Of course. This has been proven again and again on the economic level. People have to let go of old skills and learn new ones to survive.

For AI though, there is a mental angle which is being discussed now (brain gyms etc.) which was an early concern of mine. When we make something, there is an tangible value created for the buyer/consumer but there is also a more subtle positive effect the on the builder/maker. e.g. even if it's it's cheaper, faster, (and in an imaginary worlds), more healthy to buy packaged food, sitting down and making it subtly changes the chef who makes the food. Sort of the motivation for a grandmother baking a cake for her grandkids.

I've been able to realise many of my abandoned projects due to AI. I can spin up a few agents and have them build things completely without intervention more or less. Many of these are programs I use daily. This is definitely huge. However, I remember the kick of struggling with problems during projects which was where most, if not all, the learning happened. All that experience is what makes me able to command and control these agents properly. It had an effect on me beyond the outcome (most of the projects are dead/abandoned anyway). Another example - I remember an old company called "Bond" which had a robot to create stationery using a calligraphic hand. Contrast that to the almost spiritual effect doing calligraphy has on a master penman. Using automation to create fine calligraphy gets you the former but the individual and society loses the latter. It's not immediately clear to me what the end result will be but I do feel that a lot is being lost.

This is the problem.

While I agree that new skills must be learnt to survive, what exactly are these new skills in the AI-age?

I see this line everywhere - whenever someone's mourning their loss of a career, there's responses telling the person to "man up" (for lack of a better phrase) and learn new skills. Nobody says what these "new skills" are?

I like that calligraphy example, I am afraid that's how a field would stagnate: the tools become advanced, but now with less and less people wanting to approach and struggle with learning the field, the human intuition, the community effort, and the mastery to push past the bleeding edge withers.

(Unless if AGI could do something like that.)

Stuff that used to be hard is easy.

You're blind to the stuff that's easy making previously impossible things hard.