humanize-korean

humanize-korean is a skill for Claude Code, Codex from beefiker/superloopy. It costs 175 tokens per session (1,630 once invoked), scanned A, original, MIT.

A tool for rewriting Korean prose so it sounds more naturally written by a person while preserving its meaning, tone, facts, protected text, and evidence. It targets translation-like wording, repetitive endings, and formulaic AI-style phrasing.

In plain words
What is it for?
Use it to edit Korean documentation, messages, or other prose, remove common AI writing patterns, and preserve names, technical terms, facts, and supporting evidence.
Why use it?
It helps polish Korean text that feels unnatural or overly machine-written without changing the information it contains. This is useful when clarity and a natural Korean voice matter.

Skill for Claude CodeCodex

Part of the superloopy plugin — 9 skills, 6 agents, 4 hooks shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/beefiker/superloopy/humanize-korean
Any agent
npx skills add beefiker/superloopy --skill humanize-korean
Clone the repo
git clone --depth 1 https://github.com/beefiker/superloopy

Made for: Claude Code, Codex.

Or install superloopy, the plugin that ships this one along with the rest of its 9 skills, 6 agents, 4 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for humanize-korean

README.md
[![agentmods](https://agentmods.dev/badge/skills/beefiker/superloopy/humanize-korean.svg)](https://agentmods.dev/skills/beefiker/superloopy/humanize-korean)
Your own site
<a href="https://agentmods.dev/skills/beefiker/superloopy/humanize-korean"><img src="https://agentmods.dev/badge/skills/beefiker/superloopy/humanize-korean.svg" alt="Measured on agentmods" height="20"></a>
Per session 175 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,630 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00175 $0.01630
Opus 5 $0.00088 $0.00815
Sonnet 5 $0.00035 $0.00326
Haiku 4.5 $0.00017 $0.00163

Measured 6d ago against content hash 312ba327c293, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

humanize-korean scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/audit-humanize-output.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/humanize-korean/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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.

Before After
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.
  • 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.

Read the full file on GitHub · 68 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 68 lines · 175 tokens per session scan A 312ba327c293

Subscribe to this mod's changes

humanize-korean is a skill published in the GitHub repository beefiker/superloopy (108 stars, last pushed today), licensed MIT. It adds 175 tokens to every session and 1,630 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

local-rules-adapter

Route China worker-rights cases through city-specific labor-rule checks, local wage-cap verification, social-insurance or housing-fund source lookup, arbitration venue/form checks, and source-card status labels. Use when a case involves Beijing, Shanghai, Shenzhen, Guangzhou, Hangzhou, a local average-wage cap, local…

90le/worker-rights-cn · 102 tokens

xcode-localization-workflow

Plan, implement, review, and validate Apple-platform localization with Xcode String Catalogs. Use for .xcstrings setup, localizable SwiftUI and Foundation text, string tables, comments, plural and device variants, XLIFF handoff, locale UI checks, or Xcode 27 agent-assisted translation.

gaelic-ghost/socket · 69 tokens

ludoweft-localize

This skill should be used for game localization patches — when a project contains ludoweft.project.json, or when the user asks to localize, extract, translate, review, patch, or rebuild text in moddable game files, such as FreeMote info-PSB archives and MAGES visual novels. It covers resource inspection, extraction…

zeikar/ludoweft · 129 tokens

narrative-quest-content-contract

Use when narrative, quest, dialogue, objective, state, reward, localization, cinematic, and implementation teams need one explicit content contract; not for general story brainstorming or protocol review.

hoatv2211/GameStudio-CodexKIT · 44 tokens

localization-authority-audit

Use when auditing localization source authority, generated copies, translation keys, missing or extra entries, mismatched text, encoding, mojibake, or client and server localization drift.

hoatv2211/GameStudio-CodexKIT · 42 tokens

magical-translation

Translate, interpret, and localize user-facing text using the deterministic translation locale from the Grimoire session config cache.

hon454/grimoire · 29 tokens