DSH 思考增强插件:思考与回复强制中文(system-prompt 注入),思考内容默认展开显示,界面硬编码英文中文化。DSH web plugin: force Chinese in agent thinking/replies, expand reasoning blocks by default, localize hard-coded UI labels.
스킬 · Agent 협업 · 알림 · 인터페이스 확장 · 개발 도구
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:baosfeng/my-dsh-plugins#cc837f22ecaa841de7d263346073dc44c55d50ee&path:plugins/dsh-think-zh-expand
Desktop-grade DeepSeek Harness plugin: native notifications for user questions/approvals, a floating attention HUD, a screen-capture tool, and a multi-agent tiling canvas.
Agent 협업 · 알림 · 인터페이스 확장
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:FuqiangCraft/dsh-desktop#8a807c1b09134e3c232f4991ab8c9a6f615f0b3f&path:packages/dsh-desktop-plugin
DSH notification framework: unified notification event management, per-item config cards on the Settings page, built-in notifiers, and a registration API for derived plugins.
알림
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:gameswu/dsh-notifacation-frame
Desktop notifications for DeepSeek Harness (dsh): get a system notification when a run completes, the model asks a question, or waits for approval. Zero-dependency Cordis plugin.
알림 · 인터페이스 확장
$ npx -p @deepseek-ai/dsh dsh plugin --profile web add github:pitetow/dsh-notify-on-complete
Computer-use settings: a '电脑控制' settings section to enable and configure the Windows-MCP runtime (python version, package, prompt reminder) with live status and rebuild
Computer-use settings: a '电脑控制' settings section to enable and configure the Windows-MCP runtime (python version, package, prompt reminder) with live status and rebuild
Mobile bridge for DeepSeek Harness: forwards dsh/notify events (AI task start/done, scheduler, reminders) to Android system notifications via a queue file the native layer watches — works in background
Mobile bridge for DeepSeek Harness: forwards dsh/notify events (AI task start/done, scheduler, reminders) to Android system notifications via a queue file the native layer watches — works in background
Deliver AI artifacts to the user: model-facing send_file tool copies a produced file into <files>/deliver and emits dsh/notify (kind=deliver) so the mobile native layer can offer one-tap save to Download/DeepSeekHarness
Deliver AI artifacts to the user: model-facing send_file tool copies a produced file into <files>/deliver and emits dsh/notify (kind=deliver) so the mobile native layer can offer one-tap save to Download/DeepSeekHarness
Task notifications + scheduler for DeepSeek Harness: Windows notifications when the AI starts/finishes a task, plus user-defined repeating scheduled tasks with optional commands, driven by the `notify` settings namespace