humanize
humanize is a skill in epoko77-ai/im-not-ai, last changed 1 Sept 2026. It is instructions only: no scripts, no named hosts and no pre-approved tools. Our pattern check flagged nothing at commit b37e020 on 27 Oct 2026.
Pattern check: nothing flagged · commit b37e020 · 27 Oct 2026
InstallAI가 쓴 한글 텍스트를 자연스럽게 윤문하는 진입 명령. humanize-korean 파이프라인을 shim 의 route_hint 가 정한 경로(light 1콜 · standard 2콜 · heavy 3+콜)로 실행하고 `--strict`면 heavy 고정. 트리거 — "/humanize".
- Licence
- MIT
- Repo stars
- 6.3k
- Folder last changed
- 1 Sept 2026 (opens in a new tab)
- Publisher
- epoko77-ai
- Files
- 1 file
- Checked
- b37e020 (opens in a new tab) · 27 Oct 2026
Install
Each tab says whether it installs commit b37e020, the one we checked, or the latest version.
No tab for your agent? Use Any agent for OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity, and Claude Code for Cline. Kiro needs the folder copied by hand.
Pinned to commit b37e020, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&
git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/epoko77-ai/im-not-ai.git "$tmp" &&
git -C "$tmp" fetch -q --depth 1 origin b37e0206d31fffd9149bf57168d4d62eb2086bee &&
git -C "$tmp" sparse-checkout set -- skills/humanize &&
git -C "$tmp" checkout -q b37e0206d31fffd9149bf57168d4d62eb2086bee &&
mkdir -p .claude/skills &&
mkdir .claude/skills/humanize &&
cp -R "$tmp"/skills/humanize/. .claude/skills/humanize/ &&
rm -rf "$tmp"If Claude Code was already running and this created the skills folder, run /reload-skills.
Or install the humanize-korean plugin it ships in. Installs the latest version, not the one we checked. Installs everything in the plugin, including any hooks, MCP servers and scripts our check doesn't cover.
claude plugin marketplace add epoko77-ai/im-not-ai --scope project &&
claude plugin install humanize-korean@im-not-ai --scope projectPinned to commit b37e020, the one we checked.
Skills in the Claude apps belong to your account rather than to a project.
Make humanize.zip, with the skill folder at the top level:
tmp="$(mktemp -d)" &&
git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/epoko77-ai/im-not-ai.git "$tmp" &&
git -C "$tmp" fetch -q --depth 1 origin b37e0206d31fffd9149bf57168d4d62eb2086bee &&
git -C "$tmp" sparse-checkout set -- skills/humanize &&
git -C "$tmp" checkout -q b37e0206d31fffd9149bf57168d4d62eb2086bee &&
out="$(mktemp -d)" &&
cp -R "$tmp"/skills/humanize "$out"/humanize &&
(cd "$out" && zip -qr - humanize) > humanize.zip &&
rm -rf "$tmp" "$out"In Claude, open Customize > Skills, select +, then + Create skill > Upload a skill, and choose humanize.zip.
On Free, Pro and Max plans, turn on Code execution and file creation (Create and edit files in newer settings) under Settings > Capabilities.
Pinned to commit b37e020, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&
git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/epoko77-ai/im-not-ai.git "$tmp" &&
git -C "$tmp" fetch -q --depth 1 origin b37e0206d31fffd9149bf57168d4d62eb2086bee &&
git -C "$tmp" sparse-checkout set -- skills/humanize &&
git -C "$tmp" checkout -q b37e0206d31fffd9149bf57168d4d62eb2086bee &&
mkdir -p .agents/skills &&
mkdir .agents/skills/humanize &&
cp -R "$tmp"/skills/humanize/. .agents/skills/humanize/ &&
rm -rf "$tmp"Codex picks up new skills on its own; restart it if this one does not appear.
Pinned to commit b37e020, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&
git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/epoko77-ai/im-not-ai.git "$tmp" &&
git -C "$tmp" fetch -q --depth 1 origin b37e0206d31fffd9149bf57168d4d62eb2086bee &&
git -C "$tmp" sparse-checkout set -- skills/humanize &&
git -C "$tmp" checkout -q b37e0206d31fffd9149bf57168d4d62eb2086bee &&
mkdir -p .cursor/skills &&
mkdir .cursor/skills/humanize &&
cp -R "$tmp"/skills/humanize/. .cursor/skills/humanize/ &&
rm -rf "$tmp"Pinned to commit b37e020, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&
git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/epoko77-ai/im-not-ai.git "$tmp" &&
git -C "$tmp" fetch -q --depth 1 origin b37e0206d31fffd9149bf57168d4d62eb2086bee &&
git -C "$tmp" sparse-checkout set -- skills/humanize &&
git -C "$tmp" checkout -q b37e0206d31fffd9149bf57168d4d62eb2086bee &&
mkdir -p .github/skills &&
mkdir .github/skills/humanize &&
cp -R "$tmp"/skills/humanize/. .github/skills/humanize/ &&
rm -rf "$tmp"In a running Copilot CLI session, run /skills reload.
