lzszq/dsh-scholar

Name: lzszq/dsh-scholar
Author: lzszq

Plugin插件 Native原生 ⭐ 47 BSD-3-Clause Data & Analysis数据与分析 Subagents & Orchestration子代理与编排

dsh-scholar

Project Overview项目介绍

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

DSH Scholar is a native plugin built exclusively for DeepSeek Harness (DSH), designed as an AI-powered research workspace for computational research workflows like machine learning and data science. It centralizes project conversations, research materials, code, datasets, controlled experiment runs, research evidence, and TeX manuscripts into a single recoverable project structure. Users can start a new research project from a blank question or continue work that was originally started in other external environments, and access stage-aware research guidance and auditable governance for all research decision steps. It also supports multiple execution environments, including local machines, local Docker, and remote SSH connections.

It is built for researchers who need structured, auditable computational research workflows focused on areas like machine learning, data science, and bioinformatics. The default gate-only mode requires human approval for all major research decisions, so agents cannot bypass research gates or fabricate accepted evidence on their own. A full-auto mode is available for pre-registered fixture profiles, but release, direction, evidence, and unsupported actions still remain under explicit human control. All new projects created with the /new <name> command start in gate-only mode by default to maintain strict research integrity.

The project is released under the open-source BSD 3-Clause License, and is currently under active development. To run a local standalone instance, you need a Linux system with Node.js 24, pnpm 11.20.0, and Docker Engine for controlled experiments and TeX compilation. After installing dependencies with a frozen lockfile and building the project, you can start the standalone UI, access it at http://127.0.0.1:18610, and log in with the generated token stored in your user directory. Users are advised to review all research outputs independently and keep backups of all important project data.

dsh-scholar 是专为 DeepSeek Harness（DSH）开发的原生插件，是面向计算研究领域的 AI 研究工作空间。它将项目对话、研究材料、代码数据、受控实验运行、研究证据和 TeX 手稿整合到同一个可恢复项目中，既支持从零开始针对新问题展开研究，也可以接续已有的外部工作，还提供分阶段研究引导和可审计治理工作流。

它面向研究人员设计，支持明确记录范围、思路、合约、证据、方向和发布等各个研究阶段的决策，所有修改都可追溯审计。执行环境支持本地机器、本地 Docker 或远程 SSH，可绑定固定容器镜像和声明 NVIDIA GPU 能力。典型工作流从项目创建开始，经过思路梳理、基线设定、合约制定，再到受控运行、证据收集，最后完成手稿撰写和发布审核。

本项目采用 BSD 3-Clause 许可证开源，目前仍处于活跃开发阶段，建议仅用于受监督的计算研究工作流，用户需要对所有研究结论和批准操作进行独立审核，并自行备份重要的源材料和结果。运行依赖 Linux 系统、Node.js 24、pnpm 11.20.0，受控实验和 TeX 编译还需要 Docker Engine 支持。

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-scholar（lzszq/dsh-scholar）
仓库：https://github.com/lzszq/dsh-scholar
本站详情页：https://www.yhbd.top/plugins/lzszq-dsh-scholar/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 BSD-3-Clause · ⭐ 47 · 最近提交 2026-09-09 · 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

47 stars - an early-stage project星标 47，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 web add github:lzszq/dsh-scholar

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

READMEREADME

11.5 KB · 缓存于 2026-09-01 05:12:49 · 11.5 KB

DSH Scholar

简体中文 | English

DSH Scholar is an AI research workspace for computational research. It keeps project conversations, research materials, code and data, controlled experiment runs, evidence, and TeX manuscripts in one recoverable project. You can start from a new question or continue work that already exists elsewhere.

DSH Scholar is still under active development. Use it for supervised computational-research workflows, review every approval and research claim, and keep independent backups of important source material and results.

DSH Scholar standalone workspace in English

What it provides

Stage-aware research guidance: Chat supports natural conversation, Grill Me intake, file upload, visual-model input, explicit slash commands, and an authoritative next-step prompt for the current research stage.
Governed research workflow: Scope, Idea, Contract, Evidence, Direction, and Release decisions remain explicit, revision-bound, and auditable.
Controlled execution: Runner Profiles describe local, local-Docker, or remote-SSH environments, including pinned container images and declared NVIDIA GPU capability.
Integrated workspace: project-scoped Chat, editable files, session-bound Web terminals, run logs, artifacts, TeX source, compilation diagnostics, and PDF preview share the same context.
Traceable methodology: Protocol revisions, run classifications, synthesis requests, assurance results, reviewer findings, knowledge-pack activation, and claim-to-evidence links are recorded as durable research state.
Visible collaboration: Trajectory and Topology expose subagent parent-child relationships, status, follow-ups, and outputs.

Intended use and boundaries

DSH Scholar assists researchers; it does not assume responsibility for scientific judgment, approval, authorship, or publication.
gate-only is the normal mode. Agents cannot impersonate a Human principal, fabricate accepted Evidence, or bypass a research Gate.
full-auto means automatic approval only for the allowlisted Scope, Idea, Contract, and Budget Gates of an exact registered FixtureProfile. Its only canonical action executor is currently survey_run. Release, Direction, Intake, Evidence, and unsupported actions remain Human-controlled or are parked with a typed reason.
A name-only /new <name> project always starts as gate-only and collects its Brief through Grill Me; it does not silently inherit full-auto.
Formal experiments must bind immutable code and data snapshots, a frozen Protocol where required, and an explicit Runner Profile. Chat text, ordinary stdout, and Interactive Terminal output do not automatically become formal Evidence.
Images sent to a visual model are untrusted, current-turn Chat context. They do not automatically become OCR output, Brief answers, Evidence, Claims, Gate decisions, or proof that a command ran.
The product focuses on computational research such as machine learning, data science, and bioinformatics. It is not intended for clinical decisions, human studies, wet-lab work, or other high-risk research.

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 lzszq/dsh-scholar 的 README.md。在 GitHub 查看原文 →