LoRA's are more robust than context tokens - their influence remains strong over long contexts and do a much better job of actually changing behavior rather than mimicking a desired behavior via instruction.

But even if LoRA isn't it - the point is that "skill" seems like the wrong term for something that already has a name: instructions. These are instruct-tuned models. Given instructions they can do new things; this push to rebrand it as a "skill" just seems like marketing.