Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/kensuh-humanize
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 26, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/humanize
What's inside
- Skill name
humanize- Description
- AI가 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".
- License
- MIT
- Instructions
- 30 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# /humanize — 한글 AI 티 제거 `humanize-korean` 스킬을 발동해 인자로 전달된 한글 텍스트(또는 파일)에 윤문을 실행한다. ## 입력 $ARGUMENTS ## 동작 1. 인자가 비면: "윤문할 텍스트를 붙여넣어 주세요" 안내 후 종료. 2. 인자가 파일 경로(.txt/.md)면 `Read`로 본문 로드. 3. 인자가 텍스트면 그대로 입력으로 사용. 4. `humanize-korean` 스킬 SKILL.md 절차(Phase 0 → 결과 전달)를 따른다 — 경로는 **route_hint**(light|standard|heavy)가 정하고, `--strict` 시 heavy 고정. 5. 결과 전달: - 한 줄 상태(변경률 / 등급 / 자체검증 통과) - 윤문본 본문(마크다운 블록) - 카테고리별 탐지 건수 before/after - 주요 변경 하이라이트 3~5건 - 등급 B 이하면 "`/humanize-redo`로 2차 윤문 가능" 안내 ## 옵션 (인자 끝에 자연어로) - `장르: 칼럼|리포트|블로그|공적` — 장르 명시 (생략 시 첫 300자로 자동 추정) - `강도: 보수|기본|적극` — 윤문 강도 (기본값: 기본) - `최소심각도: S1|S2|S3` — 탐지 임계값 (기본값: S2) - `--strict` — 정밀 3콜(진단→겨냥 윤문→finalize) 강제 ## 참고 - 분류 체계: `humanize-korean/references/ai-tell-taxonomy.md` - 윤문 처방: `humanize-korean/references/rewriting-playbook.md`
From KenSuh/open-agent-harness, MIT.
More from KenSuh/open-agent-harness
- 0.606score
gpt-5-4-prompting
KenSuh
Internal guidance for composing Codex and GPT-5.4 prompts for coding, review, diagnosis, and research tasks inside the Codex Claude Code plugin
SkillAFreshness: A★ 3Claude Code +9 - 0.605score
humanize-korean
KenSuh
AI(ChatGPT·Claude·Gemini 등)가 쓴 한글 텍스트를 "사람이 쓴 글처럼" 윤문해주는 오케스트레이터 스킬.
SkillAFreshness: A★ 3Claude Code +9 - 0.604score
computer-use
KenSuh
Drives the GUI of a visible local app window through `orca computer`: accessibility tree, clicks, typing, menus, dialogs, and screenshots in native apps and…
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
humanize-scan
KenSuh
한글 글에 AI 티가 얼마나 있는지 재고, 실제로 고치면 어떻게 되는지 표본으로 보여주는 정찰 스킬.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
humanize-redo
KenSuh
가장 최근 윤문 결과를 2차로 다시 다듬는다 — 특정 카테고리·문단·강도 조정도 가능.
SkillAFreshness: A★ 3Claude Code +9 - 0.598score
codex-cli-runtime
KenSuh
Internal helper contract for calling the codex-companion runtime from Claude Code
SkillAFreshness: A★ 3Claude Code +9 - 0.593score
codex-result-handling
KenSuh
Internal guidance for presenting Codex helper output back to the user
SkillAFreshness: A★ 3Claude Code +9 - 0.579score
codebase-design
KenSuh
Shared vocabulary for designing deep modules.
SkillAFreshness: A★ 3Claude Code +9 - 0.579score
prototype
KenSuh
Build a throwaway prototype to answer a design question.
SkillAFreshness: A★ 3Claude Code +9 - 0.579score
domain-modeling
KenSuh
Build and sharpen a project's domain model.
SkillAFreshness: A★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 23, 2026 (5 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/KenSuh/open-agent-harness
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from KenSuh
- 0.606score
gpt-5-4-prompting
KenSuh
Internal guidance for composing Codex and GPT-5.4 prompts for coding, review, diagnosis, and research tasks inside the Codex Claude Code plugin
SkillAFreshness: A★ 3Claude Code +9 - 0.605score
humanize-korean
KenSuh
AI(ChatGPT·Claude·Gemini 등)가 쓴 한글 텍스트를 "사람이 쓴 글처럼" 윤문해주는 오케스트레이터 스킬.
SkillAFreshness: A★ 3Claude Code +9 - 0.604score
computer-use
KenSuh
Drives the GUI of a visible local app window through `orca computer`: accessibility tree, clicks, typing, menus, dialogs, and screenshots in native apps and…
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
humanize-scan
KenSuh
한글 글에 AI 티가 얼마나 있는지 재고, 실제로 고치면 어떻게 되는지 표본으로 보여주는 정찰 스킬.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
humanize-redo
KenSuh
가장 최근 윤문 결과를 2차로 다시 다듬는다 — 특정 카테고리·문단·강도 조정도 가능.
SkillAFreshness: A★ 3Claude Code +9 - 0.598score
codex-cli-runtime
KenSuh
Internal helper contract for calling the codex-companion runtime from Claude Code
SkillAFreshness: A★ 3Claude Code +9
Cite this page
humanize skill. Agent Mart. https://agentmart.dev/skills/kensuh-humanize (last updated 2026-10-24)