Skills are kind of a new thing starting around January 2026, but the spec was established about 12 months ago.

https://news.ycombinator.com/item?id=46871173

Anyways the most layman way I’ve seen it explained is this: skills help save token usage for the right context. Not every request needs all instructions all the time - running tests is different than reviewing a PR, so why should the context window have instructions for both on every request?

So now you split instructions into “skill” files, which are basically opinionated markdown files. And you invoke those with something like /grill-me in the prompt depending on what you’re doing.

There are some steps to have the agent automatically know what to invoke for you but in my experience this automation is hit or miss.

It is also challenging to keep track of a growing library of skills and keeping those up to date.

So YMMV regarding skills. I typically keep things in a single markdown file even if the context window gets a bit bloated.

You can /i-have-adhd when you get a wall of text and are exasperated. You don't always want the responses that it generates when you /i-have-adhd, and things in AGENTS.md tend to lose weight as context grows.

It's a fashion choice.

It lets the author pretend to be doing software engineering, like running tests and deploying versions.

[dead]