JoukoPuro/dsh-prompt-polish

一个DeepSeek Harness(DSH)插件:在Web输入框的工具行中添加一个✨图标按钮。点击后选择打磨风格,已接入的大模型会把你草稿中的提示词改写得更专业、更易被AI理解。

Project Overview项目介绍

This is a native plugin built exclusively for DeepSeek Harness (DSH), that adds a sparkle icon button to the toolbar of DSH’s web composer. To install the plugin, you need to clone the repository, then run the command dsh plugin --profile web add ./dsh-prompt-polish from the containing directory, then restart dsh web to activate the new bundle. Once activated, the button lets you pick one of four rewrite styles, then uses your connected DSH LLM to rewrite your draft prompt to be more professional and AI-readable before you send it. It supports 11 interface languages, and will automatically match your browser’s language setting, falling back to English if your language isn’t supported.

This plugin is designed for all DSH users who want to improve their prompt quality without extra work. It is especially helpful for new users who are still learning how to write clear, effective prompts for LLMs. When you write a rough draft of your prompt in the DSH web composer, you just click the sparkle button, select your preferred rewrite style, wait a few seconds for the LLM to process, and the plugin will replace your original draft with the polished version for you to review before sending. If you set a default style in the config, you can skip the selection step entirely.

The plugin is released under the open source MIT license, so you can use, modify, or distribute it for any purpose, personal or commercial. To run it, you need a working installation of DeepSeek Harness web version, with a configured model adapter that has an active API key, such as the DeepSeek official provider with a valid API key set in DSH settings. You can optionally configure the plugin via your profile’s cordis.patch.yml file to set an explicit provider and model, default rewrite style, maximum output tokens, or even a custom system prompt for rewriting. If you don’t set an explicit provider and model, it will automatically use the current default agent model from your active DSH session.

这是一款为DeepSeek Harness(DSH)开发的原生插件,它会在DSH网页版的提示词编写器工具栏添加一个带闪光图标的按钮。用户编写好提示词草稿后,点击按钮选择改写风格,插件就会调用当前对话绑定的大模型,将草稿改写得更专业、更易于AI理解,改写完成后会替换原草稿供用户预览确认。插件支持四种改写风格,UI语言会跟随浏览器语言自动切换,支持11种语言,默认回退到英语。

对于经常需要编写提示词的DSH用户来说,这款工具可以帮助优化粗糙的草稿提示词,降低AI理解偏差,提升输出质量。典型使用流程是:用户先在DSH网页对话界面编写好提示词草稿,点击工具栏上的闪光按钮,从菜单中选择想要的改写风格,等待几秒后,原草稿就会被替换成优化后的版本,用户检查确认无误后就可以发送。如果设置了默认风格,还可以省去每次选择的步骤,适配不同使用需求。

本插件基于MIT许可证开源,免费供用户使用和修改。使用前需要用户已经部署好DSH网页版,并且配置好大模型适配器,比如配置好DeepSeek官方API密钥的DeepSeek提供方。安装可以通过DSH命令行执行对应安装命令,完成后重启dsh web即可生效。用户还可以在配置文件中自定义模型提供方、默认风格、最大输出token数,甚至自定义改写的系统提示词。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 warning1 项注意
  • Only 6 stars - very few users, little community feedback星标只有 6,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 web add github:JoukoPuro/dsh-prompt-polish

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

READMEREADME

dsh-prompt-polish

English | 中文

A DeepSeek Harness (DSH) plugin that adds a ✨ sparkle button to the web composer's tool row. Click it, pick a rewrite style, and the already-connected LLM rewrites your draft prompt to be more professional and easier for an AI to understand — then replaces the draft so you can review before sending.

  • Icon-only button — a sparkle glyph in the composer tool row; no text, tooltip gives the full description.
  • Four rewrite styles — balanced / concise / detailed / code-oriented.
  • Multi-language UI — menu copy follows your browser language (zh, en, ja, ko, fr, de, es, pt, ru, it, tr, vi; falls back to English).
  • Uses your connected model — resolves the current default agent model (agentDefaultModel), or an explicit provider/model from config.

Requirements

  • DeepSeek Harness (@deepseek-ai/dsh) web profile running, with a model adapter configured (e.g. the DeepSeek provider with an API key in Settings).

Install

# from a checkout of this repository (or the directory containing it)
dsh plugin --profile web add ./dsh-prompt-polish

Then restart dsh web so the profile picks up the new bundle:

dsh web

Open the web UI, type a draft, and click the sparkle button in the composer tool row.

Configuration

The plugin accepts optional config in the profile's cordis.patch.yml (user layer, applied after the bundle layer):

- id: prompt-polish
  config:
    provider: deepseek-official   # explicit route (optional)
    model: deepseek-v4-flash      # must be paired with provider
    style: balanced               # default rewrite style: balanced | concise | detailed | code
    maxTokens: 2048               # output cap for the rewrite call
    # system: '...'               # custom rewrite instruction (replaces the built-in per-style prompts)

Without provider/model, the plugin uses agentDefaultModel.currentSelection() — the same default model the session uses.

How it works

Half File Role
Host lib/index.js Registers POST /prompt-polish on the web server; streams one LLM rewrite via ctx.llm
Browser lib/client.js Registers the sparkle button into conversation.input.right; opens a style menu; posts the draft and replaces it with the polished text

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 tuning-engines-cli 下一个 Next dsh-token-panel →