[alexwwang]

I am trying to avoid this by building a plugin based on my memory management project Aristotle. I add a status machine to monitor the activities of LLM while it does jobs following my tdd-pipeline skills, which begins with requirements clarification and ends up with delivery.

These two projects are on GitHub, you may search alexwwang/aristotle and alexwwang/tdd-pipeline to dive into the details or just ask your LLM to scan them to tell you the points you are interested in.