LLMs are wonderful for this. I can't write hardly a line of shell script without looking something up. And then there are three different ways to do <thing> so I spend time beard-tugging as to which way to do it. Now I just tell the LLM what I want changed about this shell script and look at what it comes up with. 100% of the time it's fine.
Lol! This is probably my sneaky number one productivity benefit from LLMs, I would never want to go back to writing shell scripts pre-llm. So many hours wasted debugging and deciphering stack overflow over the years, dropping &,$, [[]], “”,|,<> in different places hoping to get my .shitty scripts working. Like conceptually I understand shell scripting very well, but anyone nobody can argue that bash isn’t footgun central.
