I’ve asked AI a few times and I still don’t get it.

Why do frameworks like Claude Code or Codex have the concept of “skills” instead of just using well-organized Markdown docs?

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.

What am I missing? Is there a real architectural benefit, or is it mostly a standardization/convenience thing?

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.

> Why do frameworks like Claude Code or Codex have the concept of “skills” instead of just using well-organized Markdown docs?

"Well-organized markdown docs" are exactly what skills are.

More specifically, they are well-organized markdown docs that explain how to do some particular thing.

It is just marketing speak to evoke some similarity to Sci-fi movies show AI robots learning stuff by quickly going books.

Nothing of the sort happens here though...

So you are not missing anything. What you think is exactly what it is. Just some prefix for preloading the LLM context with..

Skills represent a pattern many of us converged to before it was named as such (very useful for comms): Progressive disclosure, determistic scripts bundled (not just markdowns). See past comment:

https://news.ycombinator.com/item?id=48132477

Don't underestimate the value of "Skill builder" skills too. Great UX

Skills is just lazy loading of well-organized Markdown docs. The "lazy" part is the core part.

Skill is a document that AI agent ignores, distorts and forgets immediately after reading it :)

To add to what the other person said, they're also loaded differently than arbitrary docs.

They're presented as a list of titles and descriptions to the LLM and it can pick which ones seem relevant and load them.

Markdown docs the LLM needs to make a tool call to read the files and potentially multiple tool calls to discover data if there's a hierarchy. Additionally, it now has to decide if it should read the entire file or cherry pick parts of it.

Skills organize that in an atomic and composable way.

I think ChatGPT and Claude skills will also package arbitrary artifacts like scripts as well. Not sure if that's standard or not

Skills are lazy loaded. AGENTS.md is not. It’s stupid regardless.

Aren't "skills" just some words and syntax that tokenize in a fashion that gets an instance of an LLM primed for (you hope) the right thing statistically?

After that, I think "skill" is just a good name. It sounds more "AI" than a "spell" or "incantation", which would sound magical and esoteric.