最高の DSH プラグインを見つけよう
1453件
画像理解、スクリーンショット分析、視覚操作プラグインの入力条件と使い方を比較できます。
@arcaneorion/dsh-teaching-boardDSH teaching surface: project agent-generated self-contained HTML into a sandboxed in-session board with handwriting annotation and a built-in screenshot that returns to the conversation as a real user message.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ArcaneOrion/dsh-teaching-board@azhe0306/dsh-desktop-connector桌面控制连接器（Windows）：截屏（含被遮挡/半出屏窗口）、枚举与置顶窗口、鼠标移动点击拖拽滚轮、发送按键与任意中文文字。
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Azhe0306/dsh-connectors#0e5a9012321db8f3e60184a06b1acc5eab0580c2&path:packages/desktop-connector@baihejiangnan/dsh-custom-wallpaperCustom wallpaper engine for the dsh web GUI: upload an image (client-side WebP/JPEG compression), frosted-glass blur, pane opacity, and auto font-color linkage.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:baihejiangnan/dsh-custom-wallpaper@blue/dsh-image-model-routerDeepSeek Harness plugin: route an agent request to a vision model (deepseek-v4-flash-vision-exp) when the user message contains an image, and keep the original model otherwise.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Blue-2571/dsh-image-model-router@carlmarkswx/dsh-aux-coreAuxiliary-model core for DeepSeek Harness: the `auxiliary` settings namespace, capability registry, and unified provider resolution (harness providers or custom definitions)
@carlmarkswx/dsh-aux-settingsAuxiliary Models settings UI for DeepSeek Harness: default provider card, custom provider pool, and per-capability slot bindings
@carlmarkswx/dsh-imagen-auxImage-generation capability registration for the auxiliary-model core: the OpenAI-compatible image provider plus the Settings → Auxiliary Models closure
@carlmarkswx/dsh-imagen-serviceImage generation capability seam for text-to-image models
@carlmarkswx/dsh-imagen-toolModel-facing image generation tool for DeepSeek Harness
@carlmarkswx/dsh-imagen-uiImagen browser UI for DeepSeek Harness: the generate_image tool row (inline gallery + archive paths) and the same-origin attachment route
@carlmarkswx/dsh-multimodelThe auxiliary-model suite as ONE installable DeepSeek Harness bundle: vision + image generation behind the Auxiliary Models settings page. The internal plugin packages ride along as plain profile dependencies (wired by scripts/install-suite.cjs for local checkouts, or by registry dependencies for published builds); this patch layer is the only thing a user profile gains.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:CarlMarkswx/deepseek-multimodel#499c5e019578b7bf6b0e1262fa3f4603b54f99ae&path:packages/distribution/suite@carlmarkswx/dsh-vision-auxVision capability registration for the auxiliary-model core: the OpenAI-compatible vision provider plus the Settings → Auxiliary Models closure
@carlmarkswx/dsh-vision-serviceVision capability seam for DeepSeek Harness: multimodal models as the agent's eyes (ctx.vision registry and dispatch)
@carlmarkswx/dsh-vision-toolModel-facing vision tool for DeepSeek Harness: inspect_image over ctx.vision
@chang416/deepseeDeepSee: DeepSeek Harness vision, multi-model routing, and Gemini visual self-checks before delivery
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:chang416/deepsee@chaoset/adaptive-perfDSH host plugin: bring standard / PTC presets to minimal-mode-level performance — real Minimal tool pair, permanent injected-context suppression with on-demand discovery, runtime-context suppression, and adaptive tool-catalog trimming with demand-driven escalation
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:winliyou/dsh-plugins#c4f3ebb6f33963c89385cecc3318105249464713&path:packages/adaptive-perf@chaoset/dsh-any-connectDSH plugin: bring models offered by WorkBuddy-style desktop agents into DeepSeek Harness — zero configuration, per-model thinking effort, and billing rate at a glance
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ShanWuYinShe/dsh-plugins#fd8e58e4a343b37eb0b706118d6a7015bea718f8&path:packages/dsh-any-connect@chaoset/sandbox-extra-rootsDSH host plugin: extra writable roots for the workspace-write sandbox (Seatbelt/bwrap/Landlock profiles and the fs fence)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ShanWuYinShe/dsh-plugins#fd8e58e4a343b37eb0b706118d6a7015bea718f8&path:packages/sandbox-extra-roots@chaoset/sandbox-extra-rootsDSH host plugin: extra writable roots for the workspace-write sandbox (Seatbelt/bwrap/Landlock profiles and the fs fence)
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:winliyou/dsh-plugins#c4f3ebb6f33963c89385cecc3318105249464713&path:packages/sandbox-extra-roots@chaoset/session-archiveDSH plugin: browse archived sessions, inspect their content, batch-restore or permanently delete them with multi-select
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ShanWuYinShe/dsh-plugins#fd8e58e4a343b37eb0b706118d6a7015bea718f8&path:packages/session-archive@chaoset/session-archiveDSH plugin: browse archived sessions, inspect their content, batch-restore or permanently delete them with multi-select
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:winliyou/dsh-plugins#c4f3ebb6f33963c89385cecc3318105249464713&path:packages/session-archive@chaoset/vision-routerDSH host plugin: route image requests to a vision model for transcription when the session model is text-only
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:winliyou/dsh-plugins#c4f3ebb6f33963c89385cecc3318105249464713&path:packages/vision-router@crazy_th/dsh-computer-useNative Windows Computer Use tools for DeepSeek Harness.
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:ThreeBody6666/dsh-computer-use@deepseek-ai/dsh-acpAutomation-only Agent Client Protocol server for driving DeepSeek Harness agents over JSON-RPC stdio
機能のキーワードやカテゴリで絞り込み、更新日や GitHub Star で並べ替えます。
紹介、AI 分析、元の README を読み、プラグインの機能を確認します。
互換性、依存関係、手順を確認し、利用可能なインストールコマンドをコピーします。
DeepSeek Harness のコミュニティプラグイン集です。紹介、ソースへのリンク、インストール手順をまとめ、拡張機能の検索と比較を支援します。
いいえ。詳細ページは記録された互換性と依存関係を表示します。不明は互換性ありを意味しません。導入前にプロジェクトの文書を確認してください。
詳細ページのインストール欄を開き、コマンドがあれば Harness 環境で実行します。ない場合はプロジェクトの README に従ってください。