138 results
Browser tab status indicator: paints the document favicon from the sessions list projection (green done / amber waiting / blue running, spinning while work executes) so a backgrounded dsh web tab still shows task state
Handoff button for DeepSeek Harness: adds a button to every assistant message that writes a whole-session handoff document into the workspace /handoff directory.
DeepSeek Harness plugin for accurLex Open Platform legal tools
DSH 公文模式：助手回复渲染为公文格式（题头/称谓/标题/正文/落款），发送时临时附加正式公文文风约束，输入区圈阅反馈（画圈=同意，画叉=不同意，自动写入并发送）。
Quick prompts dock for the dsh web GUI: a row of user-defined prompt chips above the composer — click a chip to preview and edit its text (with {{placeholder}} fields), then sync it into the input or send it directly. Prompts are stored in the official settings document, not localStorage.
Independent community DeepSeek Harness plugin for secure multi-file upload, native images, local document retrieval, and coordinate-aware text/PDF/DOCX/XLSX/PPTX reading.
DeepSeek Harness Web GUI 插件:会话输入框 📎 按钮——图片直传官方附件管线;文本类原样暂存;文档(docx/pptx/xlsx/pdf/rtf/odt/epub/csv…)经本地 anydoc 转为 Markdown 后暂存,消息只插图短回执。Composer picker that converts documents to Markdown.
Feishu (Lark) tools for DeepSeek Harness: send messages, read chat history, create/read/append Feishu documents, and grant document access.
自适应 GitHub README 撰写与截图技能：先判断目标类型与截图能力——网页走浏览器截图，无网页的控制台/CLI 走终端截屏（System.Drawing / HTML 终端 / termtosvg），能则询问并自动配图，不能则走无截图模板；强调相对路径防丢图。作为 dsh 插件（cordis skill-bundle）安装后由 host 层注册 readme-writer 技能；SKILL.md 含可被插件商城索引的 name/description/keywords/category/version 元数据。
Microsoft MarkItDown as a DeepSeek Harness tool: convert PDF, Word, Excel, PowerPoint, HTML, CSV, EPUB, or a URL into Markdown the model can read.
Ships a skill that documents how to build, debug and publish DSH plugins, and registers it as a skill root on install
Project PDF library with background indexing and cited page highlights for DeepSeek Harness Web
DeepSeek Harness plugin: typeset LaTeX as font-free SVG/PNG images, draw geometry and function figures from a declarative spec, convert formulas or SVG into embeddable images, and assemble documents with those images inserted
Markdown view: markdown rendering for DSH client plugins, exposed through the client service mdView. A thin facade over the harness MarkdownText primitive (GFM, math, footnotes, highlighted code) plus README-ism handling: raw <img> tags and document-relative targets resolved against the repo.
Local file-upload plugin for DeepSeek Harness: a paperclip button and drag-and-drop that store files per-session under .dsh-uploads/<sessionId>/, plus a read_document tool that pages text and OCRs images (tesseract.js) so a text-only model can still read screenshots.
DeepSeek Harness plugin: operate Office documents via officecli CLI, with live sidebar preview
Ships a skill that documents how to write, review and verify DSH skills: SKILL.md frontmatter rules, how to phrase a description so it triggers, length and splitting guidance, and an A/B check that the skill actually changes agent behaviour.
DSH plugin: zoomable, pannable image preview for the right-sidebar document pane. Adds wheel-zoom (cursor-anchored), drag-pan, fit / fit-width / 1:1, and a zoom readout to the images dsh already shows. / dsh 右侧边栏图片预览缩放插件。