dsh-eye-care
★ 0dsh-eye-care眼部护理
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-eye-careDiscover The Best DSH plugins
24183results
Search community plugins for DeepSeek Harness. Compare capabilities, installation instructions and compatibility to find extensions for your AI workflow.
dsh-eye-care眼部护理
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-eye-caredsh-eye-makeup眼妆基础
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-eye-makeupdsh-eyecare-bg把 DSH Web / 桌面版的背景换成护眼绿:宿主侧注入样式覆盖 31 个背景 token(画布/卡片/侧栏/输入框/代码块…),并把自己的设置分区注册进 DSH 设置页(settings.section 槽位)。不改字体字号布局,零依赖。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Sorphone/dsh-eyecare-bgdsh-eyes给纯文本模型装眼睛:把粘贴/拖入/本地图片交给外部视觉大模型,翻译成文字自动喂给主模型(DSH 官方 bundle 插件,图片进来文字出去)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:qing9835/plugdsh-fabric-care面料护理
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-fabric-caredsh-facetDeepSeek Harness 插件:模型架构可视化 —— /visualize 一个模型名或 arXiv 链接,主 agent 自动调研成 spec.json,双子代理并行生成 2D(SVG)与 3D(three.js)架构图,浮窗直接弹出
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:wobenshiwomu/dsh-facetdsh-fact-checkFact-checking skill for DeepSeek Harness: verifies claims against the open web instead of model memory, cross-checks independent sources across domestic and international search ecosystems, and can route three factual judgements (does the evidence support the claim / is this source primary / does this page carry usable text) to a TypeSafe Jev (System One) decision model when a key is configured, falling back to the skill's deterministic rules when it is not.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:7starsseeker/dsh-fact-checkdsh-factorial阶乘
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-factorialdsh-factoryDurable dependency-graph task factory for DeepSeek Harness
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:monotykamary/dsh-factorydsh-failover-continueUnified auto-continue + model failover for DeepSeek Harness: ordered fallback chain with circuit breaking plus automatic continuation of failed turns, one bilingual (RU/EN) settings card.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:elanski/dsh-failover-continuedsh-fal-imagegenfal.ai native image generation for DSH: a FAL_KEY settings card that follows DSH's language (zh/en, English default) plus Agent tools (fal_generate_image async / fal_edit_image / fal_get_image_task / fal_list_image_models) that call queue.fal.run directly — Authorization: Key, queue polling, images[].url.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Enchanted0911/dsh-fal-imagegendsh-family-contact家庭应急联络
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-family-contactdsh-family-gather家庭聚会
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-family-gatherdsh-fanout-pluginDeepSeek Harness 并行多智能体编排插件:发布一条指令,同时派出多个 DeepSeek 副进程并行执行,主进程可随时与任一进程通话、修改指令、中断或收集结果,带对话流内嵌状态面板。
dsh-fare-meter出租车计价器式实时计费:模型生成时逐秒跳动、空闲归零,内置 DeepSeek 官方峰谷时段与 V4-Flash 价格表,5 位小数。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:bunipai/dsh-fare-meterdsh-farmDSH service farm: register, start, stop, restart and watch long-running project services. Left-sidebar entry + overview drawer (per-workspace groups, live log follow, search, export); farm_status/start/stop/restart/logs/register tools for the agent; optional farm.yaml declaration per workspace.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:MarchLiu/dsh-farmdsh-farm-dispatch子代理派发规范(吝啬农场主模式)全局化插件:安装后自动同步 cordis-async(创造模式·异步派发)预设到 ~/.dsh/.agent-presets,并携带派发规范全文(instructions/AGENTS.md)作为 $DSH_HOME/AGENTS.md 的安装源。装完即用:标准/PTC/创造/异步派发等所有带 agent-instructions 的预设自动遵守全局派发规范。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:sangning-h/dsh-farm-dispatchdsh-fasthtml-desktopfasthtml-desktop skill as a distributable DeepSeek Harness (dsh) Cordis Bundle plugin. Registers the fasthtml-desktop Agent Skill (full repo, self-contained) as an embedded skill provider on ctx.skills.
dsh-fate-twin-contractUnofficial Fate-inspired Archer × Rin skin for the DeepSeek Harness Web GUI
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Jayliu2025-vip/dsh-fate-twin-contractdsh-fatigue疲劳自测
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:uckkk/dsh-fatiguedsh-favicon-statusBrowser tab status indicator: paints the document favicon from the ui-session status snapshot (blue running / amber waiting / green done, spinning while work executes) so a backgrounded dsh web tab still shows task state
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:bf185003/dsh-favicon-statusdsh-favoritesDeepSeek Harness plugin: a 收藏夹 (favorites) feature — star a session to keep it, list favorites in a sidebar entry, and protect favorited sessions from archive (fork and rename stay available).
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:andyzhuang233/dsh-favoritesdsh-favorites-digestDeepSeek Harness plugin: /favorites exports your own Douyin and Xiaohongshu web collections to Markdown using a logged-in browser session
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:kittimzhe/dsh-favorites-digestdsh-faxin-searchDSH 客户端插件:登录你的法信(faxin.cn)账号,向 AI 提供结构化的法律条文 / 司法解释 / 裁判规则(审判意见) / 指导性案例检索工具
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:sousike/dsh-faxin-searchUse a feature keyword or category, then sort by recent updates or GitHub stars.
Read the description, AI analysis and original README to understand what a plugin does.
Review compatibility, dependency ranges and instructions, then copy the available install command.
DSH Hub is a community plugin directory for DeepSeek Harness, bringing together descriptions, source links and installation instructions to help you discover and compare extensions.
No. Detail pages show recorded compatibility and dependency ranges. Unknown does not mean compatible; check the project documentation before installing.
Open its detail page and check the installation section. Copy the command into your Harness environment when available, or follow the project README.