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.
"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.
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..
https://news.ycombinator.com/item?id=48132477
Don't underestimate the value of "Skill builder" skills too. Great UX
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
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.