
Docx Reader
Pulls text and tables out of .docx files using python-docx, which is handy when you need to process Word documents without opening Microsoft Office. It runs via WSL and handles path conversion from Windows to WSL format automatically. The extracted content comes out plain, so you lose all formatting, images, and embedded objects. Works well for turning reports or documents into markdown or feeding their content into other tools. Main gotcha is making sure python-docx is installed correctly, since there's a naming conflict with an older package called docx that'll break things if you grab the wrong one.
- skills.sh installs
- 309
- last updated
- Aug 21, 2026
Install
$ npx -y skills add childbamboo/claude-code-marketplace-sample --skill docx-reader --agent claude-codeInstalls into .claude/skills of the current project.
Files
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
- スクリプトでテキスト抽出
- 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
- ユーザーが .docx ファイルパスを指定
- Windows パスを WSL パス形式に変換 (
C:\→/mnt/c/) wsl python3 scripts/read_docx.pyを実行- 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
- Glob で .docx ファイルを検索
- 各ファイルに対してスクリプトを実行
- 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
Sponsors
Details
- Repository
- github.com/childbamboo/claude-code-marketplace-sample
- Categories
- Python, Office & Documents
- First seen
- Jun 3, 2026