Plugins

AI 编译纯文本小说工作台 for the dsh web GUI: import a novel outline (docx/text), plan volumes & chapters with LLM, generate chapter by chapter (3000-4000 chars each), auto AI review & book audit, and export the full book as Markdown/TXT into your chosen output fold

Deterministic loop guard: denies a tool call repeated with identical arguments and caps per-agent calls, in code outside the model; incident log lets a parent interrupt a stuck subagent.

Pre-install static audits for npm-installable DSH plugins; emits and validates the open `dsh-vet/v1` report with severity, confidence, evidence, derived grades, a CI Action, and auditable badges.

right slider for deepseek-harness-plugin.

DSH 自记忆插件（v0.3）把会话中遇到的问题、多种解决方法、脚本文件路径与模型调用全过程结构化记录下来；新会话中，「先查记录 → 有就试 → 成功标命中/失败记根因 → 无则自研 → 最后回写」的闭环自动发生，并支持外部导入解决方法。零运行时依赖、纯本地、离线可用。

Custom script manager for DSH: turn verified operations into reusable scripts that run directly via /script or register as agent tools, with parameterized scripts, declared expected outcomes, and execution history.

Plugin Guard for DeepSeek Harness (DSH): isolate broken plugins so the web UI never goes down, with one-click self-update from npm.

Live request metadata minimization for DeepSeek Harness, covering the native DeepSeek provider with WebUI settings.

let dsh use your skills.quick command and diy buttons.

基于 SenseVoiceSmall（iic/SenseVoiceSmall）多语言语音理解模型的 DSH Desktop 本地语音输入插件。

用于在deepseek harness上直接暴露工作区的文件，使大肥鱼能够直接显示他想给你显示的图片等信息，解决了大肥鱼老是说自己显示不了图片，要你去看本地文件的问题。在过验证码或截图的时候极为有用。

Cursor 风格的 AI 代码编辑器工作台插件（DSH）：文件树、多标签页编辑、引用/备注/翻译、内嵌 AI 输入框、语法高亮

“What should we build next?” There’s a skill for that.

Git-native, auditable long-term memory for AI agents

Actionable quality diagnostics for DSH agent sessions, with tool-call evidence and next-step recommendations.

Visual channel configuration UI for DeepSeek Harness (feishu / imessage / telegram / ...)

A visual plugin marketplace for DSH: browse multiple Git sources, install plugins with one click, and wire skills, subagents, MCP connectors, LSP servers and hooks into the harness automatically.

Stability audit for installed dsh plugins: static risk grading (hook surface, startup work, inject, entry, dep ranges) plus optional isolated install verification.

Browser notification plugin for DeepSeek Harness - system toasts when a task finishes, a run errors, or your input is needed (question / approval / plan review), click to open the session, per-type toggles, and no false 'done' while the main session waits on its subagents.

Evidence-first GitHub research subagent with bounded tools and in-memory request caching.

Self-evolution actuator: consumes problem tickets mined from session logs, synthesizes skill candidates (zero-code tiers by default) behind an eval gate with hold-out canaries, then promotes to project .dsh/skills with human confirm and deterministic rollback.

An approval-gated OME engineering delivery preset with session-isolated lifecycle evidence.

Product Design workflow suite for DeepSeek Harness - a router plus nine pd-* skills carrying ideas from a minimum design brief through visual directions, evidence-grounded research and audits, URL cloning, frontend builds and a blocking design-QA gate.