/ Directorio / Playground / humanizer
● Comunidad blader ⚡ Instantáneo

humanizer

por blader · blader/humanizer

Rewrite AI-generated prose to lose the em-dashes, tricolons, and hedged claims that scream "ChatGPT wrote this".

Humanizer is a Claude Code skill that identifies and removes the telltale markers of AI writing: aggressive em-dash use, rule-of-three cadence, unnecessary hedging ("It's important to note"), and generic emphatic adjectives ("delve", "navigate", "robust"). Works on your drafts before you ship.

Por qué usarlo

Características clave

Demo en vivo

Cómo se ve en la práctica

listo

Instalar

Elige tu cliente

~/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
    }
  }
}

Abre Claude Desktop → Settings → Developer → Edit Config. Reinicia después de guardar.

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

Cursor usa el mismo esquema mcpServers que Claude Desktop. La configuración del proyecto prevalece sobre la global.

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "humanizer-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/blader/humanizer",
        "~/.claude/skills/humanizer"
      ],
      "_inferred": true
    }
  }
}

Haz clic en el icono MCP Servers de la barra lateral de Cline y luego en "Edit Configuration".

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

Mismo formato que Claude Desktop. Reinicia Windsurf para aplicar.

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

Continue usa un array de objetos de servidor en lugar de un mapa.

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

Añádelo a context_servers. Zed recarga en caliente al guardar.

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

Un solo comando. Verifica con claude mcp list. Quita con claude mcp remove.

Casos de uso

Usos del mundo real: 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

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

Requisitos previos
  • Skill installed — git clone https://github.com/blader/humanizer ~/.claude/skills/humanizer
Flujo
  1. Diagnose
    Use humanizer. Analyze /drafts/post.md. List the AI tells — em-dashes, rule-of-three, hedged opener, generic adjectives — with counts.✓ Copiado
    → Concrete tell inventory, not vibes
  2. Rewrite conservatively
    Rewrite paragraph by paragraph. Change only the AI tells. Keep my voice. Show diff.✓ Copiado
    → Minimal diff, voice preserved
  3. Spot-check
    Read the revised version aloud (just the first 200 words). Does it still sound like me?✓ Copiado
    → Sampled read; flag anything that drifted

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

Errores comunes
  • Over-aggressive rewrite flattens your actual voice — Run conservatively first; only escalate sentence-by-sentence on problem areas
Combinar con: filesystem

Make technical docs sound written, not generated

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

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

Flujo
  1. Scan a batch
    Use humanizer on every .md under /docs. For each, report the tell density (tells per 100 words).✓ Copiado
    → Doc-by-doc density report
  2. Fix worst offenders
    Rewrite the 5 with highest density. Stay technical — no vibes, just strip the filler.✓ Copiado
    → Diffs show removed fluff without losing substance

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

Errores comunes
  • Stripping hedging where it was actually a safety note — Review diffs — if a "note that..." was a real warning, keep it
Combinar con: filesystem

Combinaciones

Combínalo con otros MCPs para multiplicar por 10

humanizer-skill + filesystem

Bulk-humanize a folder of drafts

Run humanizer on every .md under /blog/drafts.✓ Copiado
humanizer-skill + github

Humanize a PR's auto-generated description

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

Herramientas

Lo que expone este MCP

HerramientaEntradasCuándo llamarCoste
diagnose text: str Before rewriting, to see what's wrong 0
rewrite text: str, intensity: conservative|aggressive Apply the fix 0
compare_voice sample_a, sample_b Check voice preservation after rewrite 0

Coste y límites

Lo que cuesta ejecutarlo

Cuota de API
N/A
Tokens por llamada
Proportional to text length
Monetario
Free
Consejo
Diagnose first — cheap. Rewrite only what needs it.

Seguridad

Permisos, secretos, alcance

Almacenamiento de credenciales: None
Salida de datos: None — skill is prompt-level

Resolución de problemas

Errores comunes y soluciones

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"

Alternativas

humanizer vs otros

AlternativaCuándo usarlaContrapartida
Humanizer-zhYou're writing in ChineseChinese-tuned patterns
Manual editingShort piece; faster to just editNo systematic pattern catch

Más

Recursos

📖 Lee el README oficial en GitHub

🐙 Ver issues abiertas

🔍 Ver todos los 400+ servidores MCP y Skills