Converts PDF pages to images and uses vision analysis to extract content including diagrams, charts, and visual elements. Use for PDFs with rich visual content. Requires pdf2image and poppler-utils.
/plugin marketplace add childbamboo/claude-code-marketplace-sample/plugin install general@claude-code-marketplace-sampleThis skill inherits all available tools. When active, it can use any tool Claude has access to.
README.mdscripts/pdf_to_images.py図表が多い PDF を画像化して、Claude の vision 機能で内容を解析・Markdown 化するスキルです。
# 1. PDF を画像に変換
wsl python3 scripts/pdf_to_images.py "/mnt/c/path/to/file.pdf"
# 2. 各画像を Read ツールで読み込んで解析
# 3. Markdown 形式でまとめる
必要なパッケージ:
# Python パッケージ
wsl pip3 install pdf2image Pillow
# システムパッケージ (poppler)
wsl sudo apt-get update
wsl sudo apt-get install -y poppler-utils
wsl python3 scripts/pdf_to_images.py "/mnt/c/path/to/document.pdf"
これにより document_pages/ ディレクトリが作成され、各ページが画像として保存されます:
page_001.pngpage_002.pngpage_003.pngRead ツールで各画像を順番に読み込み、内容を解析します。
解析時の指示例:
この画像の内容を詳しく説明してください:
- タイトルや見出し
- 本文テキスト
- 図表の説明
- グラフやチャートのデータ
- 重要なポイント
各ページの解析結果を統合して、一つの Markdown ファイルを作成します。
User: "presentation.pdf を vision で解析して Markdown 化して"
Assistant:
1. scripts/pdf_to_images.py で PDF を画像に変換
2. 各画像を Read ツールで読み込み
3. 各ページの内容を解析(タイトル、図表、テキスト)
4. 全ページの解析結果を統合
5. Write ツールで Markdown ファイルに保存
User: "document.pdf の 5-10 ページだけ解析して"
Assistant:
1. PDF を画像に変換(全ページ)
2. page_005.png から page_010.png のみ Read で読み込み
3. 該当ページの内容を Markdown 化
各ページの画像から以下を抽出:
テキスト情報
図表
グラフ・チャート
テーブル
レイアウト・構造
# [PDFタイトル]
**解析日時:** YYYY-MM-DD
**総ページ数:** N
---
## Page 1: [ページタイトル]
### 概要
[ページの概要説明]
### 主要な内容
- [ポイント1]
- [ポイント2]
### 図表
**図1: [図のタイトル]**
[図の説明]
### テキスト内容
[ページ内のテキスト]
---
## Page 2: [ページタイトル]
...
機能:
使い方:
python scripts/pdf_to_images.py <pdf_path> [output_dir] [dpi]
# 例
python scripts/pdf_to_images.py document.pdf ./images 300
出力:
[pdf_name]_pages/page_001.png[pdf_name]_pages/page_002.png| PDF の種類 | 推奨スキル |
|---|---|
| テキスト中心の文書 | pdf-reader |
| プレゼンテーション資料 | pdf-vision-reader |
| 図表・グラフが多い資料 | pdf-vision-reader |
| 技術図面・設計書 | pdf-vision-reader |
| 論文(図表含む) | pdf-vision-reader |
| 単純なテキストPDF | pdf-reader |
wsl pip3 install pdf2image
wsl sudo apt-get update
wsl sudo apt-get install -y poppler-utils
python scripts/pdf_to_images.py document.pdf ./images 300
| ページ数 | 画像変換 | 解析(Claude vision) | 合計 |
|---|---|---|---|
| 10ページ | 5秒 | 30-60秒 | ~1分 |
| 30ページ | 15秒 | 90-180秒 | ~3分 |
| 100ページ | 50秒 | 300-600秒 | ~10分 |
必要なページのみ処理
DPI の調整
バッチ処理
Windows パスから WSL パスへの変換:
C:\Users\... → /mnt/c/Users/...D:\Projects\... → /mnt/d/Projects/...Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.