Humanizer
daleseo/korean-skillsAI written Korean text often has telltale patterns. It might use too many commas or sound stiff. This skill spots those patterns and rewrites the text to flow like a human wrote it.
The tool is based on real language research from a paper called KatFishNet. It checks for 40 different signs of AI writing, like odd spacing or overused words. Each sign is rated by how serious it is.
You can use this skill to polish text from ChatGPT, Claude, or Gemini. The meaning stays the same but the words feel natural. It works only for Korean and keeps your original message intact.
Add Humanizer skill to your workflow
Global
mkdir -p ~/.claude/skills/humanizerProject
mkdir -p .claude/skills/humanizerSource Repository
More Prompt Engineering & Context Engineering Claude Code Skills
Cavemanjuliusbrussee/caveman
Talk like a smart caveman to save tokens without losing technical accuracy
Cavemanmattpocock/skills
Caveman mode for AI cuts token count 75% without losing technical accuracy
Enhance Promptgoogle-labs-code/stitch-skills
Turn vague UI ideas into clear, polished prompts with design system consistency
Humanizer Zhop7418/humanizer-zh
Remove AI writing patterns to make your text sound natural and human
Gws Modelarmorgoogleworkspace/cli
Filter harmful user content automatically with Google Model Armor for safety
Prompt Engineering Patternswshobson/agents
Master advanced prompt engineering patterns to get reliable and powerful AI outputs every time
Context Engineeringaddyosmani/agent-skills
Optimize your agent's context to improve output quality and focus
Writetw93/waza
Rewrite your prose to sound human and natural every time