OCR 文档识别转 Markdown（WiseOCR）
WiseOCR 是一个基于 WiseDiag 云 API 的 Skill，可将 PDF 和图片转换为高质量 Markdown 文本，支持表格识别、多栏版式还原、中英文混排。适用于扫描件文字提取、纸质文档数字化、合同报告论文转文本等场景。
Read More翔云 OCR 表格识别 文字识别-Pro：在 Agent 里做文档与表格 OCR
介绍 SkillHub 社区 Skill「翔云 OCR 表格识别 文字识别-Pro」（@user_6b190ef3/xiangyun-table-ocr，v1.0.10）。说明其作为翔云通用文档/表格识别 Agent 的定位，涵盖文字与 PDF OCR、表格提取、转 Excel/Word/Markdown、批量识别、多语言及倾斜校正等官方列出的能力；标注 requires_api_key=true。给出 skillhub install 与 AI 安装提示两种启用方式，以及基于官方触发语义的对话示例与使用注意。
Read Moredsh-baidu-ocr: DeepSeek Harness Baidu Cloud OCR Bundle
This plugin integrates Baidu Cloud OCR capabilities into the DeepSeek Harness Web interface by collaborating between Host and Client. It supports dual engines—PaddleOCR-VL and Unlimited-OCR—and provides two usage modes: GUI drag-and-drop and command invocation. It can recognize images, PDFs, and office documents into Markdown and save them to the local `ocr_output` directory. Installation requires running specified commands in the terminal, and a Baidu API Key must be configured before use. With zero dependencies and built-in CSRF protection, it is suitable for scenarios requiring batch document processing.
Read MoreDeepSeek Harness PaddleOCR Plugin
The DeepSeek Harness (DSH) plugin `qiuchunhuimax/dsh-plugin` provides local document recognition capabilities using PaddleOCR 3.x. It can be invoked via the `/ocr` command or Agent tools, supports formats such as PDFs and images, automatically generates Markdown files from the results, and stores them in the workspace. Installation requires Python 3 and PaddleOCR 3.x, with an environment variable available to specify the Python path. Built on the official DSH interface, the plugin is well suited for local document processing within workflows.
Read More