resume-analyer：在 Agent 对话里完成简历解析与多维度评估
resume-analyer（@user_281d357b/resume-analyer，v1.0.0）是 SkillHub 社区 data-analysis 类 Skill，在对话中解析 PDF/DOCX/DOC/TXT/MD 简历，按内容完整性、结构、技能匹配、表达与项目经验等维度给出 0–100 分评估及改进建议，无需自建后端。本文基于官方 SKILL.md 与 SkillHub 安装文档，说明安装命令、Cursor 等客户端 skills 目录及典型触发话术，并提醒 API 依赖、扫描 PDF 与文件大小等限制。
Read MoreTextIn xParse Document Parse：用 xparse-cli 把文档转成 Agent 可读内容
介绍 SkillHub 社区 Skill「TextIn xParse Document Parse」（@user_2e25d6a2/xparse-parser，v1.0.4）。它以 xparse-cli 为内核，指导 Agent 解析 PDF、图片、Office、HTML、OFD 等本地文件或 URL，输出 Markdown 或 JSON，并支持 get_doc_info 导航、搜索抽取及多文档 Task Runtime。文章说明 SkillHub 与 npm 安装方式、--api auto/free/paid 路由、典型 parse 与 task 命令，以及免费格式范围与付费确认等注意点。
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 MoreDeepSeek Harness Plugin: dsh-evidence (Enabling Models to Actually Read Files)
dsh-evidence is a local file parsing plugin for DeepSeek Harness. It parses and indexes files locally to transform them into structured, versioned evidence, rather than feeding them directly into context. The plugin supports multiple formats and provides two tools, `search_documents` and `read_document`, enabling models to retrieve content precisely. Installation requires Node.js 22.13.0+ and Harness 0.1.7+, and it is currently in beta.
Read MoreTextIn xParse Plugin
`intsig-textin/dsh-plugin-xparse` is a document parsing plugin for DeepSeek Harness. Installation requires specific environmental prerequisites, and once installed, it offers multiple document parsing and task management features. The plugin configures AppKey and OAuth through browser cards and supports device login. Parsing results are written to the workspace as artifacts, while task operations return Task/Run identifiers. Users should note the paid licensing mechanism and credential security, and all file operations are managed by the sandbox.
Read Moredsh-docs: Local Document Parsing and OCR Plugin
dsh-docs is a localized document processing plugin designed specifically for DeepSeek Harness, enabling offline OCR recognition and text extraction without internet access. It supports reading multiple formats, including PDFs, Office documents, and images, and can convert content into Markdown or plain text. The plugin also provides full-text search and batch processing capabilities. Running on Windows, it emphasizes data privacy and security, making it suitable for offline environments or for handling sensitive documents.
Read Moredsh-ds-attach: DeepSeek Harness Attachment Upload and Document Text Injection Plugin
dsh-ds-attach is an MIT-licensed DeepSeek Harness plugin (v0.1.0, depends on @deepseek-ai/cordis ^4.0.1) maintained by wqx-txdsyl, aiming to replicate the attachment experience of chat.deepseek.com for the DSH web client. Core features include: uploading files via the paperclip button or drag-and-drop; displaying 240x64px file cards with official icons and status (uploading/parsing/completed/failed); supporting text extraction for PDF, DOCX, XLSX, TXT/MD, and code files (default 150,000 character budget, truncation at paragraph boundaries); injecting extracted text into messages for the model to read; and automatically clearing the attachment area after sending. Images automatically go through the native vision pipeline, scanned P.
Read Moredsh-doc: DeepSeek Harness Full-Local Document Parsing and Offline OCR
dsh-doc is an MIT-licensed plugin for DeepSeek Harness released by Sqhao-O. It locally parses PDFs, Office documents, images, and scanned files, outputting Markdown, plain text, or JSON without requiring Docker, HTTP services, or API keys. On Windows x64, it can mount pre-built Python + Xberg runtimes and offline Tesseract (for Chinese and English); other platforms fall back to the Node engine. The installation command is `dsh plugin --profile web add dsh-doc`. After configuring the engine via `cordis.patch.yml`, it can be used through `dshdoc_health` and `dshdoc_extract`.
Read MoreUse dsh-docs to let DeepSeek Harness parse PDFs, Office documents and scanned files locally
dsh-docs is a fully local documentation plugin for DeepSeek Harness maintained by Sqhao-O. It can parse PDF, Office documents, images and scanned documents within authorized directories. For Windows x64 systems, it uses offline Python/Tesseract OCR with fixed hash verification, while other platforms fall back to Node Xberg. The directory installation command is `dsh plugin add github:Sqhao-O/dsh-docs`, and the npm package `dsh-doc` is recommended for web scenarios.
Read MoreConnect MinerU Document Parsing to DeepSeek Harness with dsh-plugin-mineru
# dsh-plugin-mineru, maintained by HuanLinOTO, integrates MinerU FastAPI with DeepSeek Harness: it can convert PDF, images, DOCX, PPTX and XLSX files to Markdown/JSON. This article covers the catalog page, verification of installation commands via GitHub and npm, five tools, baseURL configuration, and important notes such as the requirement to build MinerU locally and not use the default port 18000.
Read More