Or install it with gh skill, which also installs the commit we checked. Needs GitHub CLI 2.90 or later.
gh skill install epoko77-ai/im-not-ai skills/humanize/SKILL.md@b37e0206d31fffd9149bf57168d4d62eb2086bee --agent github-copilot --scope projectPinned to commit b37e020, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&
git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/epoko77-ai/im-not-ai.git "$tmp" &&
git -C "$tmp" fetch -q --depth 1 origin b37e0206d31fffd9149bf57168d4d62eb2086bee &&
git -C "$tmp" sparse-checkout set -- skills/humanize &&
git -C "$tmp" checkout -q b37e0206d31fffd9149bf57168d4d62eb2086bee &&
mkdir -p .gemini/skills &&
mkdir .gemini/skills/humanize &&
cp -R "$tmp"/skills/humanize/. .gemini/skills/humanize/ &&
rm -rf "$tmp"In a running session, run /skills reload.
Or use Gemini CLI’s own installer. Installs the latest version, not the one we checked.
gemini skills install https://github.com/epoko77-ai/im-not-ai.git --path skills/humanize --scope workspacePinned to commit b37e020, the one we checked.
Codex, Cursor, Copilot, VS Code, Gemini CLI, OpenCode, Goose, Amp and Zed all read .agents/skills; Claude Code and Kiro list only their own folders.
From your project's root folder:
tmp="$(mktemp -d)" &&
git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/epoko77-ai/im-not-ai.git "$tmp" &&
git -C "$tmp" fetch -q --depth 1 origin b37e0206d31fffd9149bf57168d4d62eb2086bee &&
git -C "$tmp" sparse-checkout set -- skills/humanize &&
git -C "$tmp" checkout -q b37e0206d31fffd9149bf57168d4d62eb2086bee &&
mkdir -p .agents/skills &&
mkdir .agents/skills/humanize &&
cp -R "$tmp"/skills/humanize/. .agents/skills/humanize/ &&
rm -rf "$tmp"Or use the skills CLI from skills.sh. Installs the latest version, not the one we checked. The skills CLI reports installs to skills.sh unless you set DISABLE_TELEMETRY=1.
npx skills@1.7.4 add epoko77-ai/im-not-ai --skill humanizeWhat it can touch
From the files and frontmatter at commit b37e020. This is how much a skill can do, not whether it is risky.
What it can touch: Instructions only
It is instructions only: no scripts, no named hosts and no pre-approved tools.
Pattern check
Pattern check: nothing flagged · commit b37e020 · 27 Oct 2026
We checked every text file in this skill, at commit b37e020 on 27 Oct 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.
Format check
Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.
Agent Skills specPasses with warnings
The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.
- Warning
Fields outside the spec: argument-hint (read by Claude Code and VS Code) and disable-model-invocation (read by Claude Code and VS Code). Uploads to the Claude apps and API, and the spec's validator, reject the file; most agents ignore these fields. O1
Fix: Delete them for a portable skill, or keep them if you only target the agents that read them.
- Note
The description doesn't say when to use the skill. D6
Fix: Add a sentence such as "Use when …" naming the requests or files that should trigger it.
- Note
There is no license field, so readers can't tell whether they may reuse the skill. O2
Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.
- Warning
- Claude CodePasses
Claude apps & API uploadFails
Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.
- Error
Upload and packaging fail on fields outside the spec: argument-hint and disable-model-invocation. O1
Fix: Delete them, and keep your own data under metadata as text values.
- Error
OpenAI (Codex & API)Passes with warnings
Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.
- Warning
Fields outside the spec: argument-hint and disable-model-invocation. Codex ignores them; OpenAI doesn't say whether its upload accepts them. O1
Fix: Delete them, or move your own data under metadata as text values.
- Warning
- VS Code & CopilotPasses
SKILL.md
Files
1 file
| Path | Size |
|---|---|
| SKILL.md (opens in a new tab) | 1.7 KB |
More from epoko77-ai/im-not-ai
commit-ko
epoko77-ai/im-not-ai
AI(Claude 등)가 제안한 한글 커밋 메시지의 사무적·번역투 어휘("~을 수행함", "~을 진행함", "~적 개선을 실시함" 등)를 실제 개발자가 쓰는 자연스러운 한국어 커밋 메시지로 다듬는 스킬. humanize-korean과 달리 산문 문단이 아니라 1~2줄짜리 커밋 메시지 register에 특화되어 진단·청킹 없이 단일 콜로 즉시 처리한다. 트리거 — "커밋 메시지 자연스럽게", "커밋 메시지 다듬어줘", "이 커밋 메시지 AI 티 나", "commit message 한국어로 자연스럽게", "커밋 메시지 어색해", "커밋 메시지 사람처럼".
