pdf-vision-reader

PDF Vision Reader

This skill converts image-heavy PDFs into images and analyzes their content using Claude's vision capability, converting it into Markdown.

Quick Start

Basic Usage

# 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

Prerequisites

Required packages:

# 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

Workflow

Step 1: Convert PDF to images

wsl python3 scripts/pdf_to_images.py "/mnt/c/path/to/document.pdf"

This allows document_pages/ A directory is created, and each page is saved as an image:

page_001.png
page_002.png
page_003.png
...

Step 2: Analyze each image

Read each image in order using the Read tool and analyze its content.

Example instruction during analysis:

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

Step 3: Integrate into Markdown

Integrate the analysis results for each page to create a single Markdown file.

Usage Examples

Example 1: Convert presentation materials to Markdown

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

Example 2: Analyze only specific pages

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

Analysis Perspectives

Information to be automatically extracted

Extract the following from the image of each page:

Text Information
- Title・Headings
- Body text
- Bulleted lists
- Notes・Captions
Figures and Tables
- Type of diagram (flowchart, organizational chart, etc.)
- Description・Summary of the diagram
- Main elements and relationships
Graphs & Charts
- Type of graph (bar graph, pie chart, etc.)
- Axis labels
- Main data points
- Trends and tendencies
Tables
- Table structure
- Header row
- Data content
- Convert to Markdown table format
Layout・Structure
- Overall page layout
- Section division
- Emphasized information

Markdown Output Format

# [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]
...

Script Details

pdf_to_images.py

Features:

Convert each page of the PDF to a PNG image
Resolution can be specified (default: 200 DPI)
Automatic creation of the output directory

Usage:

python scripts/pdf_to_images.py <pdf_path> [output_dir] [dpi]

# 例
python scripts/pdf_to_images.py document.pdf ./images 300

Output:

[pdf_name]_pages/page_001.png
[pdf_name]_pages/page_002.png
...

Supported Content

✅ Text (Japanese・English)
✅ Figures and tables・Diagrams
✅ Graphs & Charts
✅ Tables
✅ Screenshots
✅ Infographics
✅ Complex layouts
⚠️ Handwritten notes (accuracy depends on the situation)
⚠️ Low-resolution images (accuracy may decrease)

Differences from Text Extraction

pdf-reader (text extraction)

✅ Fast for text-only PDFs
✅ Pure text extraction
❌ Figures and tables cannot be extracted
❌ Layout is simplified