为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode
A note-taking plugin for DeepSeek Harness (DSH). It provides a full MD notes manager and MD notes editor, letting you quickly capture conversation content into notes. Notes can be maintained by syncing to a Git repository
DSH 插件:图片与文件直达纯文本模型——图片保留原生附件体验,PDF/Office/压缩包/视频/音频显示为附件栏方块,点击发送时自动转为工作区路径,配合 dsh-vision-toolkit 粘贴即看图。A DSH plugin that delivers images AND files to text-only models as workspace paths: images keep the native attachment UI, other files show as square chips in the rail, paths append on send — pairs with dsh-vision-toolkit.
Dsh-visual-plugin.Give your text-only model eyes: forward user images to any OpenAI-compatible vision model and see the results in a Web UI right panel
Local OCR plugin for DeepSeek Harness — paste an image, get its text via PP-OCRv5 + ONNX Runtime, fully offline. Supports TUI (cc-tui) and Web. | DeepSeek Harness 本地 OCR 插件:粘贴图片,PP-OCRv5 + ONNX Runtime 识别文字,完全离线,支持 TUI 与 Web
Tavily-backed web search provider plugin for DeepSeek Harness (dsh) — registers a tavily search provider into ctx.web with a settings card in the web GUI
DeepSeek Harness 工作区文件资源管理器:右侧目录树面板,点击/拖拽文件引用进输入框,UI 对齐 DSH 原生风格 | Workspace file explorer plugin for DeepSeek Harness: right-side file tree panel, click or drag file references into the composer, native DSH look
Codex-style attachment formats for the DeepSeek Harness Web GUI: PDF text-layer extraction, Office text extraction, scanned-PDF OCR, long-document spill + index cards, image-to-PNG.
Silent vision bridge for DeepSeek Harness: route chat images to a fixed vision model, preserve UI originals, and reuse observations across compaction and restarts.
Render Markdown to standalone, self-contained HTML in the DeepSeek Harness — an md_html_render tool that works headless, plus a preview/export drawer in the web GUI. One renderer behind both. Zero dependencies.
Vision-augmented DeepSeek adapter plugin for DeepSeek Harness: a vision-capable model describes image input, then a text-only DeepSeek model reasons over the description