I think we're largely in agreement here, though I wouldn't go so far as to say it's limited to "little tiny" things, but I guess that's a matter of scale. I use it for a lot of tooling, which is typically in the 500-5,000 line size, and it works really well for these sorts of things. A lot of them it will just one-shot and not break a sweat.
I have cases where it saves hours for sure, but they are fewer and further between. Last week we used it to solve 600+ linting warnings in 25 year old code, which probably saved me the better part of a day. It did a fantastic job of converting %-format strings to f-strings. I created a skill telling it how to test a %-to-f conversion in isolation, and it was able to use that skill to flawlessly convert all of our strings to modern usage.
I have cases where it saves hours for sure, but they are fewer and further between. Last week we used it to solve 600+ linting warnings in 25 year old code, which probably saved me the better part of a day. It did a fantastic job of converting %-format strings to f-strings. I created a skill telling it how to test a %-to-f conversion in isolation, and it was able to use that skill to flawlessly convert all of our strings to modern usage.