Yep - this has worked well for me too. I do it a little differently:

I have a /review-sessions command & a "parse-sessions" skill that tells Claude how to parse the session logs from ~/.claude/projects/, then it classifies the issues and proposes new skills, changes to CLAUDE.md, etc. based on what common issues it saw.

I've tried something similar to DISCOVERIES.md (a structured "knowledge base" of assumptions that were proven wrong, things that were tried, etc.) but haven't had luck keeping this from getting filled with obvious things (that the code itself describes) or slightly-incorrect things, or just too large in general.

100%. I like the idea of turning it into a SKILL.

I do have to perform more manual adjustments/consolidation to the final postmortem before placing it in the discoveries md file, because as you pointed out LLMs tend to be exceptionally verbose.