-native/ 的 README 与 validation/ 目录。bojieli/ai-agent-book
dbc046e
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.