document-conversion

Harryoung's avatarfrom Harryoung

将 DOC/DOCX/PDF/PPT/PPTX 文档转换为 Markdown 格式。自动检测 PDF 类型（电子版/扫描版），提取图片到独立目录。当管理员入库非 Markdown 文档时使用此 Skill。触发条件：入库 DOC/DOCX/PDF/PPT/PPTX 格式文件。

⭐9stars🔀1forks📁View on GitHub🕐Updated Dec 22, 2025
[Document Processing]

When & Why to Use This Skill

This Claude skill automates the conversion of multi-format documents—including DOCX, PDF, and PPTX—into high-quality Markdown. It features intelligent PDF detection to switch between fast extraction and OCR for scanned files, while automatically managing image extraction to ensure seamless integration into AI-ready knowledge bases and RAG workflows.

Use Cases

  • Knowledge Base Onboarding: Efficiently migrate legacy corporate documents (Word, PDF, PPT) into Markdown format for centralized AI knowledge management.
  • Automated OCR Processing: Automatically detect scanned PDF documents and apply PaddleOCR to extract text and images into structured digital formats.
  • Content Repurposing: Convert presentation slides (PPTX) into structured Markdown text and separate image assets for technical documentation or blog posts.
  • Data Preparation for LLMs: Clean and format unstructured documents into standardized Markdown to improve the accuracy of retrieval-augmented generation (RAG) systems.
namedocument-conversion
descriptionConvert DOC/DOCX/PDF/PPT/PPTX documents to Markdown format. Automatically detect PDF type (electronic/scanned), extract images to separate directory. Use this Skill when administrator onboards non-Markdown documents. Trigger condition: Onboard DOC/DOCX/PDF/PPT/PPTX format files.

Document Format Conversion

Convert various document formats to Markdown for knowledge base onboarding.

Supported Formats

Format Processing Method
DOCX Pandoc conversion, preserve formatting and images
DOC LibreOffice → DOCX → Pandoc
PDF Electronic PyMuPDF4LLM fast conversion
PDF Scanned PaddleOCR-VL online OCR
PPTX pptx2md professional conversion
PPT LibreOffice → PPTX → pptx2md

Usage

python .claude/skills/document-conversion/scripts/smart_convert.py \
    <temp_path> \
    --original-name "<original_filename>" \
    --json-output

Parameters:

  • <temp_path>: Temporary file path (e.g. /tmp/kb_upload_xxx.pptx)
  • --original-name: Must pass original filename, used to generate correct image directory name
  • --json-output: Output JSON format result

Output Format

{
  "success": true,
  "markdown_file": "/path/to/output.md",
  "images_dir": "original_filename_images",
  "image_count": 5,
  "input_file": "/path/to/input.pptx"
}

Processing Flow

  1. Execute conversion command (must use --original-name and --json-output)
  2. Parse JSON output, check success field
  3. If success: false, report error and end
  4. If success: true, record generated file path and image directory

Important Notes

  • Image directory uses original filename naming (e.g. 培训资料_images/)
  • Not passing --original-name will cause incorrect image reference paths
  • PDF type is automatically detected, scanned version processing is slower (tens of seconds to minutes)

Format Details

Detailed processing instructions for each format, see FORMATS.md