/ ディレクトリ / プレイグラウンド / Avoid AI Writing
● コミュニティ conorbronsdon ⚡ 即起動

Avoid AI Writing

作者 conorbronsdon · conorbronsdon/avoid-ai-writing

Audit and rewrite content to remove AI-tell patterns (em-dashes, 'delve', etc.).

A skill that audits your draft against 21 known AI-writing tells — em-dashes everywhere, 'delve', 'in the realm of', 'it's important to note' — and rewrites to sound human. Use it as a post-pass on anything you ship.

なぜ使うのか

主な機能

ライブデモ

実際の動作

avoid-ai-writing-skill.replay ▶ 準備完了
0/0

インストール

クライアントを選択

~/Library/Application Support/Claude/claude_desktop_config.json  · Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "avoid-ai-writing-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/conorbronsdon/avoid-ai-writing",
        "~/.claude/skills/avoid-ai-writing"
      ],
      "_inferred": true
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config を開く。保存後、アプリを再起動。

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

Cursor は Claude Desktop と同じ mcpServers スキーマを使用。プロジェクト設定はグローバルより優先。

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

Cline サイドバーの MCP Servers アイコンをクリックし、"Edit Configuration" を選択。

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

Claude Desktop と同じ形式。Windsurf を再起動して反映。

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

Continue はマップではなくサーバーオブジェクトの配列を使用。

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

context_servers に追加。保存時に Zed がホットリロード。

claude mcp add avoid-ai-writing-skill -- git clone https://github.com/conorbronsdon/avoid-ai-writing ~/.claude/skills/avoid-ai-writing

ワンライナー。claude mcp list で確認、claude mcp remove で削除。

ユースケース

実用的な使い方: Avoid AI Writing

Strip AI tells from a blog post before publishing

👤 Anyone shipping AI-assisted writing ⏱ ~15 min intermediate

使うタイミング: Right before you hit publish.

前提条件
  • Server/skill installed and authenticated — See repo README
フロー
  1. Audit
    Run the avoid-ai-writing skill on /drafts/launch-post.md. Show me the offending phrases and counts.✓ コピーしました
    → Inline list of detections
  2. Rewrite
    Apply the rewrite in-place but show me a diff first.✓ コピーしました
    → Diff you can accept or reject hunk-by-hunk

結果: A post that doesn't make readers smell the model.

注意点
  • Don't run it on someone else's prose — Don't run it on someone else's prose — the rewrite changes voice. Use on your own drafts only.

コストと制限

運用コスト

APIクォータ
See provider docs for rate limits
呼び出しあたりのトークン
Varies by tool
金額
See repo README for pricing details
ヒント
Cache tool results and avoid repeated identical calls.

セキュリティ

権限、シークレット、影響範囲

認証情報の保管: Use environment variables; never commit secrets
データ送信先: Tool calls go to the provider's API as documented

トラブルシューティング

よくあるエラーと対処法

skill flags valid em-dashes

Tune the threshold in the skill's config — em-dash usage above 1 per 200 words is the default tell.

確認: Reduce density and re-run
rewrites change meaning

Use the diff mode and reject hunks that drift. The skill's confidence score helps prioritize.

確認: Compare original vs rewrite per paragraph

代替案

Avoid AI Writing 他との比較

代替案代わりに使う場面トレードオフ
Generic lintersYou want full style-guide enforcementVale is broader; this skill is AI-tell-specific

その他

リソース

📖 GitHub の公式 README を読む

🐙 オープンな issue を見る

🔍 400以上のMCPサーバーとSkillsを見る