New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Humanize Korean Prose

by beefiker in beefiker/superloopy

Rewrites already-written Korean text to remove AI-sounding rhythm and translationese while keeping its meaning, register, facts and protected terms untouched.

MITAuto-check passedWriting & Content

Install Humanize Korean Prose

skills CLI
$ npx skills add beefiker/superloopy --skill humanize-korean -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install beefiker/superloopy humanize-korean --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/beefiker/superloopy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/humanize-korean .claude/skills/humanize-korean && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
humanize-korean
GitHub stars
111
Used in
1 other repo
Token cost
~1.7k tokens
SKILL.md length
856 words
Files
8 (incl. scripts, references)
Skills in repo
9
Repo updated
First seen
Licence
MIT

At a glance

Rewrites already-written Korean text to remove AI-sounding rhythm and translationese while keeping its meaning, register, facts and protected terms untouched.

  • Works in 11 steps: Identify source text from the prompt or… → Refuse non-Korean source text with 한국어… → Estimate genre as 공적, 리포트, 블로그, 칼럼, 대화체,… → …
  • Removing AI-sounding tone from a Korean draft before publishing
  • SKILL.md covers What This Skill Is, Comparison Examples, Contract and Workflow, plus 1 more section
  • Runs JavaScript scripts from its folder; calls node

What it does

The skill acts as a post-editor rather than a drafting tool, stripping stock transitions, translationese, inflated significance claims and repetitive sentence endings while leaving product names, numbers, dates, URLs, code, model names, acronyms and quoted spans exactly as written. A comparison table shows calibration examples, such as turning an indirect concluding phrase into a direct statement, scored at audit grade A with a 29.43% change rate; a larger set of 28 verified before and after pairs plus a modifier-placement example lives in a reference file and is checked by a bundled test.

The contract is to rewrite Korean text only, keep formal text formal and conversational text conversational, prefer fewer sharper edits over broad smoothing, and never add examples, metaphors, facts, citations or marketing claims that were not already in the source. It credits an outside project for the original Korean AI-tell ideas and adds protected-span preservation, file-backed audits and its own evidence receipts on top. It is explicitly not for translation, fact expansion, SEO rewriting, legal drafting or generic proofreading.

When your agent uses it

  • Removing AI-sounding tone from a Korean draft before publishing
  • Fixing translationese or repetitive endings in Korean copy
  • Polishing Korean text without changing its facts or claims
  • Checking a rewrite against a bundled before-and-after calibration set

Example prompts

  • “Make this Korean draft sound less AI-written, but keep the facts as they are.”
  • “This paragraph reads like a translation. Smooth it out in Korean.”
  • “The closing sentence sounds too AI-generated. Can you make it sound more natural?”

Workflow steps

11 steps, taken from the first numbered list in SKILL.md.

  1. Identify source text from the prompt or from a .txt or .md path supplied by the user.
  2. Refuse non-Korean source text with 한국어 텍스트만 처리할 수 있습니다.
  3. Estimate genre as 공적, 리포트, 블로그, 칼럼, 대화체, or 제품 문구; user-provided genre wins. Record it to describe the output register.
  4. Mark protected spans before editing: numbers, dates, units, URLs, emails, code spans, quoted spans, English acronyms, product names, model…
  5. Detect AI-tell patterns from references/quick-rules.md, prioritizing S1 then repeated S2. Include the P calque rows; the audit reports…
  6. Rewrite paragraph by paragraph in this order: protected spans unchanged, signature phrases, translationese, passive/hedging…
  7. Keep total character-change rate under 30% whenever possible; stop and report risk above 50%.
  8. Write outputs
  9. Run node skills/humanize-korean/scripts/audit-humanize-output.mjs --source --final --report --genre "". The audit records the genre in the…
  10. If audit fails, repair once. If it still fails, keep the safest version and report the failing audit reason.
  11. Respond concisely with output path, change rate, grade, preserved-token status, and 3 to 5 before/after highlights. Do not paste the full…

What it can do on your machine

Read from SKILL.md and the folder at commit 4bb19dd. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 2 files in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • node

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Humanize Korean Prose loads about 1.7k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 165 tokens; SKILL.md has 856 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~165
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~11k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from beefiker/superloopy at commit 4bb19dd, republished under its MIT licence (© beefiker). 856 words, ~1,654 tokens.

Download SKILL.mdSave it as .claude/skills/humanize-korean/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
humanize-korean
description
Korean prose humanizer for Codex and Superloopy that rewrites Korean text so it sounds naturally human while preserving meaning, register, facts, protected tokens, and evidence. Use when the user asks to remove Korean AI tells, make Korean copy sound human, fix 번역투, remove ChatGPT/Claude/Gemini tone, polish Korean without changing meaning, or says "AI 티 없애줘", "AI 윤문", "번역투 고쳐", "사람이 쓴 것처럼", "humanize Korean", "한글 AI 티 제거", "글 자연스럽게 다듬어줘". Inspired by Korean AI-tell ideas from https://github.com/epoko77-ai/im-not-ai. Handles Korean rewriting only; not for translation, fact expansion, SEO rewriting, legal drafting, or generic proofreading.

