DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

Prompt Optimization — DSH Plugin for DeepSeek Harness
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in
← Plugins
P

dsh-prompt-optimization

Prompt Optimization

DSH Prompt Optimization plugin: one-click prompt optimization in the composer input, with an optional dedicated optimizer model in Settings

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add github:du-u-uck/DSH-Prompt-Optimization#c6ccc6d6798911dab53f81ffc40b5e8f229be733
READMECompatibilityVersions

Compatibility and provenance

Prompt Optimization is published as dsh-prompt-optimization and currently resolves to version 0.1.1. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
web
Release source
github
Registry updated
9/13/2026

Versions

0.1.1stable
9/13/2026

Related plugins

Loading related plugins…

Latest
0.1.1
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
web
License
MIT
Source
github
GitHub
★ 0
Weekly downloads
0
Last push
9/13/2026
View source ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue

Related plugins

More verified plugins in productivity-workflow.

Acp App@deepseek-ai/dsh-acp-appThe dsh ACP profile bundle: automation-only JSON-RPC stdio and process lifecycle over dsh-baseClient Ui Task Board@linxin666/dsh-client-ui-task-boardHost-authoritative task board for the DSH Web GUI with real session execution, Host cron scheduling, and optional cross-platform idle-sleep protection; mounted without DSH source changes.Web All@linxin666/dsh-web-allDSH Web UI 全家桶聚合插件:一键安装全部功能插件(task-board / git-graph / pet / remote-web-ui / web-ui-settings / skin-center / community-plugins / compat shim)。compat 桥接层已并入本包(src/client),无需独立 compat npm 包。Agent Teams@nanmicoder/dsh-agent-teamsAgentTeams for DeepSeek Harness: multi-agent team collaboration (captain, members, tasks with dependencies, messaging) driven by natural language, with a tree monitor in the web GUI

README

DSH-Prompt-Optimization(提示词优化插件)

English | 中文

DeepSeek Harness Web 端插件:在对话框输入框旁提供「优化提示词」按钮,一键把当前草稿静默优化后直接覆盖回输入框,支持一键撤回;可在「设置 → 提示词优化」里单独固定优化所用模型(模型列表与「设置 → 模型」同源)。

安装

sh dsh plugin --profile web add github:du-u-uck/DSH-Prompt-Optimization

重启 DSH Web 后即可使用。

功能

功能说明
一键优化点击后把草稿交给宿主侧后台的模型调用,优化结果通过 inputActions.setDraft 直接覆盖输入框
撤回优化成功后按钮变为「撤回」,再点一次恢复优化前的原始草稿(每个会话独立记忆)
默认模型未固定模型时,优先用当前会话所选模型,否则用部署默认模型
设置 → 提示词优化新增设置分区,下拉列出「设置 → 模型」中已配置的全部提供商与模型;选择写回持久化设置命名空间,「跟随当前会话模型」为默认值。

优化前

优化前

优化后

优化后

架构

  • Host 半区(lib/index.js)
    • settings.register('dsh-prompt-optimization', …):持久化 optimizerModel({provider, model} | null)。
    • GET /api/dsh-prompt-optimization/models:读 llm.listProviders/listModels + agentDefaultModel.currentSelection(),即设置页模型列表的同源数据。
    • POST /api/dsh-prompt-optimization/optimize:{draft, provider, model} → 固定 system 指令 + 单条用户消息的一次性 llm.stream 调用,聚合可见文本返回。双端均带 loopback 围栏(peer socket + Host 头)。
  • Client 半区(lib/client.js)
    • conversation.input.right:按钮组件(读 useInput 草稿、写 inputActions.setDraft,会话级状态存模块 Map)。
    • settings.section:模型选择卡片,经 ctx.settingsScope.bind('dsh-prompt-optimization') 写持久化设置。

构建

pnpm install
pnpm build      # 产出 lib/index.js(ESM,Node)+ lib/client.js(CJS closure factory,浏览器)

最推荐安装方式:把整个仓库文件夹扔给Agent,让它自己装

安装(本地 web profile)

powershell -NoProfile -File scripts/install-web.ps1
# 等价于:
#   pnpm build
#   pnpm add "file:D:\...\prompt-optimization"   (在 web profile 目录下;dsh CLI 对含空格路径有限制)
#   把 "dsh-prompt-optimization" 写入 package.json 的 dsh.profile.bundles
#   重启 dsh web --profile web

卸载:

# 在 C:\Users\asus\.dsh\profiles\web 下
pnpm remove dsh-prompt-optimization
# 并从 package.json 的 dsh.profile.bundles 删除 "dsh-prompt-optimization",重启

已知边界

  • 覆盖输入框会丢失草稿中的引用 chip(@文件 等)——优化后文本为纯文本草稿;原始草稿(含 chip 的剪贴板投影)保存在撤回状态中,撤回时按文本恢复。
  • 优化是「纯文本增强」:模型可能在语义上改写措辞,不会新增你在草稿里没有的需求;对结果不满意随时撤回。
  • 一次优化请求的输入上限 256 KB、输出预算 4096 tokens、超时 120 s。