DSH插件商店

dsh-plugin-vision-toolkit

YYTbit

Vision toolkit for DeepSeek Harness -- give text-only agents eyes

sidesight

ZhuXinAI

CLI-first vision sidecar for text-only coding agents. Analyze screenshots, diagrams, charts, UI diffs, and videos with OpenAI-compatible multimodal models.

dsh-multimodal

chenkezhen480

添加deepseek harness生图识图能力插件

dsh-design-qa

sunxin-ai

Design-fidelity QA for DeepSeek Harness: lend any text-only model an eye, then judge whether the implementation matches the mock. Ships the benchmark behind that judgement — four fixtures, 23 injected defects, and every raw model transcript. Retires itself when DeepSeek ships vision.

dsh-multimodal-skill

v587d

给纯文本 LLM 一双慧眼。 一个 DeepSeek Harness（DSH）原生 skill + 零依赖 Python CLI， 为 DeepSeek 等纯文本模型补上图像理解与文档解析（OCR、表格、公式、PDF → Markdown）， 使用免费额度优先的三方多模态 API，国内网络直连、无需代理。

mimo-vision

wulusai2333

DeepSeek Harness (DSH) native plugin — describe_image tool: a vision bridge (image → mimo-v2.5 → text description) over the ctx.fs / ctx.credentials seams

dsh-plugins

zjcdkj

DeepSeek Harness (DSH) plugins. qwen-image gives a text-only coding model eyes: an image goes to a Qwen-VL route through ctx.llm and comes back as text, so DeepSeek keeps coding while Qwen looks. Pure ESM, no build permission at install. | DSH 插件集：qwen-image 让纯文本模型借千问 VL 读图，返回文本；纯 ESM，安装无需构建授权。

dsh-vision-bridge

DreamRift

DeepSeek Harness 多模态视觉桥（dsh-vision-bridge）：贴图经 llm/stream 自动转 VL 文字描述（解决 UNSUPPORTED_CONTENT）+ view_image/ocr_image 主动视觉工具 + 原生多模态路由自动跳过（rc.7）；零依赖。Vision bridge for text-only DeepSeek models.

deepseek-harness-extension

hypergraphdev

DeepSeek Harness browser-extension edition: side panel with page-context awareness, vision-bridge multimodal image reading, and voice input

dsh-vision-relay

junhongchashui

零修改、零切换的 DeepSeek Harness 视觉能力插件：纯文本模型粘贴即读图片，云端 + 本地 Ollama 双后端自动切换，ModLens v2 风格结构化证据输出。

dsh-bundle-vision

skillre

Zero-core-change vision capability for DeepSeek Harness: the describe_image tool + profile bundle, installable via 'dsh plugin add'

vision-mcp

weekitmo

MCP server for image understanding through OpenAI-compatible vision APIs. To provide image recognition capabilities for those large models that do not support Multimodal.