Humanize Korean

SUPERLOOPY HUMANIZE KOREAN ENABLED

What This Skill Is

Use this skill as a Korean prose post-editor: it takes already-written Korean text and removes AI-like rhythm, translationese, repetitive endings, formulaic transitions, and over-polished phrasing without changing the underlying message.

Shout out to https://github.com/epoko77-ai/im-not-ai for the Korean AI-tell inspiration. This Superloopy version keeps the workflow local, adds protected-span preservation, file-backed audits, and Superloopy evidence receipts.

Comparison Examples

Use these as calibration examples for the amount of change this skill should make. The Before side is intentionally more AI-like so the repair shape is obvious: remove stock transitions, translationese, inflated significance claims, and ~인 것입니다-style endings while preserving product names and facts.

BeforeAfter
결론적으로, Fileloom은 무료로 사용할 수 있는 파일 뷰어 앱이라고 할 수 있습니다.Fileloom은 무료로 사용할 수 있는 파일 뷰어 앱입니다.
이 앱은 PDF, EPUB, DOCX, PPTX, HWP, ZIP 등 다양한 파일 포맷을 열 수 있다는 점에서 주목할 만합니다.이 앱은 PDF, EPUB, DOCX, PPTX, HWP, ZIP 등 다양한 파일 포맷을 열 수 있습니다.
또한 광고 없이 제공되기 때문에 사용자는 파일을 확인하는 과정에 있어 방해 요소 없이 문서를 읽을 수 있는 것입니다.광고 없이 제공되기 때문에 사용자는 파일을 확인하는 과정에서 방해 요소 없이 문서를 읽을 수 있습니다.
따라서 Superloopy는 Codex 작업을 수행함에 있어 안정성을 높여주는 도구라고 할 수 있습니다.Superloopy는 Codex 작업의 안정성을 높여주는 도구입니다.
이는 계획, 검증, 증거 기록을 통해 작업의 진행 상황을 관리할 수 있다는 점에서 매우 중요한 의미를 가지고 있습니다.계획, 검증, 증거 기록으로 작업 진행 상황을 관리할 수 있습니다.

These examples scored audit grade A with protected tokens preserved and a 29.43% change rate. Do not copy their product claims into unrelated text; use them only as a rewrite-shape reference.

A much larger calibration set lives in references/golden-set.md: 28 established before/after pairs plus one semantic N-1 calibration for misplaced modifier targets. Every pair is verified against the bundled audit script by test/humanize-korean-golden.test.js.

Contract

  • Rewrite only Korean text.
  • Preserve meaning, claims, facts, numbers, dates, URLs, code, product names, model names, acronyms, and quoted spans.
  • Preserve register: formal text stays formal, conversational text stays conversational, official text stays official.
  • Prefer fewer, sharper edits over broad smoothing.
  • Do not add examples, metaphors, facts, citations, or marketing claims that were not in the source.
  • Remove em dashes and en dashes (—, –) from Korean prose (M-1): 줄표 is an English carryover and a strong AI tell in modern Korean writing. Restructure with 쉼표, 괄호, a colon, or a sentence split; write ranges with ~. Dashes inside code spans and quoted spans stay.
  • N-1 — misplaced modifier target: 정확성은 시간·수치·사양·정보·식별·일치처럼 확인 가능한 대상에 붙인다. 정확한 컴퓨터/보드/펌웨어 이미지는 공급된 관계에 따라 대상 컴퓨터 확인, 보드 모델 확인, 보드와 일치하는 펌웨어로 고친다. 정확한 시간/수치/사양/정보는 보존한다. This is semantic review guidance, not an audit pattern or grade effect.
  • P family — calques: 조용히는 사람이 하는 것이다. 프로그램은 조용히 하지 않는다. When 조용히/조용한, 우아하게, 투명하게 (unnoticed-by-the-caller sense), or 단일 진실 공급원 modifies a program action, say what the program did and which signal it did not give. P-1a, P-2, and P-4 gate the grade; P-1b, P-3, P-5, and P-6 only warn. Follow the repair ladder in references/quick-rules.md: delete first, state the symptom from supplied facts second, never insert a stock phrase such as 정본, 페일세이프, or 아무 표시 없이.
  • Preserve modality (서법, upstream v2.4): a demand (~해야 한다) stays a demand and a hedge (~일 수 있다) stays a hedge. When deontic endings dominate paragraph closings, reposition the sentence (D-6); never substitute a plain assertion. The audit counts deontic and hedge markers and warns when they decrease.
  • Load references/quick-rules.md before rewriting; load references/golden-set.md when you need more calibration pairs.
  • Load references/quality-rubric.md before grading or finalizing.
  • Use scripts/audit-humanize-output.mjs to validate any file-backed output.
  • If adapting upstream rule text, respect references/upstream-notice.md.
Show full SKILL.md (245 more words)Show less

