humanizer MCP — 使用場景, 安裝 & 即時演示

為什麼要用

核心特性

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

即時演示

實際使用效果

就緒

安裝

選擇你的客戶端

~/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
    }
  }
}

開啟 Claude Desktop → Settings → Developer → Edit Config。儲存後重啟應用。

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor 使用與 Claude Desktop 相同的 mcpServers 格式。專案級設定優先於全域。

VS Code → Cline → MCP Servers → Edit

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

點擊 Cline 側欄中的 MCP Servers 圖示，然後選 "Edit Configuration"。

~/.codeium/windsurf/mcp_config.json

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

格式與 Claude Desktop 相同。重啟 Windsurf 生效。

~/.continue/config.json

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

Continue 使用伺服器物件陣列，而非映射。

~/.config/zed/settings.json

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

加入 context_servers。Zed 儲存後熱重載。

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

一行命令搞定。用 claude mcp list 驗證，claude mcp remove 移除。

使用場景

實戰用法： 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

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

前置條件

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

步驟

Diagnose

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

→ Concrete tell inventory, not vibes
Rewrite conservatively

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

→ Minimal diff, voice preserved
Spot-check

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

→ Sampled read; flag anything that drifted

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

注意事項

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

搭配使用： filesystem

Make technical docs sound written, not generated

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

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

步驟

Scan a batch

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

→ Doc-by-doc density report
Fix worst offenders

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

→ Diffs show removed fluff without losing substance

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

注意事項

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

搭配使用： filesystem

組合

與其他 MCP 搭配，撬動十倍槓桿

humanizer-skill + filesystem

Bulk-humanize a folder of drafts

Run humanizer on every .md under /blog/drafts.✓ 已複製

humanizer-skill + github

Humanize a PR's auto-generated description

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

工具

此 MCP 暴露的能力

工具	輸入參數	何時呼叫
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

成本與限制

運行它的成本

API 配額: N/A
每次呼叫 Token 數: Proportional to text length
費用: Free
提示: Diagnose first — cheap. Rewrite only what needs it.

安全

權限、密鑰、影響範圍

憑證儲存： None

資料出站： None — skill is prompt-level

故障排查

常見錯誤與修復

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"

替代方案

humanizer 對比其他方案

替代方案	何時用它替代	權衡
Humanizer-zh	You're writing in Chinese	Chinese-tuned patterns
Manual editing	Short piece; faster to just edit	No systematic pattern catch

humanizer

為什麼要用

核心特性

即時演示

實際使用效果

安裝

選擇你的客戶端

使用場景

實戰用法： humanizer

Strip AI tells from a draft blog post before publishing

前置條件

步驟

注意事項

Make technical docs sound written, not generated

步驟

注意事項

組合

與其他 MCP 搭配，撬動十倍槓桿

工具

此 MCP 暴露的能力

成本與限制

運行它的成本

安全

權限、密鑰、影響範圍

故障排查

常見錯誤與修復

替代方案

humanizer 對比其他方案

更多

資源