Humanize Redo is the follow-up command of the Humanize Korean plugin. It finds the most recent run folder in the current directory and starts the rewrite step again, so a first result can be refined without a fresh start.
You can say which category to fix again, which paragraph to touch, whether to lower or raise the strength, or ask for a rollback of a change. Each round is saved as a new version and the previous final file is kept as a backup.
What You Get
- A second or third rewrite round on the latest run
- Versioned output files, with the earlier final file kept as a backup
- A comparison table and a new grade after each round
- A stop at round three with a recommendation for human review
Common Use Cases
- Redoing only the translation-style fixes after a first pass left some behind
- Rewriting one paragraph that still reads like AI
- Lowering the strength after a result changed too much
What Makes It Unique
It reuses the findings and files of the previous run, so only the requested part is redone and the earlier version stays on disk. Instructions are short phrases such as one category only or lower the strength, and a rollback request can undo a single edit.
Under The Hood
The skill is a short instruction file with model invocation disabled, so it runs only when you type the command. It searches the workspace folder for the latest run, reads its findings, calls the rewriter and review agents, and writes new versioned files and a backup of the previous final file into that folder. It has no scripts of its own and does not fetch web pages or call outside APIs.