Workflow

  1. Identify source text from the prompt or from a .txt or .md path supplied by the user.
  2. Refuse non-Korean source text with 한국어 텍스트만 처리할 수 있습니다.
  3. Estimate genre as 공적, 리포트, 블로그, 칼럼, 대화체, or 제품 문구; user-provided genre wins. Record it to describe the output register.
  4. Mark protected spans before editing: numbers, dates, units, URLs, emails, code spans, quoted spans, English acronyms, product names, model names, and legal/article references.
  5. Detect AI-tell patterns from references/quick-rules.md, prioritizing S1 then repeated S2. Include the P calque rows; the audit reports every remaining P id with its ladder step in warnings.
  6. Rewrite paragraph by paragraph in this order: protected spans unchanged, signature phrases, translationese, passive/hedging, structure/list rhythm, sentence endings, visual formatting.
  7. Keep total character-change rate under 30% whenever possible; stop and report risk above 50%.
  8. Write outputs:
    • Active Superloopy loop: .superloopy/evidence/humanize-korean/<run-id>/source.md, final.md, summary.md, audit.json.
    • No active loop: _workspace/humanize-korean/<run-id>/source.md, final.md, summary.md, audit.json.
  9. Run node skills/humanize-korean/scripts/audit-humanize-output.mjs --source <source.md> --final <final.md> --report <audit.json> --genre "<genre>". The audit records the genre in the report.
  10. If audit fails, repair once. If it still fails, keep the safest version and report the failing audit reason.
  11. Respond concisely with output path, change rate, grade, preserved-token status, and 3 to 5 before/after highlights. Do not paste the full rewritten body unless the user asks.

Superloopy Evidence

When a Superloopy loop is active, the final line of the completion note must include:

SUPERLOOPY_EVIDENCE: .superloopy/evidence/humanize-korean/<run-id>/audit.json

© beefiker, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (scripts, references) in skills/humanize-korean of beefiker/superloopy.

  • SKILL.md
  • agents/openai.yaml
  • references/golden-set.md
  • references/quality-rubric.md
  • references/quick-rules.md
  • references/upstream-notice.md
  • scripts/audit-humanize-output.mjs
  • scripts/calque-patterns.mjs

Open the folder on GitHubat commit 4bb19dd

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in beefiker/superloopy, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Humanize Korean Prose next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Humanize Korean Prose compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Humanize Korean Prose this skillbeefiker/superloopy1111 repos~1.7kAutomated safety check: PassMIT
HumanizerAzure-Samples/interview-coach-agent-framework17237 repos~5.8kAutomated safety check: PassMIT
Avoid AI Writingconorbronsdon/avoid-ai-writing4.9k3 repos~8.1kAutomated safety check: PassMIT
User-Facing Text Cleanupguillaumemeyer/watermarks-remover24k—~3.5kAutomated safety check: PassMIT
Install Anti Sloptrycompai/crm11k1 repos~881Automated safety check: PassMIT
Stop SlopXe/site7328 repos~423Automated safety check: PassMIT

Similar skills

  • Humanizer

    Azure-Samples/interview-coach-agent-framework

    Official

    Remove signs of AI-generated writing from text. An agent skill from Azure-Samples/interview-coach-agent-framework.

    172 GitHub starsUsed in 37 repos~5.8k tokens
    Writing & ContentAuto-check passed

  • Avoid AI Writing

    conorbronsdon/avoid-ai-writing

    Audit and rewrite content to remove AI writing patterns ("AI-isms").

    4.9k GitHub starsUsed in 3 repos~8.1k tokens
    Writing & ContentAuto-check passed

  • User-Facing Text Cleanup

    guillaumemeyer/watermarks-remover

    Audits prose for invisible Unicode characters and rewrites it while keeping facts, citations, code and required disclosures unchanged and the writer's voice intact.

    24k GitHub stars~3.5k tokensUpdated 3 days ago
    Writing & ContentAuto-check passed

  • Install Anti Slop

    trycompai/crm

    Install and configure the anti-slop Oxlint plugin in a local TypeScript or JavaScript repository.

    11k GitHub starsUsed in 1 repo~881 tokens
    Writing & ContentAuto-check passed

  • Stop Slop

    Xe/site

    Remove AI writing patterns from prose. An agent skill from Xe/site.

