With the new /model switcher, I wonder if there's a way to create a skill that runs at the start of a conversation and intelligently decides which model to use based on the available LLM profiles?

I don't know, it could be cool!

In my brief investigation so far OpenHands knows how to get its list of LLM profiles. I’m seeing if there's an inexpensive way for us to use OpenHands Index data to make a judgment call :)

It'd be nice to have a "Dynamic" choice for LLM profile