[simonw]

They're not. They are just a formalization of that pattern, with a very tiny extra feature where the model harness scans that folder on startup and loads some YAML metadata into the system prompt so it knows which ones to read later on.

[lupire]

So "skills" are a hack around the LLM not actually being very smart? Interesting.

[simonw]

Everything we do with LLMs is a hack around them not actually being very smart!

Working around their many limitations has been the nature of the game since the original GPT-3.

[vidarh]

It's more that they are embracing that the LLM is smart enough that you don't need to build-in this functionality beyond that very minimal part.

A fun thing: Claude Code will sometimes fail to find the skill the "proper" way, and will then in fact sometimes look for the SKILL.md file with tools, and read the file with tools, showing that it's perfectly capable of doing all the steps.

You could probably "fake" skills pretty well with instructions in CLAUDE.md to use a suitable command to extract the preamble of files in a given directory, and tell it to use that to decide when to read the rest.

It's the fact that it's such a thin layer that is exciting - it means we need increasingly less special logic other than relying on just basic instructions to the model itself.

[Glemkloksdjf]

No, skills are a set of manifested and tested 'skills' which reduce the 'mental load' of the LLM and reduces the context the LLM needs to do things reproducable.

Similiar to what humans do.

[conception]

More not wasting context having it figure it out.

It’s documentation vs researching how to do something.