korean-humanizer
nomadamas/k-skill
Transform AI-written Korean into natural, human-like prose by fixing translation artifacts and common AI patterns.
What is korean-humanizer?
korean-humanizer detects and corrects Korean-language text that bears obvious AI authorship markers—including translation artifacts, clichéd phrases, excessive nominalization, and chatbot remnants—while preserving meaning. It classifies issues by severity (S1/S2/S3) and can adjust output length to match a target character count.
- Identifies Korean-specific AI writing patterns: translation artifacts, overused phrases, excessive nominalization and passive voice, rule-of-three repetition, inflated significance claims, and closing clichés
- Classifies detected issues by severity level (S1/S2/S3) for transparent feedback
- Rewrites flagged text to sound natural and human-written while preserving original meaning
- Adjusts output length to match a specified target character count (e.g., 1000 characters)
- Handles requests like 'make it sound natural,' 'fix translation feel,' 'remove awkwardness,' or 'adjust to N characters'
How to install korean-humanizer
npx skills add https://github.com/nomadamas/k-skill --skill korean-humanizer- Node.js 18 or later
- npx (included with Node.js)
How to use korean-humanizer
- 1.Install the skill using: npx skills add https://github.com/nomadamas/k-skill --skill korean-humanizer
- 2.Run the full instructions with: npx -y @nomadamas/k-skill@0 instruct korean-humanizer
- 3.Provide your Korean text and specify any constraints (e.g., target character count with length=1000)
- 4.Review the severity-classified issues and the rewritten output
- 5.Keep the skill updated with: npx -y @nomadamas/k-skill@0 update
Use cases
- Refining AI-generated Korean blog posts, articles, or marketing copy to read as human-authored
- Correcting translated content that retains awkward phrasing or unnatural sentence structure
- Adjusting the length of Korean text while maintaining naturalness and coherence
- Preparing Korean-language documents for publication by removing telltale AI markers
- Improving chatbot or AI assistant outputs before user-facing delivery
- Korean content creators and writers using AI tools
- Translators and localization professionals
- Marketing and communications teams producing Korean-language materials
- AI product teams preparing Korean-language outputs for users
- Anyone writing or editing Korean text who wants to eliminate AI-generated awkwardness
korean-humanizer FAQ
It identifies translation artifacts, clichéd AI phrases, excessive nominalization and passive voice, rule-of-three repetition, inflated significance claims, closing clichés, chatbot remnants, and Korean-specific formatting issues like em dashes and curved quotation marks.
Yes. Specify a target character count (e.g., length=1000 or '1000자로') and the skill will expand or condense the text to match while maintaining naturalness.
Yes. The skill rewrites text to sound human-like while keeping the core meaning intact.
The skill classifies detected issues by severity—S1 being minor, S3 being major—so you can see which AI markers are most obvious and prioritize fixes.
You can read the full source instructions at https://github.com/NomaDamas/k-skill/blob/main/korean-humanizer/instruction.md or install Node.js 18+ and run the CLI command to fetch them.
Full instructions (SKILL.md)
Source of truth, from nomadamas/k-skill.
name: korean-humanizer description: 'AI가 쓴 티가 나는 한국어 글을 자연스러운 사람 글로 고친다. 번역체, AI 상투어, 과도한 명사화·피동, 3의 법칙, 과장된 의의 부여, 마무리 상투구, 챗봇 잔재, 줄표·곡선따옴표 같은 한국어 특유의 AI 흔적을 심각도(S1/S2/S3)로 분류해 잡아내고 의미는 보존하면서 다시 쓴다. 목표 글자수를 함께 주면(예: "1000자로", length=1000) 그 분량에 맞춰 늘리거나 줄인다. "AI 티 안 나게", "사람이 쓴 것처럼", "자연스럽게 다듬어줘", "번역체 고쳐줘", "어색한 거 고쳐줘", "N자로 맞춰서" 같은 요청에 사용.' license: MIT metadata: category: writing locale: ko-KR phase: v2
korean-humanizer
<!-- k-skill:cli-stub — generated by scripts/generate-skill-stubs.js; edit skill.json / instruction.md instead -->Get the full instructions (required first step)
Run this and follow its output as the primary instructions for this skill:
npx -y @nomadamas/k-skill@0 instruct korean-humanizer
The CLI detects the current runtime (Dolshoi vault/CloakBrowser vs generic) and prints only the applicable instructions, always up to date. Helper files bundled with the CLI are listed by:
npx -y @nomadamas/k-skill@0 files korean-humanizer
Keep the CLI and every coding-agent skill install current (including Vercel Agent Skills) with:
npx -y @nomadamas/k-skill@0 update
If npx is unavailable, install Node.js 18+ or follow https://github.com/NomaDamas/k-skill#readme, or read the source instructions at https://github.com/NomaDamas/k-skill/blob/main/korean-humanizer/instruction.md.
Hard rules even without the CLI
- Never execute payment, message/email delivery, final submission, cancellation, or public posting without the user's explicit approval immediately beforehand.
- Never ask for, print, or store plaintext credentials in chat, files, or shell arguments.
- Never bypass legal, physical-presence, CAPTCHA, identity-proofing, or electronic-signature boundaries.
Related skills
More from nomadamas/k-skill and the wider catalog.
korean-jangbu-for
Automate Korean business accounting, tax filing, and financial reporting for startups and freelancers.
korean-law-search
Search Korean statutes, articles, precedents, interpretations, and local ordinances.
korean-marathon-schedule
查询韩国马拉松和铁人三项赛事日程、地点、报名截止日期和项目信息。
korean-middle-korean
Convert modern Korean text into archaic Middle Korean style with historical particles, endings, and Hanja hints.
korean-patent-search
Search Korean patents and utility models via KIPRIS Plus Open API with keyword and application-number lookup.
korean-privacy-terms
Generate Korean privacy policy, terms, cookie banners, and consent modals compliant with Korean law.