dsh-ds-attach
chat.deepseek.com-style attachments for DeepSeek Harness: official upload icon, DS-style file cards (240x64, 16px radius), drag-drop, text extraction (PDF/DOCX/XLSX/TXT) injected into the message
94 results
chat.deepseek.com-style attachments for DeepSeek Harness: official upload icon, DS-style file cards (240x64, 16px radius), drag-drop, text extraction (PDF/DOCX/XLSX/TXT) injected into the message
DSH 办公文件插件:阅读 PDF/DOCX/XLSX/PPTX 等常见二进制文档,生成 DOCX/XLSX/PPTX/PDF/CSV 等常见文件。
DeepSeek Harness bundle: the read_document tool reads Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF files as Markdown for the model
Web access for DeepSeek Harness — multi-provider search/fetch on ctx.web, plus GitHub/PDF/YouTube extraction.
Remove gray or off-white scan backgrounds from image-based PDF pages while preserving original image pixel dimensions, page geometry, and anti-aliased text edges. Use for requests such as PDF 去底灰, 扫描件底色变白, 去除纸张灰底, 保持原分辨率, or avoid jagged/binarized text in scanned PDFs.
AI投标灵标书审核 Skill:审核非扫描版 PDF/DOCX 的商务标、技术标和通用文档风险。
VS Code-style file explorer plugin for the dsh web GUI: file panel beside the sidebar, multi-tab preview panel (code/images/PDF/audio/video/Markdown/CSV/Excel/Word/zip), filename search, sort/filter, copy-paste, swap sides and drag-resize — zero patches to official packages
A DeepSeek Harness bundle for local PDF reading, durable paper records, traceable evidence, and cross-paper synthesis.
AI老师 (ai-teacher) agent preset for the dsh web GUI: a full-capability teaching agent focused on reading PDF documents and helping the user master them. The preset files are synced into ~/.dsh/.agent-presets on host startup.
Local-first file conversion for DeepSeek Harness - images, PDF, data, audio/video and office documents. No API keys, no uploads, no token cost.
dsh bundle: local semantic index over workspace documents (MD/PDF/DOCX/TXT) with FTS5 BM25 + local embedding hybrid retrieval, hit citations with line numbers, and incremental updates.
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/math pages to high-DPI region crops rendered for read_image — avoiding DeepSeek's ~800x800 whole-page token ceiling. Backed by PyMuPDF; returns a clear warning (with the exact install command) when Python or a dependency is missing.
AI 系统的数据层:把 18 种来源(文档站/GitHub/PDF/视频/Notebook/Wiki…)转成结构化知识资产,导出到 22 种目标(Claude/Gemini/OpenAI/RAG 管道/编码助手);AI 驱动项目扫描生成配置。受 yusufkaraaslan/Skill_Seekers(14k★ MIT)启发。
SQL 优化模式:EXPLAIN 分析、索引策略、N+1 解决、查询改写。受 wshobson/agents(38k★ MIT)启发。
ZPDF tools for DeepSeek Harness with durable API-key settings and CLI configuration.
DSH 对话报告化分享插件:生成带封面、摘要统计与章节排版的精美报告,导出为 PNG 图片 / 单 HTML 文件 / PDF。
文档快处插件: 拖拽文档进 Web 对话框 → Agent 直接读取处理 → 完成时右侧弹出侧栏展示产出与文件路径。host 端直读本地文件系统(支持 PDF/Word/PPT/EPUB/Notebook/Markdown/文本),提供 doc_list / doc_read / doc_complete 工具与任务侧栏。
DSH Web GUI 全屏 Markdown 阅读器插件:GFM、KaTeX、Mermaid、目录与阅读进度、外部文件变更同步、图片/代码/表格/长章节增强,以及打印与另存 PDF。工作区门禁的只读路由;零构建、零运行时依赖。
Jina AI tools for DeepSeek Harness: search (incl. arxiv/ssrn academic domains), read, screenshot, embed, rerank, classify, pdf, expand, datetime, primer — with a settings-page API key UI.
SendPage for DeepSeek Harness: mounts the remote SendPage MCP (https://sendpageapp.com/mcp) via the in-box @deepseek-ai/dsh-mcp-client bridge — publish an HTML document as a shareable link that opens in one tap, and export it to PNG/PDF/Word.
DeepSeek Harness plugin: web browsing tools (markdown / screenshot / pdf) powered by Cloudflare Browser Run — real headless Chrome with JS rendering, login sessions and WebMCP support.
DeepSeek Harness 对话导出套件:MD/TXT/JSON/CSV/PNG/PDF 导出、公式复制与设置备份
dsh 文件上传解析插件:在对话框“+”菜单与拖拽中接收 txt/md/代码/Word/Excel/PDF 文件,解析后随下一条消息注入模型
Codex-style attachment format expansion for the DeepSeek Harness Web GUI: PDF text-layer extraction (pymupdf4llm / pdfjs), Office text extraction, long-document spill + index cards, scanned-PDF OCR (tesseract.js), and browser-decodable images to PNG.