yeah it 100% depends on who you'll be sharing them with, for me its just myself and a couple agents i have on a dedicated machine so git is ideal to keep versions matching when i update something on my daily driver
personally if i have the need to move a skill/script, etc. to another one of my machines, i'll make a git repo for them (if they aren't already on git)
In my mind, an AI Engineer builds products on top of LLMs, integrating them into real software (RAG, agents, evals, inference/prompt infra).
Using Claude or Copilot to write your otherwise-normal app isn't that. That's a dev with good tooling, the same way an IDE doesn't make you an "IDE Engineer" or Google a "Search Engineer." You don't title yourself after your tools.
Most of the LinkedIn relabels are that second group borrowing the title. Nothing wrong with using AI in your day to day, especially when you understand the concepts underneath, know what it does well, and know what it doesn't. But that and "makes use of LLMs in what they build" still aren't the same job.
I've thought that skills and small scripts > MCP for quite a while now, tried out MCP in the early days (official ones, ones i made for scripts i already had), but they always end up using more tool calls/tokens than if i had just written a script + skill for claude.