/ Annuaire / Playground / humanizer
● Communauté blader ⚡ Instantané

humanizer

par 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.

Pourquoi l'utiliser

Fonctionnalités clés

Démo en direct

Aperçu en pratique

prêt

Installer

Choisissez votre 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
    }
  }
}

Ouvrez Claude Desktop → Settings → Developer → Edit Config. Redémarrez après avoir enregistré.

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

Cursor utilise le même schéma mcpServers que Claude Desktop. La config projet l'emporte sur la globale.

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

Cliquez sur l'icône MCP Servers dans la barre latérale Cline, puis "Edit Configuration".

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

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

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

Continue utilise un tableau d'objets serveur plutôt qu'une map.

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

Ajoutez dans context_servers. Zed recharge à chaud à la sauvegarde.

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

Une seule ligne. Vérifiez avec claude mcp list. Supprimez avec claude mcp remove.

Cas d'usage

Usages concrets : 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

Quand l'utiliser : You drafted a post with Claude, and it reads like every LinkedIn thought-leader post from 2025.

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

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

Pièges
  • Over-aggressive rewrite flattens your actual voice — Run conservatively first; only escalate sentence-by-sentence on problem areas
Combiner avec : filesystem

Make technical docs sound written, not generated

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

Quand l'utiliser : Your auto-generated docs all have "This comprehensive guide will navigate you through..." — and users hate it.

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

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

Pièges
  • Stripping hedging where it was actually a safety note — Review diffs — if a "note that..." was a real warning, keep it
Combiner avec : filesystem

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

humanizer-skill + filesystem

Bulk-humanize a folder of drafts

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

Humanize a PR's auto-generated description

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

Outils

Ce que ce MCP expose

OutilEntréesQuand appelerCoût
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

Coût et limites

Coût d'exécution

Quota d'API
N/A
Tokens par appel
Proportional to text length
Monétaire
Free
Astuce
Diagnose first — cheap. Rewrite only what needs it.

Sécurité

Permissions, secrets, portée

Stockage des identifiants : None
Sortie de données : None — skill is prompt-level

Dépannage

Erreurs courantes et correctifs

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"

Alternatives

humanizer vs autres

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

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills