MJorgin/dsh-media-skills
DeepSeek Harness免费视觉与图像生成——在任何对话中粘贴图像,即使是纯文本会话。GLM-4V-Flash / Qwen3-VL / Gemini故障切换链,ModLens风格的结构化证据,Kolors生成。免费读图·生图 · 三引擎容错 · 无Key入库
Project Overview项目介绍
dsh-media-skills is a native plugin bundle built exclusively for DeepSeek Harness that adds both image reading and generation capabilities to the base DSH environment. It includes two free skills, a pre-configured free vision model route, and a built-in failover chain that automatically switches between providers if one is unavailable. Users can paste, drag, or select any image in a DSH chat session, and the plugin converts the image to text for the base text-only model to process, alongside capabilities to analyze screenshots, detect watermarks, and generate free watermark-free media including illustrations, avatars, backgrounds, and custom banners.
The typical workflow starts when a user adds an image to a text-only DSH chat. The plugin will automatically call the configured vision model, generate a text description of the image, and pass that description along with a thumbnail to the current active model for further processing. To generate new images, users just call the built-in media-tools skill, input their desired prompt, and get a free watermark-free output back in their chat. This plugin is ideal for any DSH user, whether developer or general user, that needs to incorporate visual content processing directly into their existing DSH workflow.
This plugin requires Python 3.9 or newer to run, and works natively with DeepSeek Harness v0.1.1-rc1 and newer; older versions of DSH require the bundled patches included in the repository. All API keys are stored locally on the user’s device, and no keys are ever committed to the plugin repository, which keeps user data private and fully under the user’s own control. The plugin is released under the open source MIT license, is completely free to use, and includes documentation in 9 different languages to support users around the globe.
dsh-media-skills 是专为 DeepSeek Harness 打造的原生媒体技能插件,提供图像识别读取和 AI 图像生成两类核心能力,还内置了免费视觉模型路由和故障转移链。它支持在任意 DSH 对话会话中粘贴、拖入或选择图像,通过免费视觉模型将图像转为文本供当前大模型处理,同时支持分析图像截图、检测水印,生成免费无水印的插图、头像、背景图和横幅。
针对原本仅支持文本处理的 DeepSeek Harness 会话,用户只需要将图像粘贴、拖入或者通过添加按钮选择添加到对话输入框,插件就会自动调用你选定的视觉模型生成图像文本描述,再将描述和缩略图提供给当前大模型使用。需要生成图像时,用户只需要调用 media-tools 技能输入提示词,即可获得免费无水印的生成结果,适合所有需要在 DSH 工作流中处理视觉内容的开发者和普通用户。
该插件要求 Python 3.9 及以上版本,支持 DeepSeek Harness v0.1.1-rc1 及以上版本,旧版本需要应用插件内置的补丁。所有密钥保存在用户本地,不会提交到代码仓库,用户可以自行选择视觉服务商,保障隐私。插件采用 MIT 许可证开源,完全免费使用,文档提供了 9 种语言支持,方便不同地区用户查阅。
请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】,检查通过再动手。
插件:dsh-media-skills(MJorgin/dsh-media-skills)
仓库:https://github.com/MJorgin/dsh-media-skills
本站详情页:https://www.yhbd.top/plugins/mjorgin-dsh-media-skills/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 19 · 最近提交 2026-09-21 · 主语言 Python
按下面顺序执行,每步先把结论告诉我,再进入下一步:
【1 兼容性检查】
① 我这边:DSH 版本、Node 版本、操作系统、当前 profile(web / desktop)。
② 读它的 README、package.json、插件 manifest,列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对,结论只写「满足 / 不满足 / 未知」三种;不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突:命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。
【2 安全性检查】
① 仓库可信度:和上面「本站登记」是否一致;star / fork 数、创建时间、最近提交,是否归档或长期停更。
② 安装脚本:逐行看 package.json 的 preinstall / install / postinstall,以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名,立刻停下来告诉我,不要继续装。
③ 依赖:列出新增依赖,标出无人维护、或与知名包拼写近似的可疑包(typosquatting)。
④ 权限与副作用:它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限(filesystem / network / shell / clipboard 等),以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限,或权限明显超出功能所需,先停下来问我。
【3 安装】
上面两步没有「不满足」和「高危项」时才执行;用官方推荐方式安装,不要自行提权。
【4 汇报】
用表格输出:检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜,也不要替我决定。
Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH:它会先核对兼容性与安全性(逐条给「满足 / 不满足 / 未知」),确认没问题再安装,有高危项会停下来问你。框内可滚动,复制到的是完整提示词;安装命令不一定准确,发给 DSH 更稳。
- 19 stars - an early-stage project星标 19,属于早期项目
DSH walks through these 9 checksDSH 会逐条核对这 9 项
Compatibility兼容性
- DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
- External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
- Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册
Security安全性
- Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
- Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
- curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
- Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
- Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
- Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式
Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。
Or use CLI install (for developers)或使用命令行安装(适合开发者)
CLI Install命令行安装
dsh plugin --profile web add github:MJorgin/dsh-media-skills
把 MJorgin/dsh-media-skills 加入你的 DSH 配置(web profile)即可启用。
READMEREADME

🎨 dsh-media-skills
Give DeepSeek Harness eyes — and a brush. Read images in any chat, generate new ones, all with free models.
DeepSeek Harness is brilliant at reasoning — but a text-only model can't see the image you just dragged into the chat. This bundle fixes that with two free skills, a free vision model route, and a vision engine failover chain:
- 📎 Paste to read — paste, drag, or pick an image in any session; the free vision model turns it into text your current model understands. (Native on v0.1.6 / v0.1.1; on rc.7 / rc.8 via the bundled core patches — see docs/HARNESS_PATCH_EN.md.)
- 👁️
vision-review— analyze images and screenshots, catch UI visual bugs, detect watermarks, turn images into text. - 🎨
media-tools— generate illustrations, avatars, backgrounds and banners with a free, watermark-free model. - 🔀 Engine failover — GLM-4V-Flash (free) → DeepSeek-V4-Flash-Vision-Exp (same key as your agent, higher quality) → SiliconFlow Qwen3-VL → SenseNova → Google Gemini (AI Studio) → any OpenAI-compatible endpoint, with ModLens-style structured evidence output.
No hardcoded keys, no paid API, no file saving, no session switching.
Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →
Alisa0808/vox-director
wuzhigouno-collab/dsh-rp-composer
Anionex/agent-vision-toolkit
ysr666/dsh-vision-router
Anionex/dsh-vision-toolkit
shanliuling/dsh-image-gen
Mars-Sea/dsh-commandcode-provider