humanizer MCP — Anwendungsfälle, Installieren & Live-Demo

Warum nutzen

Hauptfunktionen

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

Live-Demo

In der Praxis

bereit

Installieren

Wählen Sie Ihren Client

~/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
    }
  }
}

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

VS Code → Cline → MCP Servers → Edit

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

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json

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

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json

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

In context_servers hinzufügen. Zed lädt beim Speichern neu.

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

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: 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

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

Voraussetzungen

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

Ablauf

Diagnose

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

→ Concrete tell inventory, not vibes
Rewrite conservatively

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

→ Minimal diff, voice preserved
Spot-check

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

→ Sampled read; flag anything that drifted

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

Fallstricke

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

Kombinieren mit: filesystem

Make technical docs sound written, not generated

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

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

Ablauf

Scan a batch

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

→ Doc-by-doc density report
Fix worst offenders

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

→ Diffs show removed fluff without losing substance

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

Fallstricke

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

Kombinieren mit: filesystem

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

humanizer-skill + filesystem

Bulk-humanize a folder of drafts

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

humanizer-skill + github

Humanize a PR's auto-generated description

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

Werkzeuge

Was dieses MCP bereitstellt

Werkzeug	Eingaben	Wann aufrufen
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

Kosten & Limits

Was der Betrieb kostet

API-Kontingent: N/A
Tokens pro Aufruf: Proportional to text length
Kosten in €: Free
Tipp: Diagnose first — cheap. Rewrite only what needs it.

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: None

Datenabfluss: None — skill is prompt-level

Fehlerbehebung

Häufige Fehler und Lösungen

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"

Alternativen

humanizer vs. andere

Alternative	Wann stattdessen	Kompromiss
Humanizer-zh	You're writing in Chinese	Chinese-tuned patterns
Manual editing	Short piece; faster to just edit	No systematic pattern catch

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen