document-image-extractor
Document Image Extractor
从 Word 和 PDF 文档中提取图片的 skill。
依赖安装
使用前需要安装依赖（默认用户已安装）：
conda run -n claude-code pip install python-docx pymupdf
使用方法
基本命令
conda run -n claude-code python scripts/extract_images.py <文档路径> [-o <输出目录>]
More from mhliulgy/my-skills
alphaxiv-paper-lookup
Look up any arxiv paper on alphaxiv.org to get a structured AI-generated overview. This is faster and more reliable than trying to read a raw PDF.
36code-ocr
使用百度 OCR 高精度含位置版将代码截图转换为文本文件，保持原始缩进。使用场景包括：(1) 将代码截图识别为可编辑文本，(2) 从截图提取代码，(3) 图片转代码文字。触发条件：用户提到"截图转文字"、"OCR"、"识别代码"、"图片转文本"、"code screenshot to text
25docling-convert
Convert local files or URLs with a locally deployed Docling Gradio service into Markdown, JSON, HTML, text, or DocTags, with OCR and image export support. Use when handling `.docx`, `.pdf`, `.pptx`, `.xlsx`, `.html`, images, or web pages for document-to-Markdown conversion, batch conversion, image extraction, or Docling-based parsing through `http://localhost:5001`.
11remotion-best-practices
Best practices for Remotion - Video creation in React
2