maddogfinance/dsh-trading

Name: maddogfinance/dsh-trading
Author: maddogfinance

Plugin插件 Native原生 ⭐ 37 MIT Dev Workflow开发与代码工作流 Data & Analysis数据与分析

交易研究工作台插件：数据接缝 · 确定性指标 · 交互式K线卡

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

This is a native trading research workbench built exclusively for DeepSeek Harness (DSH), distributed as a DSH plugin bundle that works with stock DSH installations without requiring forked or patched core code. You can add it to your existing DSH profile, either the default web or headless profile, and it adds market data fetching, technical analysis, and interactive charting capabilities directly to your DSH agent session. It uses a modular architecture with separate packages for model-facing tools, market data interfaces, and third-party data provider integrations. To install the included Market Analyst preset, copy the preset files to your DSH agent presets directory using the provided shell command.

The workbench is designed for trading researchers and quantitative developers who want to use DSH for market analysis. When running in DSH's web mode, it creates a persistent live chart column on the left side of the interface, where users can enter a trading symbol and select a timeframe to pull and display live market data. Any technical annotations generated by the DSH agent will render directly on this live chart column, and the current chart state is sent back to the agent automatically, so users never need to manually share screenshots for further analysis.

The project is released under the open source MIT license, and it is currently in an early scaffold development stage. It requires the pnpm package manager for installation, dependency management, type checking, building, and running tests. Currently, it supports two data providers: local CSV files as a reference implementation, and Futu OpenD for live market data of global equities and crypto pairs. DSH itself is still in developer preview, so users should expect possible breaking changes between versions as both projects continue to evolve. Future roadmap plans include adding more data providers and new features like backtesting and research journaling.

这是专为DeepSeek Harness（DSH）构建的原生交易研究插件工作台，无需修改DSH核心代码，可直接堆叠在官方的web或headless配置文件之上运行。它为DSH添加了市场数据获取、技术图表绘制、交易研究辅助等核心功能，支持对接本地数据源获取实时行情数据，适配DSH的插件架构。

面向交易研究员和量化开发者，它支持在DSH的web界面中创建固定的实时图表栏，用户输入交易品种和时间周期后即可自动拉取数据展示。AI生成的技术分析标注会直接渲染到图表栏，还可将当前图表信息回传给AI，无需用户手动截图提供给模型分析。

项目采用MIT许可开源，目前处于早期开发阶段，依赖pnpm进行构建和测试，当前已支持CSV本地数据源和富途OpenD实时数据源。项目未来计划添加更多数据源、回测框架、研究日志等功能，使用时需注意DSH本身处于开发者预览版，可能会出现不兼容变更。

View on GitHub在 GitHub 查看

Send to your DSH发给你的 DSH 安装

请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：dsh-trading（maddogfinance/dsh-trading）
仓库：https://github.com/maddogfinance/dsh-trading
本站详情页：https://www.yhbd.top/plugins/maddogfinance-dsh-trading/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 37 · 最近提交 2026-08-23 · 主语言 TypeScript

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 note1 项提示

37 stars - an early-stage project星标 37，属于早期项目

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 trading add @dsh-trading/bundle

把 maddogfinance/dsh-trading 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

22.1 KB · 缓存于 2026-08-23 03:41:09 · 22.1 KB

dsh-trading

A trading research workbench built as plugins for DeepSeek Harness (dsh). No fork, no patched core — just a bundle you stack on the stock web or headless profile.

Status: early scaffold. dsh itself is in developer preview and moves fast; expect breaking changes on both sides.

The workbench

Under dsh web with the optional shell frame, the app becomes chart-first: a persistent, live chart column on the left, the conversation on the right.

┌──┬────────────────────────────────────┬─────────────────────────┐
│  │  CC.BTCUSDT   1m 5m [15m] 1h 1d    │  ⌄ Market Analyst       │
│▸ │  ┌──────────────────────────────┐  │                         │
│  │  │        ╱╲    ╱╲              │  │  MU is coiling under    │
│s │  │  ╱╲   ╱  ╲__╱  ╲_ ── 118,400 │  │  118.4k; the 15m ADX …  │
│e │  │ ╱  ╲_╱          ╲ ── 116,900 │  │                         │
│s │  │▁▂▃▁▂▄▃▁▂▃▅▂▁▃▂▁▄▃▁▂▃         │  │  ▸ annotate_chart       │
│s │  └──────────────────────────────┘  │    ✎ 6 marks — Show     │
│  │  ● live · 15m · 5:05:10 PM   📌    │                         │
└──┴────────────────────────────────────┴─────────────────────────┘
   rail        the chart you drive          the agent you talk to

The column is yours: type a symbol, pick a timeframe, and it fetches over a loopback channel without going through the model at all. It also follows the conversation — when the agent charts something, the column loads that instrument live rather than mirroring the agent's frozen snapshot. Touching the chart at all — a symbol, a timeframe — pins it, and a 📌 chip says so; from then on the agent's drawings arrive as a Show offer on a pill instead of taking the chart out from under you. Click the chip to start following again.

Drawings work the same way in both directions. annotate_chart levels, zones and paths land on the live column; the prose half of the same analysis — the level table, the bull/bear scenario cards — stays in chat, where reading text belongs. And the loop closes: the panel publishes what it is showing back to the host, so the agent can read your chart (get_chart_view, plus a one-line context injection each turn) instead of asking you to screenshot it.

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 →

渲染基于仓库 maddogfinance/dsh-trading 的 README.md。在 GitHub 查看原文 →