How do you find skills, keep them organized, and make sure they actually work? Do you keep improving them over time?
I believe skills will eventually be eating by model capabilities, but until then I'm just looking for a better way to manage things.
An Ask HN thread surfaces a practical pain point emerging around agentic AI tooling: developers are accumulating 'skills' files for their models and lack established conventions for discovering, organizing, testing, and iterating on them. The poster also raises the open question of whether such scaffolding is a temporary crutch that improving model capabilities will absorb.
How do you find skills, keep them organized, and make sure they actually work? Do you keep improving them over time?
I believe skills will eventually be eating by model capabilities, but until then I'm just looking for a better way to manage things.