问HN：我仍然不明白为什么人工智能代理需要“技能”
我问过几次人工智能，但仍然不太明白。<p>为什么像Claude Code或Codex这样的框架会有“技能”的概念，而不是仅仅使用结构良好的Markdown文档？<p>我不能只创建一个AGENTS.md文件，指向一些.md文件的文件夹，并告诉代理何时读取它们吗？在我看来，这在功能上是等价的。<p>我错过了什么？这背后是否有真正的架构优势，还是主要是一种标准化/便利性的问题？<p>如果技能只是一个位于技能文件夹中的md文件，我怀疑我们会对其产生如此大的热情。所以我觉得我错过了什么。
查看原文
I’ve asked AI a few times and I still don’t get it.<p>Why do frameworks like Claude Code or Codex have the concept of “skills” instead of just using well-organized Markdown docs?<p>Couldn’t I just have an AGENTS.md that points to folders of .md files and tells the agent when to read them? That feels functionally equivalent to me.<p>What am I missing? Is there a real architectural benefit, or is it mostly a standardization/convenience thing?<p>I doubt we’d create so much hype about skills if they’d just be a md file that’s in a skills folder. So I feel I’m missing something.