Pdf Field Extractor：用 Agent 把 PDF 关键字段抽成 Excel 或 JSON
Pdf Field Extractor 是 SkillHub 社区办公效率类 Skill（v1.0.2），由 user_26bdbd50 发布。它将 PDF 文本/表格解析、扫描件 OCR、文档类型识别、OpenAI 兼容大模型字段抽取与 Excel/JSON 输出串成端到端流程，支持发票、合同、收据等类型及批量处理。安装可通过 skillhub install 指向 Cursor 等 skills 目录；需用户自配 API Key 与 Python/Tesseract 依赖。本文基于官方页面与 Skill 包内文档整理安装步骤与典型用法。
Read More本地文件解析专家：用 LiteParse 在本地提取 PDF 与 Office 文档
SkillHub Skill「本地文件解析专家」基于开源 LiteParse，在本地解析 PDF、Word、PPT、Excel 与图片，支持纯文本、带坐标的 JSON、页面截图与目录批量处理，无需联网与文档云 API 费用。文章说明 Skill 定位、核心能力、skillhub install 安装方式、install.sh 与 pip 依赖，以及 lit parse、batch-parse、screenshot 等典型命令与 Python 调用，并列出 LibreOffice、OCR 与加密 PDF 等注意事项。
Read MorePDF and Image Text Extraction: Extracting Text and Tables from Images and PDFs in an Agent
This article introduces the SkillHub Skill “PDF and Image Text Extraction” (@user_5f9c21aa/pdf-image-text-extractor, v1.0.13). It supports text recognition from multiple image formats and PDFs, AI visual OCR for scanned documents, table extraction using PyMuPDF, and batch processing of directories; the v2.1 solution does not require tesseract or pdfplumber. It explains the `skillhub` installation command, the Cursor skills directory, and `requires_api_key` considerations, with capabilities provided by RedFoxHub.
Read Moredsh-pdf-reader: A Local PDF Text Extraction Plugin
This is a DeepSeek Harness plugin named `dsh-pdf-reader`, designed to address privacy concerns when reading local documents. The tool parses PDFs locally using `pdfjs-dist`, without network requests or file uploads. It supports specifying a path, page count, and character limits, and provides page-by-page text extraction. Once installed, the Agent can directly invoke the `read_pdf` tool within the workspace. The plugin strictly adheres to path isolation security principles, supports only PDFs with a text layer, and requires the DeepSeek Harness Web Profile to run.
Read More