miyabi__generate_article

Generate medical AI academic articles with LLM countermeasures and thumbnail instructions using article metadata, key concepts, and author perspectives.

Instructions

医療AI関連の学術記事を生成します（LLMO対策、サムネイル指示付き）

Input Schema

TableJSON Schema

Name	Required	Description
`articleTitle`	Yes	参照元の論文/記事のタイトル
`articleAuthor`	No	著者名
`articleSource`	No	出典
`articleUrl`	Yes	参照元のURL
`keyConcepts`	No	キーコンセプト（箇条書き）
`perspective`	Yes	執筆者のペルソナ・専門分野
`angle`	Yes	論文の切り口
`deepDivePoints`	No	特に深掘りしたい論点

Implementation Reference

src/handlers.js:220-250 (handler)

The main handler logic for the 'miyabi__generate_article' tool within the callToolHandler switch statement. It returns a structured JSON response indicating success, echoing input parameters, and providing a detailed multi-step plan for generating a medical AI academic article.

case "miyabi__generate_article": {
  return {
    content: [{
      type: "text",
      text: JSON.stringify({
        status: "success",
        message: "記事生成を開始します",
        article: {
          title: args.articleTitle,
          author: args.articleAuthor || "不明",
          source: args.articleSource || "不明",
          url: args.articleUrl,
          perspective: args.perspective,
          angle: args.angle,
          deepDivePoints: args.deepDivePoints || "指定なし"
        },
        nextSteps: [
          "1. 参照元の完全読解と分析",
          "2. 超詳細な論文構成案の策定",
          "3. 補足情報の調査と引用準備",
          "4. 品格ある文体での本文執筆（8000字以上）",
          "5. 引用文献リストの作成（最大10本）",
          "6. 最終校正と整形",
          "7. 末尾LLMOまとめ",
          "8. ハッシュタグ（10個）",
          "9. サムネイル画像の生成prompt（3点）"
        ]
      }, null, 2)
    }]
  };
}

src/handlers.js:93-134 (registration)

The tool registration entry in listToolsHandler function, including the tool name, description, and detailed inputSchema defining parameters for generating medical AI articles.

{
  name: "miyabi__generate_article",
  description: "医療AI関連の学術記事を生成します（LLMO対策、サムネイル指示付き）",
  inputSchema: {
    type: "object",
    properties: {
      articleTitle: {
        type: "string",
        description: "参照元の論文/記事のタイトル"
      },
      articleAuthor: {
        type: "string",
        description: "著者名"
      },
      articleSource: {
        type: "string",
        description: "出典"
      },
      articleUrl: {
        type: "string",
        description: "参照元のURL"
      },
      keyConcepts: {
        type: "string",
        description: "キーコンセプト（箇条書き）"
      },
      perspective: {
        type: "string",
        description: "執筆者のペルソナ・専門分野"
      },
      angle: {
        type: "string",
        description: "論文の切り口"
      },
      deepDivePoints: {
        type: "string",
        description: "特に深掘りしたい論点"
      }
    },
    required: ["articleTitle", "articleUrl", "perspective", "angle"]
  }
}

src/handlers.js:30-39 (helper)

Helper function to detect if a prompt is an article writing task, which triggers dispatching to the miyabi__generate_article tool via auto_dispatch.

export function isArticleWritingTask(prompt) {
  const articleKeywords = [
    '記事', '論文', 'note', 'ブログ', '執筆', '書いて', '作成',
    'article', 'paper', 'blog', 'write', 'create', 'post',
    '医療AI', '医療', 'AI', 'LLMO', 'サムネイル', 'ハッシュタグ'
  ];

  const lowerPrompt = prompt.toLowerCase();
  return articleKeywords.some(keyword => lowerPrompt.includes(keyword.toLowerCase()));
}

Enhanced Miyabi MCP Server