docx-reader

childbamboo's avatarfrom childbamboo

Reads Microsoft Word (.docx) files and extracts text content. Use when needing to read .docx documents. Requires python-docx package.

0stars🔀0forks📁View on GitHub🕐Updated Jan 8, 2026

When & Why to Use This Skill

This Claude skill provides a robust solution for programmatically reading and extracting text and table data from Microsoft Word (.docx) files. By integrating the python-docx library, it allows Claude to access local document content, facilitating automated data retrieval, content analysis, and format conversion within a WSL (Windows Subsystem for Linux) environment.

Use Cases

  • Case 1: Extracting text from specific local .docx files to generate summaries, identify key points, or answer questions based on the document's content.
  • Case 2: Automating the conversion of Word documents into Markdown format for better integration with developer documentation and version control systems.
  • Case 3: Batch processing multiple Word documents to aggregate information, perform data cleaning, or migrate legacy documentation into structured knowledge bases.
namedocx-reader
descriptionReads Microsoft Word (.docx) files and extracts text content. Use when needing to read .docx documents. Requires python-docx package.

DOCX Reader

Microsoft Word (.docx) ファイルをテキスト形式で読み込むスキルです。

クイックスタート

基本的な使い方

# WSL環境でPythonスクリプトを実行
wsl python3 scripts/read_docx.py "/mnt/c/path/to/file.docx"

Markdown形式で保存

  1. スクリプトでテキスト抽出
  2. Write ツールで .md ファイルに保存

前提条件

python-docx パッケージが必要です:

wsl pip3 install python-docx

使用例

例1: .docx ファイルを読み込んで内容を表示

User: "C:\Users\keita\repos\file.docx を読み込んで"
Assistant:
1. Windowsパスを WSL パスに変換: /mnt/c/Users/keita/repos/file.docx
2. wsl python3 scripts/read_docx.py を実行
3. 抽出されたテキストを表示

例2: .docx を Markdown に変換して保存

User: "申請書.docx を Markdown に変換して保存"
Assistant:
1. scripts/read_docx.py でテキスト抽出
2. Markdown形式で整形
3. Write ツールで 申請書.md に保存
4. 保存完了を報告

ワークフロー

単一ファイルの読み込み

  1. ユーザーが .docx ファイルパスを指定
  2. Windows パスを WSL パス形式に変換 (C:\/mnt/c/)
  3. wsl python3 scripts/read_docx.py を実行
  4. 抽出されたテキストを表示または保存

複数ファイルの一括処理

  1. Glob で .docx ファイルを検索
  2. 各ファイルに対してスクリプトを実行
  3. 結果をまとめて報告

スクリプト詳細

Python スクリプトは scripts/read_docx.py に配置されています。

主な機能:

  • 段落テキストの抽出
  • テーブルデータの抽出
  • エラーハンドリング

使い方:

python scripts/read_docx.py <file_path>

制限事項

  • 画像は抽出されません
  • 複雑なレイアウトは簡略化されます
  • フォント情報、色などのスタイルは失われます
  • 埋め込みオブジェクトは抽出されません

トラブルシューティング

python-docx がインストールされていない

wsl pip3 install python-docx

"No module named 'docx'" エラー

wsl pip3 uninstall docx
wsl pip3 install python-docx

ファイルが開けない

  • ファイルパスが正しいか確認(Windows → WSL パス変換)
  • ファイルが他のプログラムで開かれていないか確認
  • ファイルのアクセス権限を確認

パス変換

Windows パスから WSL パスへの変換:

  • C:\Users\.../mnt/c/Users/...
  • D:\Projects\.../mnt/d/Projects/...
  • バックスラッシュ \ をスラッシュ / に変換

関連ツール

  • pandoc: より高度な変換が必要な場合
  • python-docx2txt: 軽量な代替ライブラリ
  • mammoth: HTML形式での変換

バージョン履歴

  • v1.0.0 (2026-01-06): 初期リリース
    • 基本的なテキスト抽出機能
    • テーブル抽出対応
    • WSL環境での動作
docx-reader – AI Agent Skills | Claude Skills