winditer/dsh-prompt-optimizer 预览 preview

winditer/dsh-prompt-optimizer

Plugin插件 Native原生 ⭐ 4 MIT Prompts & Skills提示词与技能

Project Overview项目介绍

This is a native DSH plugin built exclusively for DeepSeek Harness that adds one-click prompt polishing functionality to the DSH composer. To install it, run the DSH CLI command dsh plugin --profile desktop add github:winditer/dsh-prompt-optimizer, replacing desktop with web if you use a web profile. We recommend installing from GitHub instead of npm because the npm package name dsh-prompt-optimizer is shared by multiple unrelated projects, which can cause ambiguity in the DSH marketplace’s installed packages tab. After installation completes, you will need to fully quit and restart DSH to see the new ✨ optimization button added to the right side of the composer.

After installation, the workflow is straightforward: type your raw prompt draft into the DSH composer, then click the ✨ button or press Alt+O while the composer is focused to trigger optimization. The plugin streams results in real time, first showing the model’s reasoning process token by token, then streaming the polished prompt into a preview overlay that appears above the composer. When optimization finishes, you can choose to replace your original draft in-place, copy the result to your clipboard, run another optimization, or dismiss the preview card entirely. This tool is perfect for DSH users who want to quickly turn rough prompt ideas into clear, well-structured prompts.

By default, the plugin works with zero configuration: it reuses the default model from your current DSH session, so you don’t need to provide a separate API key. If you prefer to use a different model, you can disable the "follow session model" option and add a custom OpenAI-compatible endpoint, including base URL, API key, and model name. All plugin settings are stored locally in ~/.dsh/prompt-optimizer-config.json, and any custom API key you add is only sent to the endpoint you configure. The plugin automatically follows DSH’s active theme and language settings, and it is released under the permissive open source MIT license.

dsh-prompt-optimizer 是专为 DeepSeek Harness (DSH) 开发的原生提示词优化插件,可为 DSH 编辑器提供一键提示词润色功能。它默认零配置运行,复用当前 DSH 会话的模型,无需额外配置 API 密钥,同时也支持用户自定义接入兼容 OpenAI 接口的第三方端点。推荐通过 DSH CLI 安装 GitHub 源,避免 npm 包存在的同名歧义问题,安装后重启 DSH 即可使用。

使用时,用户只需在 DSH 编辑器中输入原始提示词草稿,点击编辑器右侧的✨按钮,或按下快捷键 Alt+O 即可触发优化。优化过程支持流式输出,模型推理过程会先逐 token 滚动展示,随后输出优化后的完整提示词。优化完成后,用户可选择原位替换草稿、复制结果、重新优化或关闭预览卡片,适合需要快速提升提示词清晰度和结构性的 DSH 用户。

本插件采用 MIT 许可证开源,配置文件默认存储在 ~/.dsh/prompt-optimizer-config.json,自定义模式下的 API 密钥仅保存在本地,不会上传至其他服务。运行要求 DSH 拥有 web 或 desktop 配置,从源码编译需要 Node.js 22.19 以上版本,推荐使用 pnpm 进行依赖管理。客户端修改仅需刷新页面生效,服务端修改则需要完全重启 DSH 应用。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意
  • Only 4 stars - very few users, little community feedback星标只有 4,几乎没人在用,遇到问题缺少社区反馈
DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

  • DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
  • External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时(Electron / Python / Docker 等)是否齐备
  • Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突:命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

  • Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致,是否归档或长期停更
  • Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
  • curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
  • Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
  • Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需(filesystem / network / shell / clipboard)
  • Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限,以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照,不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装(适合开发者)

CLI Install命令行安装

dsh plugin --profile desktop add dsh-prompt-optimizer

把 winditer/dsh-prompt-optimizer 加入你的 DSH 配置(web profile)即可启用。

READMEREADME

dsh-prompt-optimizer preview card

dsh-prompt-optimizer

English | 中文

License: MIT Node npm

One-click prompt polishing for the DSH composer: select nothing, just type a draft and press ✨ (or Alt+O) — the plugin rewrites it into a clearer, better-structured prompt. Zero-config by default: it follows the current session's model through the harness host services, so no API key is needed. A self-configured OpenAI-compatible endpoint is supported as an alternative.

Features

  • One-click optimize — a ✨ button on the composer's right; Alt+O while the composer is focused does the same
  • True streaming preview — real SSE over the harness webServer: every text-delta from llm.stream is pushed immediately and rendered token by token; reasoning is streamed first, so you watch the model think while it works
  • Zero-config default — reuses the current session/agent default model (host agentDefaultModel + llm services), no API key required
  • Custom endpoint mode — uncheck "follow session model" and plug in any OpenAI-compatible /chat/completions endpoint (base URL + key + model)
  • Action row on completion — replace the draft in place, copy, re-optimize, or dismiss
  • Bilingual UI — follows the DSH language (中文 / English) live, no reload
  • Self-hosted config — settings persist in ~/.dsh/prompt-optimizer-config.json via a loopback RPC channel, independent of the host settings registry
  • Dark-mode ready — all colors follow DSH theme variables; fixed brand blue + white text in deep-night mode
  • Local-only credentials — the API key (custom mode only) lives in the local config file and goes only to the endpoint you configured

Screenshots

Optimization preview card with reasoning and streaming result

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要,完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

← 上一个 Prev dsh-engineering-workflow 下一个 Next DSH-Deeptop →