Skip to content
SkillModel-led546 tokens in use

Humanize

A slash command that sends Korean text or a file to the Humanize Korean pipeline and reports the status, changes and grade.

6,692 stars on the repository MIT Licenseepoko77-ai/im-not-ai · skills/humanize
/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 costs

100tokens idle
546tokens 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
  • Size11/15
  • 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 is the short entry command of the Humanize Korean plugin. Type /humanize with a Korean text or a path to a .txt or .md file, and it starts the full pipeline that removes AI habits from Korean writing.

The command does not carry its own method. It hands the input to the humanize-korean skill, which picks a light, standard or heavy path, and then reports a status line, the rewritten text, detections before and after, and three to five highlighted changes.

What You Get

  • A /humanize command that accepts pasted text or a file path
  • A one-line status with change rate, grade and self-check result
  • The rewritten text and counts of detected patterns before and after
  • A hint to run the redo command when the grade is B or lower

Common Use Cases

  • Running the Korean humanizer with a single command on pasted text
  • Rewriting a Korean markdown file by giving its path
  • Forcing precise mode on a long document with the strict option

What Makes It Unique

It is only the front door. The method lives in humanize-korean, so this skill stays small and the command is easy to remember. It can only be started by typing the command, because model invocation is disabled in its frontmatter.

Under The Hood

The skill is a short instruction file with model invocation disabled, so it runs only when you type the command. It can read a file you name and then calls the humanize-korean skill, which runs shell commands, starts sub-agents and writes files into a workspace folder. This wrapper 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