Is the Humanize Korean skill free?

Yes. The skill itself is free from beefiker/superloopy. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Humanize Korean SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.

How do I install Humanize Korean?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Humanize Korean with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Humanize Korean

Rule-based Korean AI-tell remover that preserves facts and protected spans, with a live audit gate.

by beefiker · beefiker/superloopy

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 13, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 0d6dd04

Ran a real AI-flavored Korean paragraph through both versions: the skill-guided rewrite stripped every tell in the rule table (결론적으로, 을 통해, 또한, 주목할 만하다) that the baseline left half-fixed, but hand-tracing the bundled audit script's own regexes showed it pushed the change rate to 52% — over the script's own 50% fail ceiling — so full mechanical rule application on short, dense text needs to be dialed back to stay inside the tool's own gate.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 4/5

What Humanize Korean does

Rewrites Korean prose against a 30-plus-pattern AI-tell table (translationese like '~을 통해', formulaic pivots like '결론적으로', double passives, vague significance claims) while freezing protected spans such as numbers, URLs, and product names, then runs a bundled Node audit script that grades the rewrite and caps the character-change rate. Triggers on Korean-specific 'AI 티 제거'/humanize requests; explicitly excludes translation, SEO rewriting, and non-Korean text.

How to install Humanize Korean

git clone https://github.com/beefiker/superloopy
cd superloopy
mkdir -p ~/.claude/skills
cp -r skills/humanize-korean ~/.claude/skills/humanize-korean

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Humanize Korean

/humanize-korean Rule-based Korean AI-tell remover that preserves facts and protected spans, with a live audit gate.

It also activates on plain-language prompts like these:

이 한국어 문장에서 AI 티 나는 표현 좀 없애줘, 숫자랑 링크는 그대로 두고
번역투 느낌 나는 이 글 자연스럽게 다듬어줘, 결론적으로 같은 표현 빼고
이 보고서 문단이 너무 AI스러운데 사실관계는 유지하면서 다듬어줄 수 있어?

Frequently asked questions

Is the Humanize Korean skill free?: Yes. The skill itself is free from beefiker/superloopy. SkillProof publishes the install command and an independent test verdict at no cost.
Does Humanize Korean work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 13, 2026. Verdict: Tested · Works. Ran a real AI-flavored Korean paragraph through both versions: the skill-guided rewrite stripped every tell in the rule table (결론적으로, 을 통해, 또한, 주목할 만하다) that the baseline left half-fixed, but hand-tracing the bundled audit script's own regexes showed it pushed the change rate to 52% — over the script's own 50% fail ceiling — so full mechanical rule application on short, dense text needs to be dialed back to stay inside the tool's own gate.
What is the Humanize Korean SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Humanize Korean?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Humanize Korean with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.