实时扫描最新社区关于 DeepSeek Harness 发布的插件

DeepSeek Harness Web 背景图片插件：在设置-通用-外观中填写本地图片路径替换网页背景,并提供预览与填充方式

Browser automation for DeepSeek Harness: Playwright-powered open/click/type/screenshot/eval tools so the agent can drive real web pages.

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.

适用于 DeepSeek Harness 的模型无关计算机使用能力：优先使用隔离浏览器，提供与提供商无关的观测，文本规划器 + 第三方视觉感知。

DSH Desktop — 内嵌官方 DeepSeek Harness Web UI 的桌面客户端（含自动更新）

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

CORE 界面设定插件：Nous 蓝默认配色、预设与自定义 13 色、氛围光（光晕/呼吸/位置）、背景图（文件选择对话框）、localStorage+IndexedDB 持久化

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.

DSH plugin: prompt the agent to dispatch image recognition to an opencode-go mimo-v2.5 subagent

Multimodal eyes and hands for DeepSeek Harness: GLM vision transcription, OCR, and text-to-image via DashScope / OpenAI-compatible backends, with an in-conversation generated-image card.

DSH PaddleOCR (百度 PaddleOCR-VL 文档布局解析) plugin: OCR tools plus a settings card and task panel

PaddleOCR 文本识别与文档解析技能，集成原生 DeepSeek Harness 工具与 GUI 配置。

PixLuna image source tools for DeepSeek Harness

Vision toolkit for DeepSeek Harness -- glance, ground, detect, crop CLI tools for text-only agents to understand images

Pixel-diff two screenshots into diff.png + a labeled triptych (pixelmatch)

External vision model for DeepSeek Harness: inspect_image sends local images or http(s) image URLs to any OpenAI-compatible chat/completions endpoint and returns the vision model's text answer.

Eight DeepSeek Harness plugins: persona, language guard, vision fallback, python workdir guard, windows encoding guard, cross-agent memory, image generation, and skill shell injection.

DeepSeek Harness plugin: turn UI screenshots into structured, implementation-grade web frontend specs. Deterministic geometry (sharp) + optional vision-model semantics, merged into one JSON + Markdown spec.

Unlimited-OCR 长文档解析，使用原生 DeepSeek Harness 工具和 GUI 配置。

Deployment-level vision plugin for DeepSeek Harness: registers the vision_analyze tool backed by a configurable multimodal model, with a settings-page UI. Zero dependencies.

Vision sidecar for text-only coding agents.

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

DeepSeek Harness 的 see 工具：离线 OCR 带位置信息（macOS Vision）+ ASCII 布局艺术（PIL）+ 视觉模型语义描述（通过 opencode-go 网关的 mimo-v2.5）。适用于任何模型，包括仅文本模型。

DSH LLM 适配器，使用 Codex Luna 转录原生图像附件，然后委托给 DeepSeek