humanizer MCP — 사용 사례, 설치 & 라이브 데모

왜 쓰나요

핵심 기능

Pattern library of AI writing tells
Rewrites in your existing style voice when provided
Works on markdown, plain text, and HTML
Can be conservative (minimal edits) or aggressive (full rewrite)
MIT licensed; easy to fork and extend patterns

라이브 데모

실제 사용 모습

준비됨

설치

클라이언트 선택

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "humanizer-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/blader/humanizer",
        "~/.claude/skills/humanizer"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config 열기. 저장 후 앱 재시작.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "humanizer-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/blader/humanizer",
        "~/.claude/skills/humanizer"
      ],
      "_inferred": true
    }
  }
}

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "humanizer-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/blader/humanizer",
        "~/.claude/skills/humanizer"
      ],
      "_inferred": true
    }
  }
}

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "humanizer-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/blader/humanizer",
        "~/.claude/skills/humanizer"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "humanizer-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/blader/humanizer",
        "~/.claude/skills/humanizer"
      ]
    }
  ]
}

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

{
  "context_servers": {
    "humanizer-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/blader/humanizer",
          "~/.claude/skills/humanizer"
        ]
      }
    }
  }
}

context_servers에 추가. 저장 시 Zed가 핫 리로드.

claude mcp add humanizer-skill -- git clone https://github.com/blader/humanizer ~/.claude/skills/humanizer

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: humanizer

Strip AI tells from a draft blog post before publishing

👤 Writers who use AI assistance but don't want to sound like everyone else ⏱ ~20 min beginner

언제 쓸까: You drafted a post with Claude, and it reads like every LinkedIn thought-leader post from 2025.

사전 조건

Skill installed — git clone https://github.com/blader/humanizer ~/.claude/skills/humanizer

흐름

Diagnose

Use humanizer. Analyze /drafts/post.md. List the AI tells — em-dashes, rule-of-three, hedged opener, generic adjectives — with counts.✓ 복사됨

→ Concrete tell inventory, not vibes
Rewrite conservatively

Rewrite paragraph by paragraph. Change only the AI tells. Keep my voice. Show diff.✓ 복사됨

→ Minimal diff, voice preserved
Spot-check

Read the revised version aloud (just the first 200 words). Does it still sound like me?✓ 복사됨

→ Sampled read; flag anything that drifted

결과: A post that doesn't trigger the AI-detection reflex in readers.

함정

Over-aggressive rewrite flattens your actual voice — Run conservatively first; only escalate sentence-by-sentence on problem areas

함께 쓰기: filesystem

Make technical docs sound written, not generated

👤 Teams auto-generating README/API docs ⏱ ~45 min intermediate

언제 쓸까: Your auto-generated docs all have "This comprehensive guide will navigate you through..." — and users hate it.

흐름

Scan a batch

Use humanizer on every .md under /docs. For each, report the tell density (tells per 100 words).✓ 복사됨

→ Doc-by-doc density report
Fix worst offenders

Rewrite the 5 with highest density. Stay technical — no vibes, just strip the filler.✓ 복사됨

→ Diffs show removed fluff without losing substance

결과: Docs that read like a human wrote them, which in technical writing means "read like they have something to say".

함정

Stripping hedging where it was actually a safety note — Review diffs — if a "note that..." was a real warning, keep it

함께 쓰기: filesystem

조합

다른 MCP와 조합해 10배 효율

humanizer-skill + filesystem

Bulk-humanize a folder of drafts

Run humanizer on every .md under /blog/drafts.✓ 복사됨

humanizer-skill + github

Humanize a PR's auto-generated description

Humanize the description of PR #2341 and push the update.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출
diagnose	text: str	Before rewriting, to see what's wrong
rewrite	text: str, intensity: conservative\|aggressive	Apply the fix
compare_voice	sample_a, sample_b	Check voice preservation after rewrite

비용 및 제한

운영 비용

API 쿼터: N/A
호출당 토큰: Proportional to text length
금액: Free
팁: Diagnose first — cheap. Rewrite only what needs it.

보안

권한, 시크릿, 파급범위

자격 증명 저장: None

데이터 외부 송신: None — skill is prompt-level

문제 해결

자주 발생하는 오류와 해결

Rewrite sounds just as AI as before

You're in conservative mode. Switch to aggressive, and provide 3–5 sample paragraphs of your actual voice as reference.

Skill not activating

Mention it explicitly: "use humanizer". Auto-activation depends on skill metadata.

Voice drifts after rewrite

Pin your voice with a sample: "rewrite to match this paragraph's voice"

대안

humanizer 다른 것과 비교

대안	언제 쓰나	단점/장점
Humanizer-zh	You're writing in Chinese	Chinese-tuned patterns
Manual editing	Short piece; faster to just edit	No systematic pattern catch

humanizer