プラグイン

Convert PDF, Word, PowerPoint, Excel, HTML, CSV, JSON and ZIP files to Markdown for the model, using a bundled JavaScript engine or Microsoft MarkItDown.

Render interactive diagrams, charts and staged learning visuals alongside native prose in DeepSeek Harness.

Tidy the model list of DeepSeek Harness: hide any model from the selector, rename models and channels while keeping the provider billing rate, and arrange both with arrows. Search, per-provider batch toggles, back to top, one-click restore. Display only — no provider configuration is rewritten.

JavaScript orchestration over DeepSeek Harness tools using Node.js VM or QuickJS WebAssembly backends.

Load, edit, manage, and hot-reload trusted JavaScript and TypeScript userscripts in DeepSeek Harness.

让 DSH 智能体自己读写 Word / Excel：纯 JavaScript，不装 Office 也能跑。

Turns DSH conversations into reviewable community feedback and, after confirmation, submits it to the official DeepSeek Harness Discussions.

Clean Architecture reference library for DSH: 8 pinned reference repos (Go, Java, C#, Python) indexed into a local FTS5 database, with assertion rules, a review ledger, and a read-only observation panel.

Web GUI 用のスマートフォンシェル - サイドバーはセッションをタップすると閉じるオーバーレイドロワーになり、設定シートは全画面の単一カラムになり、トランスクリプトはスマートフォンでの閲覧に合わせて調整されます。

DeepSeek Harness Web UI 用の検索可能・並べ替え可能なモデルピッカー。プロバイダーグループ、お気に入り、models.dev 価格、コンテキストウィンドウ、ライブタスク毎トークンコスト、ローカルモデルフィルターを備える。ワンコマンドインストール：dsh plugin add dsh-model-garden。

DeepSeek Harness 用 run_kernel_code ツール。永続的な Python および JavaScript カーネル（セッションごとに長寿命の python3/node サブプロセス、コアホストドライバーを共有）を提供。アップストリームハーネスの変更が不要なスタンドアロンプラグイン。

DSH Web 向けの温かみのあるライト/ダークテーマ：レスポンシブレイアウト、二言語設定、安全な Markdown プレビュー、ブロックごとのコピーコントロール、テレメトリーなし。

行番号付きシンタックスハイライトと Markdown プレビューを備えた Web GUI 用フローティングワークスペースファイルツリーブラウザー。

DSH plugin: offline JVM production-report diagnostics — thread dumps with Java-level deadlock cycles, GC-log pause percentiles, Maven/Gradle dependency conflicts, exception chains and Spring config diffs. Never touches a running process: no jcmd, no jstac

Turns a Minecraft Java save into a Blender cover or animation: scans the .mca region files for flat open ground, exports the terrain to OBJ, and drives Blender headless with MCprep materials, the BPS character rig and three-point lighting. After each render it reviews the frame with OpenCV for facing, ground contact, exposure, lighting and composition, then re-renders with adjusted parameters when a check fails. Requires Blender 4.2 LTS or newer and Python 3.10+ with opencv-python and numpy; the first run assembles the Minecraft assets with the bundled setup command.

Local code memory with automatic source context, symbol lookup, vector search, and dependency graphs for JavaScript and TypeScript projects.

Select a statement in an AI answer, find candidate support in earlier chat and tool records, classify support, and jump to original passages for review.

Interactive cards in replies, built from a fixed catalog of 31 components (sliders, inputs, sortable tables, charts, function plots, typeset formulas, tabs, checklists, flowcharts, quiz buttons, an animation player): controls recompute in the browser without another model call, and the model never writes HTML or JavaScript. Includes a calculus engine (integrals, derivatives, limits, sums, roots, Taylor polynomials) and a bundled skill that teaches the model when to use a card.

⚡ One-click prompt enhance in the DSH composer. Still short? Keep going for up to 5 rounds; 🕐 every round is auto-saved, one click to roll back; ↩️ the result syncs back to the composer, with a line diff for every change; 🎨 6 read-only built-in presets plus up to 3 of your own, 🪄 button icon and 📍 position are all yours to tweak.

Open a page, wait for it the way it actually needs, extract the readable article, and take a screenshot. Playwright is optional: when it is absent the tools fall back to a static fetch and say so in the result, because a page whose JavaScript never ran means something different from one that rendered. Content is chosen by scoring candidate subtrees on prose density rather than on tag names, so a container loses to the article inside it instead of winning by containing more of the document.

Bundles the official Scrapling agent skill into a DeepSeek Harness profile: anti-bot bypass, stealth browsing, the spiders framework, adaptive parsing and JavaScript rendering, discovered through the host skill catalog.

SillyTavern-style prompt rules for DSH: layered system-prompt anchors, constant/keyword entries, reproducible probability gates and regex rewriting.

Notes taken from DeepSeek Harness conversations: quotes whole replies or selected passages, keeps highlights rendered at their original position in the session, attaches editable Markdown notes, tags them, filters by workspace or session, and exports Markdown or a full JSON backup stored as local JSON files.

Run one DeepSeek Harness web server per project inside WSL2, managed from the Windows dsh app: each project gets its own service, port and dsh home.