Not the original commenter, but I feel pretty strongly that frameworks for software review loops are at best training wheels for people who haven't yet developed the right understanding. I don't use any sort of complex skills framework, I just tell the AI what I want while leaving reasonable Claude-sized gaps to fill in, and my results are usually better and often faster than people who get lost in framework management. Perhaps they're more useful for pure greenfield development, but for most software developers who are working on existing systems I have not seen a strong use case for them.

There's one guy I know who constantly has problems with Claude going off-script, and every time I dig in, it's clear that the poor thing is so overloaded with instructions and skill lists that it can't figure out what he actually wants it to do.

The frameworks-and-tools make for good blog fodder too, as they are quite applicable across a range of areas, so many readers will find something that resonates with them, and claude-code-is-pretty-good-these-days is a less blogworthy topic.