Like you said, I think skills are quickly subsumed by model abilities. I leave relevant notes about my own projects in agents.md and local comments around tricky bits of code that need them, but otherwise I just use vanilla codex.
This could be to try and expand the capabilities of the model but in it can be used to store personal preference/workflow/organisational knowledge/improved efficiency etc. The harness could work through and build some of this on its own - but it's much more efficient if it has a document it can just look up. I use them for the database structure and it's quirks, how to use branded document templates, external document tone, system workflows, compliance requirements etc.
I wouldn't want these to load every time but being able to call them is really useful.