- Instructions only
Pattern check: Nothing flaggedMIT · 6.3k repo stars · Updated 18 Aug 2026
humanize-korean
epoko77-ai/im-not-ai
AI(ChatGPT·Claude·Gemini 등)가 쓴 한글 텍스트를 "사람이 쓴 글처럼" 윤문해주는 오케스트레이터 스킬. 번역투·영어 인용 과다·기계적 병렬·관용구·피동태 남용·접속사 남발·리듬 균일성·이모지/불릿 과다 등 10대 카테고리 85개 AI 티 패턴을 탐지·분류해 내용은 한 글자도 건드리지 않고 문체·리듬·표현만 자연스러운 한국어로 재작성한다. shim의 route_hint(light|standard|heavy)로 경로를 정해 잘 쓴 글은 1콜, 표준은 2콜, 중증·장문만 3+콜(진단→겨냥 윤문→finalize)로 처리한다. 트리거 — "AI 티 없애줘", "AI 같은 글 자연스럽게", "GPT/ChatGPT 문체", "AI 번역투 고쳐", "사람이 쓴 것처럼 윤문", "AI 윤문", "ChatGPT 티 제거", "한글 AI 탐지·윤문", "AI 글 사람처럼", "번역투 제거", "영어 인용 많은 글 윤문", "AI 글 티 안 나게", "휴머나이저", "humanize Korean", "AI detector bypass 한글". 후속 작업 — "특정 카테고리만 다시", "윤문 강도 조정", "장르 바꿔서", "이 문단만", "2차 윤문" 도 모두 이 스킬. 단순 맞춤법·오탈자 교정은 직접 처리, 번역은 번역 스킬, 내용 추가·삭제를 동반한 재작성은 별도 집필 스킬.
- Runs shell commands
- Bundles scripts
Pattern check: Nothing flaggedMIT · 6.3k repo stars · Updated 12 Oct 2026
humanize-korean
epoko77-ai/im-not-ai
AI(ChatGPT·Claude·Gemini)가 쓴 한글 텍스트를 사람이 쓴 글처럼 진단·윤문·검증한다. 번역투, 기계적 병렬, 관용구, 피동, 접속사, 균일한 리듬 등 10대 카테고리 85개 패턴을 다루며 route_hint에 따라 light·standard·heavy 경로를 실행한다. "AI 티 없애줘", "AI 윤문", "사람이 쓴 것처럼", "번역투 고쳐", "정밀 모드", "2차 윤문", "이 문단만 다시", "humanize Korean" 요청에 사용한다. 단순 맞춤법 교정, 번역, 사실이나 내용을 추가하는 재작성에는 사용하지 않는다.
- Runs shell commands
- Bundles scripts
Pattern check: 1 item to reviewMIT · 6.3k repo stars · Updated 23 Sept 2026
humanize-korean
epoko77-ai/im-not-ai
AI(ChatGPT·Claude·Gemini)가 쓴 한글 텍스트를 사람이 쓴 글처럼 윤문한다. 번역투·영어 인용 과다·기계적 병렬·관용구·피동 남용·접속사 남발·리듬 균일·이모지/불릿 과다 등 10대 카테고리 70개 AI 티 패턴을 탐지·분류해 내용은 한 글자도 건드리지 않고 문체·리듬·표현만 자연스럽게 재작성한다. 트리거 — "AI 티 없애줘", "AI 윤문", "ChatGPT 티 제거", "번역투 고쳐", "사람이 쓴 것처럼", "humanize Korean". 단순 맞춤법 교정·번역·내용 추가는 대상 아님.
- Instructions only
Pattern check: Nothing flaggedMIT · 6.3k repo stars · Updated 23 Sept 2026
humanize-redo
epoko77-ai/im-not-ai
가장 최근 윤문 결과를 2차로 다시 다듬는다 — 특정 카테고리·문단·강도 조정도 가능. humanize-korean strict 윤문(Phase B)을 기존 run_id에 재실행해 잔존 finding을 처리한다. 트리거 — "/humanize-redo".
- Instructions only
Pattern check: Nothing flaggedMIT · 6.3k repo stars · Updated 18 Aug 2026
humanize-scan
epoko77-ai/im-not-ai
한글 글에 AI 티가 얼마나 있는지 재고, 실제로 고치면 어떻게 되는지 표본으로 보여주는 정찰 스킬. 실측 판별력 상위 6개만 본다. 워크스페이스·진단·게이트·서브에이전트 없이 이 대화 안에서 끝낸다(파일 0개, 서브에이전트 0회). 손볼 게 많다고 나오면 전수 윤문은 humanize-korean(=/humanize)으로 넘긴다. 트리거 — "이 글 AI 같아?", "AI 티 있나 봐줘", "스캔해줘", "윤문 돌릴 값어치 있나", "AI 티 점수", "quick humanize", "/humanize-scan".
- Instructions only
Pattern check: Nothing flaggedMIT · 6.3k repo stars · Updated 21 Sept 2026