pdf 37

AI deep-reading assistant for DeepSeek Harness and dsh-TUI: extract traceable claims, evidence, confidence levels, knowledge maps, and review questions from articles, books, PDFs, files, URLs, or pasted text.

Local PDF, Office, image, and OCR document intelligence for DeepSeek Harness.

DeepSeek Harness 插件：论文伴读工作台 — PDF 转录 / 检索 / 原生对话伴读 + 内置阅读器页面。

DeepSeek Harness PDF production skill: reports, creative visuals, LaTeX, and existing-PDF processing, with bundled LibreOffice conversion.

PDF toolbox for DeepSeek Harness: extract text, metadata, and page ranges from PDF files (local parsing, no API key).

A general-purpose knowledge base plugin for DeepSeek Harness (DSH): import documents (md/txt/json/yml/docx/pdf), organize them in folders, and search with FTS5. 通用知识库插件：文件导入、目录化管理、全文检索、知识库管理 UI。

dsh-mineru: MinerU 文档解析插件 for DeepSeek Harness — 多模态全格式 (PDF/Word/PPT/Excel/HTML/图片) → 结构化 Markdown. 填 Token 走精准解析 API, 留空走 Agent 轻量解析 API.

DSH PDF 解析插件: 为 agent 提供 pdf_info / pdf_extract_text / pdf_render_page 三个工具。基于 pdfjs-dist + @napi-rs/canvas; 对未内嵌字体的 PDF (如嘉立创EDA导出) 自动改用系统字体渲染文字。热插拔 — 通过 cordis.patch.yml + profile node_modules 软链接挂载, 无需改动 dsh 源码。

KolmoPDF tools for DeepSeek Harness with durable API-key settings and CLI configuration.

火山方舟 Coding Plan LLM provider for DeepSeek Harness — provider-scoped PDF、图片与 Responses API 流式支持

PDF 去底灰技能（remove-pdf-background-gray）的 DSH 插件化分发：去除扫描 PDF 的灰色/米白底色，保持原始分辨率、页面几何与抗锯齿文字边缘；核心为单文件 Python 脚本（pypdf + Pillow + numpy），无损 Flate 压缩。

DeepSeek Harness bundle: the read_document tool reads Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF files as Markdown for the model

DeepSeek Harness plugin: ingest research PDFs into a citable OKF markdown library, then search, graph, measure coverage, and write surveys in the same conversation

Flagship multimodal vision hub for DeepSeek Harness: ~40 tools, PDF drag-and-drop, LaTeX formulas, complex tables, QR codes, UI flow diagrams, and multi-model consensus.

Microsoft MarkItDown as a DeepSeek Harness tool: convert PDF, Word, Excel, PowerPoint, HTML, CSV, EPUB, or a URL into Markdown the model can read.

DLT (DeepSeek Light Tool) — DSH 永久插件：每轮对话的人民币消耗、右下角账户余额、PDF/Word/Excel 直接读写工具与右栏预览、硬编码的编译/运行环境表与直接执行程序的工具、输入框旁的草图按钮（现画一张 → 图片附件或 PNG 路径），并带一个「DLT 管理器」运行期总开关；被 DET 全量接管时整体停摆。Permanent DeepSeek Harness plugin: per-turn CNY cost, account balance, native PDF/

ZPDF tools for DeepSeek Harness with durable API-key settings and CLI configuration.

DSH 插件：Markdown → 单文件 HTML + A4 PDF（同一条渲染管线，页眉按文档首个一级标题自动生成）

Human-editable notes, todos and documents for DeepSeek Harness, with search, tables, attachments, export and optional agent collaboration.

Workspace document vault for the dsh web GUI: a conversation '文档' tab with an all-type file tree (Markdown/PDF/HTML/code/Excel·CSV/images), full GFM rendering via the platform MarkdownText (tables, task lists, footnotes, KaTeX math, highlighted code fence

--- description: "The out-of-tree ocr tool: recognizes a scanned PDF or image page by page, merges the pages in order only after the last one, and saves one Markdown document with the heading levels the model decided." kind: "package-reference" ---

Project PDF library with background indexing and cited page highlights for DeepSeek Harness Web

Academic URL proxying and metadata-based paper download filenames with Simplified Chinese, Traditional Chinese and US English settings for DeepSeek Harness

DeepSeek Harness plugin: content-aware PDF reading tools for vision models (pdf_scan / pdf_read_page / pdf_render_region). Detects figures (vector+raster), tables, math, and two-column layout per page, then routes text pages to extraction and figure/table

EndNote library integration for the DeepSeek Harness: add papers with their open-access PDFs, manage attachments and groups, de-duplicate, and refresh the search index. Registers 2 skills and 7 native tools over one shared Python implementation.

Stamp a company seal onto a PDF — a contract seal on chosen pages, and a straddle seal split across every page edge so a swapped or removed page shows. Renders a seal image; it is not a cryptographic signature.

A paper-review panel for the DeepSeek Harness: converts PDF papers into structured, selectable text with figure and display-equation rendering, a floating ask-about-the-selection dialog, and per-project paper stores under a Paper workspace.

Native DeepSeek Harness Cordis plugin for PDF page extraction, splitting, merging & rotation

Read-only in-conversation file preview for DeepSeek Harness: a session-authorized host Remote and a sanitizing browser modal, installed as one profile bundle.

Drag-and-drop document reading for DeepSeek Harness: land PDF / Word / PowerPoint files in the workspace and give the agent outline, search and read tools so it can answer questions from them.

Design-enhanced Office document tools for DeepSeek Harness: generate/edit/read PPT, PDF, Word, Excel with gradient backgrounds, icon assets, illustration covers, and template system (auto-search assets when user provides none).

Meta package: one-command installation of useful community plugins for DeepSeek Harness — upload button, document reader, vision (image reading via DeepSeek's built-in multimodal model), plugin manager, and desktop launcher.

DeepSeek Harness document-routing tools: sniff a file's real format and a PDF's page layout, then extract with the right pipeline — layout-aware Markdown for multi-column papers, MarkItDown for everything else, images for scans.

Managed document pipeline for the DeepSeek Harness: Markdown to DOCX/PDF, DOCX/PDF back to Markdown, and online sources as agent tools

Independent community DeepSeek Harness plugin for secure multi-file upload, native images, local document retrieval, and coordinate-aware text/PDF/DOCX/XLSX/PPTX reading.

Office document tools (xlsx / pdf / pptx / docx) for DeepSeek Harness: generate, read, and edit spreadsheets, PDFs, presentations, and Word documents

Office document tools (xlsx / pdf / pptx / docx) for DeepSeek Harness: generate, read, and edit spreadsheets, PDFs, presentations, and Word documents