プラグイン

DeepSeek Harness プラグインバンドル: エージェント向け graphlint デッドコード検出ツール（graphlint_query / graphlint_build / graphlint_config + graphlint skill）。

Plugin manager with a rescue center: grouped enable/disable by necessity, multi update sources (npm / dshfind market / GitHub), browser-first downloads with an auto-install folder, P2P fallback, pre-boot self-check and broken-bundle quarantine.

Unified LLM request/response inspector: reasoning-effort tuning, external-think export, traffic & bundle analysis.

Git Bash shell tool for Windows: runs commands through the bash bundled with Git for Windows, with timeout, sandbox, output truncation, and background jobs, replacing the slow pwsh tool and the WSL-only bash tool.

中国語テキストを人間らしくする bundle プラグイン: 強制的な深層書き換えワークフロー（10 次元ナラティブ監査 + 機能パス + 15 層分布）+ 内容忠実性ガード。編集支援であり、AI 検出器ではない。

ネイティブな Search1API（s1）Web リサーチツール: 検索、ニュース、ページクロール、サイトマップ探索、トレンドトピックをファーストクラスの `s1_*` ツールとして提供。s1 skill を同梱。

GEO brand audit skill bundle: AI-search visibility, recommendations, citations, competitor presence and content-gap diagnosis across 17+ AI engines (ChatGPT/Perplexity/Claude/豆包/DeepSeek/Kimi/文心一言).

Plugin market inside the DSH Web UI: crawls the dsh-plugin topic with noise filtering, curated marks, ranking and one-click install (dsh.bundle-verified).

Bundled Xiaohongshu/RED viral-note agent skill: hot-note research, note generation/rewrite, verification, authorized account analysis, QR login and controlled publishing.

Cyber whale pet for DeepSeek Harness: a floating, feedable, color-customizable whale over shell.overlay that reports token usage, quota, interactions, and session counts — one dsh-plugin bundle carrying the host chat brain and the browser surface

LoongPort DeepSeek Harness (dsh) Cordis bundle and setup CLI

OpenCode Zen free models provider for dsh

飞书渠道适配器（dsh-im 插件家族，experimental）：WebSocket 长连接免公网 + 审批卡片按钮。需要真实飞书自建应用凭据，未经 CI 实测。

DeepSeek Harness plugin for SCNet HPC: SSH setup, CPU/DCU Slurm jobs, cluster probing, compute-node diagnostics, and Hygon DCU/DTK guidance.

In-web plugin manager for DeepSeek Harness: categorized plugin list, preset bundles with one-click switching, import/export and failure auto-rollback, plugin market with one-click install.

Browse and install DSH plugins without leaving the harness: a /store command, a Settings → Plugins tab, two agent-callable tools and a bundled skill, with an approval gate that lists the detected risk flags before anything installs.

Open plugin marketplace: live GitHub dsh-plugin topic search with per-repo package.json verification (dsh.bundle/dsh.client manifest badges and a verified-only filter), npm-first installs with same-source anti-squatting checks, update detection, and five agent tools for headless use.

Login gate for the dsh web surface: password or shared-token authentication, session cookies, rate limiting, and a user-management CLI (dsh.bundle manifest since 0.4.1, one-command `dsh plugin add` mounting).

GitHub search, discovery and audit scripts wrapped as a SKILL.md pack around the gh CLI: repo search, multi-axis explore, trending, repo summaries, similar projects, code search, issue/PR search and org audits; ships as a dsh bundle (and on npm).

Run Stata through DeepSeek Harness: the native Stata AI Skill service auto-starts with DSH (macOS/Windows binaries bundled), so you can run regressions, do-files and econometrics workflows with no manual setup.

Editable Excalidraw diagrams for DeepSeek Harness conversations.

Full vision-capability bundle for DeepSeek Harness: a vision_understand tool (OpenAI-compatible vision APIs, free Zhipu GLM-4V-Flash by default) plus paste/drag-and-drop/button entry points for image recognition.

Create a one-click Windows desktop shortcut from the Settings page: a .cmd launcher + desktop icon for DeepSeek Harness or any local server, auto-opens the browser, with taskbar pin hints.

**DeepSeek Chat (chat.deepseek.com) same-style attachments**: paperclip upload button, 240×64 DS-style file cards with official colored doc icons (PDF/DOCX/XLSX/PPT/IMG extracted from the DS frontend bundle), drag-and-drop, text extraction (PDF/DOCX/XLSX/TXT) injected into the message, and real attachment cards rendered in the transcript (custom user renderer) with the model reading full content.