I write my own Markdown
In the context of side projects, I've come to these rules for code and text:
1a) Code gets minimal review so long as I've architected the solution, built around the correct data structures (I've heard the code writes itself if the data structure is correct), and have specified the shape of the tests.
1b) Tests I review to check for overfitting, cheats, etc.
2) Comments in code can be chock-full of LLM-isms. Don't care.
3) But the Markdown files, which may be read by a person or an LLM, those must be heavily redacted, edited, and put into a human voice.
The simple reason is that LLM's, machines built to generate text, are incapable of presenting a linear flow of relevant facts without sidebars, tangents, irrelevancies, duplication, gaps, well-known style fails like overuse of stock words and phrases, layers of historical cruft, over-explanations, and qualitative fluff. In other words, they can't tell it straight.
I have only one audience, people. Some of them read the text themselves, others give it to an LLM and expect a coherent response. Both groups deserve, for their sake and mine, to get clear information.
LLM's are not there yet on telling it straight.
You might like slopless:
https://github.com/berelevant-ai/slopless
It’s a deterministic linter for English Markdown that catches a lot of common LLM writing patterns and can be used as part of an agent rewrite loop.
Might be worth trying if you want to automate part of that Markdown cleanup.
Good project nonetheless but you should put it in Show HN, more chances of being discovered than here because people wouldn't generally like the fact that you are advertising like this
Sorry, this isn't my project — I was just sharing it because I thought it was relevant here.
I only recently joined HN, so I'm still getting a feel for the norms. If that came across as self-promotion, I'll be more careful in the future.