    732 GitHub starsUsed in 8 repos~423 tokens
    Writing & ContentAuto-check passed

  • Korean AI-Text Humanizer

    epoko77-ai/im-not-ai

    Diagnoses and rewrites Korean text that reads as AI-generated, fixing translationese and mechanical parallelism across 85 patterns in 10 categories, with light to heavy passes.

    5.9k GitHub starsUsed in 1 repo~1.2k tokens
    Writing & ContentAuto-check passed

More from beefiker/superloopy

All 9 skills in this repo

  • Superloopy Backend Routing

    beefiker/superloopy

    Routes backend work in the Superloopy loop harness to the right reference module, covering API contracts, schema migrations, transactions, background jobs, caching and security.

    111 GitHub starsUsed in 1 repo~3k tokens
    Auto-check passed

  • Superloopy Slides

    beefiker/superloopy

    Creates zero-dependency, animation-rich HTML slide decks that run in the browser, with style presets, PowerPoint conversion and PDF export, proven by a real-browser render.

    111 GitHub starsUsed in 1 repo~8.8k tokens
    Auto-check passed

  • Superloopy Doctor

    beefiker/superloopy

    A read-only health check for a Superloopy install or checkout: state folders, evidence files, bundled agents, hooks, wrapper and plugin registration, reported before any repair.

    111 GitHub starsUsed in 1 repo~1.9k tokens
    Auto-check passed

  • Superloopy Evidence Loop

    beefiker/superloopy

    Runs a light task loop where each goal criterion passes only when a real evidence artifact exists, with progress stored in a `.superloopy` folder.

    111 GitHub starsUsed in 1 repo~5.9k tokens
    Auto-check passed

  • ADHD-Friendly Output Style

    beefiker/superloopy

    Reshapes the agent's replies for an ADHD-friendly reading style: the next action first, numbered single-action steps, visible progress and one concrete action at the end.

    111 GitHub starsUsed in 1 repo~1.8k tokens
    Auto-check passed

  • Say It Straight

    beefiker/superloopy

    Use only after explicit Codex $superloopy:say-it-straight or Claude Code /superloopy:say-it-straight invocation to make supplied or requested prose direct, concise, and natural without changing…

    111 GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed

Categories

Questions about Humanize Korean Prose

What does Humanize Korean Prose do?

Rewrites already-written Korean text to remove AI-sounding rhythm and translationese while keeping its meaning, register, facts and protected terms untouched. The skill acts as a post-editor rather than a drafting tool, stripping stock transitions, translationese, inflated significance claims and repetitive sentence endings while leaving product names, numbers, dates, URLs, code, model names, acronyms and quoted spans exactly as written.43% change rate; a larger set of 28 verified before and after pairs plus a modifier-placement example lives in a reference file and is checked by a bundled test.

When should I use Humanize Korean Prose?

Humanize Korean Prose fits situations like: removing AI-sounding tone from a Korean draft before publishing; fixing translationese or repetitive endings in Korean copy; polishing Korean text without changing its facts or claims; checking a rewrite against a bundled before-and-after calibration set.

How do I install Humanize Korean Prose in Claude Code?

Run `npx skills add beefiker/superloopy --skill humanize-korean -a claude-code`. Or copy the skill folder (skills/humanize-korean in beefiker/superloopy) into .claude/skills/humanize-korean in your project. Claude Code loads it when a task matches its description.

How do I install Humanize Korean Prose in Codex?

Run `npx skills add beefiker/superloopy --skill humanize-korean -a codex`. Or copy the skill folder (skills/humanize-korean in beefiker/superloopy) into .agents/skills/humanize-korean in your project. Codex loads it when a task matches its description.

Can I use Humanize Korean Prose in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add beefiker/superloopy --skill humanize-korean -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/humanize-korean, .gemini/skills/humanize-korean, .github/skills/humanize-korean and .opencode/skills/humanize-korean in your project.

What does Humanize Korean Prose need to run?

Going by SKILL.md and its folder, Humanize Korean Prose needs JavaScript for the scripts in its folder and the command-line tools its instructions call (node).

Does Humanize Korean Prose access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Humanize Korean Prose safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Humanize Korean Prose use?

Humanize Korean Prose is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Humanize Korean Prose use?

About 1.7k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9.2k tokens, read only when the agent opens those files.

What are the alternatives to Humanize Korean Prose?

Skills that share tags, products or a category with Humanize Korean Prose: Humanizer (Azure-Samples/interview-coach-agent-framework, 172 stars), Avoid AI Writing (conorbronsdon/avoid-ai-writing, 4.9k stars), User-Facing Text Cleanup (guillaumemeyer/watermarks-remover, 24k stars) and Install Anti Slop (trycompai/crm, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Humanize Korean Prose?

beefiker (a GitHub user) maintains it in beefiker/superloopy, which has 111 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 6, 2026.

Source: beefiker/superloopy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.