Cleanup
SkillMediaClean up the design of a large change, or a whole codebase.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Cleanup skill
What this skill tells your AI
The instructions your AI receives, as published by mkanat/skills in skills/cleanup/SKILL.md and read by ahel’s review.
Look over the current change (or the whole codebase if there is no current change) and look for:
- Any transformations or indexes that are redundant with data structures or relationships already known earlier in the whole-program data flow.
- Any backwards-compatibility shims, unnecessary defensive code, or unnecessary deduplication.
- For any deduplication added in this change, ask yourself: could these objects have arrived here inherently deduplicated?
Print out your findings, if any. Then, fix any findings you found.
After fixing your findings, look over the code again: now that we have done that cleanup, are there any other cleanups available? Print out your new findings. Then fix them.
Continue to do that in a loop (look over the code again, find any new cleanups that are visible now that you've fixed the last ones, print them out, and fix them if you find any) until you find no more cleanups to do upon reinspection.
Signals
- GitHub stars
- 69
- Forks
- 6
- Last commit
- Aug 2026
Advanced
- Catalog kind
- skill
- Gateway key
cleanup-mkanat- Source
- github.com/mkanat/skills