computer-use-agents

SKILL.md

The fundamental architecture of computer use agents: observe screen, reason about next action, execute action, repeat. This loop integrates vision models with action execution through an iterative pipeline.

Critical insight: Vision agents are completely still during "thinking" phase (1-5 seconds), creating a detectable pause pattern.

When to use: ['Building any computer use agent from scratch', 'Integrating vision models with desktop control', 'Understanding agent behavior patterns']

构建像人类一样与计算机交互的人工智能代理 - 查看屏幕、移动光标、单击按钮和输入文本。涵盖 Anthropic 的计算机使用、OpenAI 的 Operator/CUA 以及开源替代方案。重点关注沙盒、安全性以及处理基于视觉的控制的独特挑战。使用时：计算机使用、桌面自动化代理、屏幕控制AI、基于视觉的代理、GUI自动化。 来源：automindtechnologie-jpg/ultimate-skill.md。

查看原文