humanizer MCP — 使用场景, 安装 & 实时演示

为什么要用

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

实时演示

实际使用效果

就绪

安装

选择你的客户端

~/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
    }
  }
}

打开 Claude Desktop → Settings → Developer → Edit Config。保存后重启应用。

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor 使用与 Claude Desktop 相同的 mcpServers 格式。项目级配置优先于全局。

VS Code → Cline → MCP Servers → Edit

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

点击 Cline 侧栏中的 MCP Servers 图标，然后选 "Edit Configuration"。

~/.codeium/windsurf/mcp_config.json

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

格式与 Claude Desktop 相同。重启 Windsurf 生效。

~/.continue/config.json

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

Continue 使用服务器对象数组，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 保存后热重载。

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 验证，claude mcp remove 卸载。

使用场景

实战用法： 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

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

前置条件

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

步骤

Diagnose

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

→ Concrete tell inventory, not vibes
Rewrite conservatively

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

→ Minimal diff, voice preserved
Spot-check

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

→ Sampled read; flag anything that drifted

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

注意事项

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

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

步骤

Scan a batch

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

→ Doc-by-doc density report
Fix worst offenders

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

→ Diffs show removed fluff without losing substance

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

注意事项

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

组合

与其他 MCP 搭配，撬动十倍杠杆

humanizer-skill + filesystem

Bulk-humanize a folder of drafts

Run humanizer on every .md under /blog/drafts.✓ 已复制

humanizer-skill + github

Humanize a PR's auto-generated description

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

工具

此 MCP 暴露的能力

工具	输入参数	何时调用
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

成本与限制

运行它的成本

API 配额: N/A
每次调用 Token 数: Proportional to text length
费用: Free
提示: Diagnose first — cheap. Rewrite only what needs it.

安全

权限、密钥、影响范围

凭据存储： None

数据出站： None — skill is prompt-level

故障排查

常见错误与修复

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 对比其他方案

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

humanizer

为什么要用

核心特性

实时演示

实际使用效果

安装

选择你的客户端

使用场景

实战用法： humanizer

Strip AI tells from a draft blog post before publishing

前置条件

步骤

注意事项

Make technical docs sound written, not generated

步骤

注意事项

组合

与其他 MCP 搭配，撬动十倍杠杆

工具

此 MCP 暴露的能力

成本与限制

运行它的成本

安全

权限、密钥、影响范围

故障排查

常见错误与修复

替代方案

humanizer 对比其他方案

更多

资源