用好AI的第二步不是更会写 prompt，而是先外化、再复用。本文讲清 Skill 如何承载工作知识、好 Skill 的三要素，以及如何组织 Skill 文件夹让 Agent 自动找到。
Step Two to Using AI Well: Write the Skill Before You Execute
Step two isn't better prompting. It's externalize first, reuse second. This post explains how Skills carry work knowledge, the three parts of a good Skill, and how to organize them so agents find the right one.
为什么AI只会说正确的废话，以及怎么把它逼出舒适区
LLM的默认输出是consensus：正确但平庸。Deep Research其实是Wide Research。我们找到了一种系统性方法，用个人认知上下文把LLM从consensus里强行扯出来。一年实验，有控制变量证据。
Why AI Only Gives You Correct Nonsense, and How to Push It Out of Its Comfort Zone
An LLM's default output is consensus: correct but mediocre. Deep Research is really Wide Research. We found a systematic way to pull LLMs out of consensus using personal cognitive context. One year of experimentation, with controlled evidence.
用好AI的第一步：停止和AI聊天
会用AI和用好AI之间差的是10倍。这个差距的根源在于工作方式，而非模型。本文通过一个完整的工作流例子和上中下三策的框架，解释为什么应该从ChatGPT切换到Cursor这类Agentic工具。