I've been thinking about this a lot recently. I've been using Git for about 20 years, but I've never considered myself a Git expert because I have to look up how to do things like a git bisect or a history rewrite beyond just the first "git commit --amend"
But now... I use a ton of advanced Git features several times a week, because just knowing that it's possible to do something is enough for me to tell Codex or Claude Code to do that thing.
So maybe Git mastery now is more about concepts? You need to understand the DAG and roughly what's in the .git folder and origins and branches and tags and commits and so forth, but you don't need to remember the syntax.
Exactly, and now imagine that somebody introduces a tool even better than Git. Normally that tool would have major adoption problems because it would have to dislodge the incumbent standard that everybody's familiar with, and that everybody can at least tolerate.
But if you aren't even issuing commands directly to Git, suddenly it starts to look like there is room for improvement without the pain of learning a new tool or a new paradigm. That's a bigger deal than I think most people appreciate.
But now... I use a ton of advanced Git features several times a week, because just knowing that it's possible to do something is enough for me to tell Codex or Claude Code to do that thing.
So maybe Git mastery now is more about concepts? You need to understand the DAG and roughly what's in the .git folder and origins and branches and tags and commits and so forth, but you don't need to remember the syntax.