Skip to content
SkillModel-led605 tokens in use

Humanize Redo

A slash command that reruns the latest Korean humanizing result for one category, one paragraph or a different strength, up to three rounds.

6,692 stars on the repository MIT Licenseepoko77-ai/im-not-ai · skills/humanize-redo
/plugin marketplace add epoko77-ai/im-not-ai /plugin install humanize-korean@im-not-ai
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Humanize Redo costs

97tokens idle
605tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Fair
  • Frontmatter8/15
  • Structure16/25
  • Examples3/15
  • Output0/15
  • Size13/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity96
  • Maintenance100
  • Community64
  • Maturity28
  • Momentum40

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.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers