Skip to content
dsh.fish

Browse

76 results

Bundle

dsh-ernie-image

DSH ERNIE-Image-Turbo text-to-image plugin: generate images via Baidu AI Studio, save them as durable session attachments, plus a settings card and a generation gallery panel

omdsh-dev3
Bundle

dsh-wikilink

Obsidian-style [[wikilink]] mentions for the DeepSeek Harness web GUI: type [[ in the composer to fuzzy-search note titles and attach their contents to the prompt

zhaoscsc3
Bundle

dsh-image-to-path

Let DSH text-only-model conversations accept dragged/pasted images: save them into the session workspace and insert the file path as text, bypassing the webui attachment channel that otherwise rejects image parts.

cesaryike3
Bundle

@deepseek-ai/dsh-qwen-mm

Qwen-MM-Plugins integration bundle for DeepSeek Harness: bundled multimodal skills, MCP server rows, and an image attachment bridge for text-only model routes

RRRosmontis2
Bundle

dsh-auto-paste

dsh-auto-paste — a DeepSeek Harness plugin (tool template, extended with a web client paste listener): 在输入框粘贴大段文本时自动保存为附件文件。

sakuraqqq2
Bundle

dsh-file-fix

DeepSeek Harness upload UX plugin: unified file import — drag & drop / paste / picker for ANY file type into the session workspace, with a Hermes-style attachment rail

re-ITRT2
Bundle

dsh-utility-tools

DSH 对话工具插件：拖拽任意文件附件（发送时暂存系统临时目录）+ 选中文本引用。支持静态挂载与动态加载。

sharkymew2
Bundle

dsh-file-resource

Private local file attachments for DeepSeek Harness with native images and bounded document reading.

liznee2
Bundle

@dsh-external/dsh-image-vision

Eyes for text-only DeepSeek: view_image tool (any OpenAI-compatible VLM, local Ollama or cloud) + chat image-attachment bridge that rewrites pasted/dropped images into view_image path markers

xsoc12
Bundle

dsh-tool-web-enhanced

Modular search tool for DeepSeek Harness: attach SearXNG, RAG and your own sections to the native web_search.

edusrez2
Bundle

dsh-quick-attach

快捷附图：在会话输入框粘贴图片时自动保存到用户配置的目录，发送消息时把图片的绝对路径一并发送给 AI 识别。设置栏中显示为「快捷附图」。

ximisi2
Bundle

dsh-file-ref

DeepSeek Harness plugin: drag-and-drop file attachment — paste or drop any local file into the DSH web composer as an @workspace path reference

auroralab-art2
Bundle

dsh-files-native

DSH 插件:接近原生质感的附件上传——拖入/粘贴/回形针,图片缩略图与文件卡片混排在官方附件栏

meyaomiao2
Bundle

dsh-dragndrop-attachments

Local drag-and-drop attachments for DeepSeek Harness, delivered as an external plugin

aa22467402
Bundle

img-preview

Inline image preview for DeepSeek Harness: display local image files (PNG/JPG/WebP/GIF/AVIF/BMP/SVG/ICO/TGA) directly inside the chat — fence language `img` + `img_serve` tool. Double-click opens a standalone viewer with free zoom/pan.

dhb861832993-star1
Bundle

attach-plus

DSH web-ui plugin: '/' glyph on the composer command-menu button plus a '+' attach button with separated image/document/other uploads.

BaihaWhite1
Bundle

dsh-postman

DeepSeek Harness web plugin — upload files and folders straight into the conversation (no workspace copy needed): images attach as real image blocks, text content is written into the composer, folders land under ~/.dsh/uploads by directory structure

zhousun55-byte1
Bundle

dsh-drop-any-file

Extend the DeepSeek Harness (DSH) web chat drag-and-drop to accept every file type: dropping any file in the composer saves it into the current session's workspace so the agent can read and use it.

Zenjibad1
Bundle

dsh-annotator

DSH conversation annotator: select transcript text, attach a note in a popup, then send the compiled quote+note pair through the composer.

cw1999mm1
Bundle

dsh-attachment-downscale

附件自动降级：DSH 图片准入（单边 ≤2000px / ≤3.5MB / ≤4000万像素）超限图片不再拒绝，用 sharp 自动缩小/重编码后入库，用户上传手机原图不再踩线。

zoumutou1
Bundle

@iamroven/dsh-web-file-upload

File upload for the DeepSeek Harness web GUI: a folder button, paste, and drag-drop that save files into the session workspace uploads/, with file cards shown alongside image thumbnails.

rrvvvnnn1
Bundle

dsh-eyes

On-demand vision for text-only LLMs in DeepSeek Harness: keep pasted/attached images in the backend, and let the model call view_image to look at them anytime via any OpenAI-compatible vision endpoint — as if the model were natively multimodal.

Leeminjing1
Bundle

dsh-omnifile

DSH 文件适配插件（面向 DSH 0.1.2-alpha.1）：拖拽/粘贴/点击上传/@ 文件引用加入本地文件，以「文件：<路径>」引用随消息发出；主模型按需调用 dshomnifile 工具解析——文本多编码直读、Office/PDF 等文档由 anydoc 提文本、文档内嵌图片与扫描/图文混排 PDF 页由进程内 pdfjs 渲染 + 配置的多模态模型识别（内容哈希缓存 + 并发排队）并组装为 Markdown；聊天内文件卡片可预览图片、本地打开源文件；识别走官方 ctx.llm.stream。

zuuky1