YHK - yet another hacker news clone

Three or four dollars maybe? Skills.sh is probably the main one, run by vercel. I'm happy if there's a good independent one, rather than curated by a big company. No comment on whether this one is good though.

LLM harnesses haven’t retired the feature

If the skill is a process then very effective. Do x, then y, then z, then if w do... Whatever.

Or things like style guides, or instructions I find myself typing over and over.

Look at something basic like reading a file that the LLM can't read natively, a PDF or whatever. There's hundred of ways to extract the data but rather than let the agent choose randomly each time I can set up a read PDF skill and specify my preferred way to do it.

You can have LLMs do something via a prompt, then you can try making a skill for it and see how the behavior changes.

IMO still very very useful for repetitive tasks that you want done a certain way.

Your mileage may vary. So you should experiment.