poplarity/dsh-science-workbench

Name: poplarity/dsh-science-workbench
Author: poplarity

Plugin插件 Native原生 ⭐ 10 MIT Dev Workflow开发与代码工作流 Prompts & Skills提示词与技能

用于DeepSeek Harness的可复现科学工作台插件：智能体驱动单元格、带反馈/重跑的内联图形、清单溯源和环境快照。9个bio_*工具+工作台UI+出版级图形技能。

Project Overview项目介绍

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

This is a DSH-native plugin that implements a reproducible science workbench built exclusively for DeepSeek Harness. It is targeted at computational research use cases like bioinformatics that demand full end-to-end provenance for all generated research artifacts. It combines Jupyter-style interactive cell execution with inline figure previews, Claude Science’s agent-driven execution model, and Nextflow-style artifact provenance tracking. Its core guarantee is that every output can be traced back to its exact code, inputs, environment, parameters, and random seed, and can be re-run in one click. All inputs and outputs are hashed with SHA-256 to guarantee content integrity.

It ships with 9 agent-facing tools and a three-panel browser-based analysis workbench UI that supports inline figure preview, project search, and lineage tracking. Each new project is automatically initialized with a local git repository, and every step is automatically committed to the git history to preserve full change tracking. All project metadata, including cells, artifacts, provenance, and feedback history, is stored in a plain-text manifest.json file that acts as the single source of truth for the project. The UI supports all common image formats including PNG, JPEG, SVG, PDF, and large figures load on demand.

The plugin bundles two publication-ready figure styling and composition skills adapted from Claude Science, both released under the Apache 2.0 license. It is fully cross-platform, automatically using Bash on macOS/Linux, PowerShell on Windows, and adapting the Python command name to match the host system’s conventions. It can be installed easily via the built-in DSH plugin management command, and the full project is open-sourced under the MIT license. Contributors and developers can install a local development version directly from source code following the documented setup steps. The package is also distributed via npm for easy versioning and updates.

这是一个专为 DeepSeek Harness 开发的原生可重复科研工作台插件，主要面向需要完整可追溯性的计算科研（如生物信息学）场景。它结合了 Jupyter 的交互式单元格运行、Claude Science 的智能体执行引擎以及 Nextflow 的全产物溯源特性，核心承诺是让每一张图、每一个输出产物都明确对应到代码、输入、环境和参数，可一键重新运行。

它提供9个面向智能体的工具，还有浏览器端的三面板分析工作台UI，覆盖项目创建、单元格运行、附加结构化反馈后重运行、溯源查询、多项目管理等全流程功能。每个项目创建后会自动初始化本地 Git 仓库，每一步操作都会自动提交，所有产物信息保存在 manifest.json 中作为唯一可信源。

插件打包了两个符合出版要求的绘图技能，原生支持跨平台运行，在 macOS/Linux 上使用 Bash，Windows 上使用 PowerShell，Python 命令也会自动适配对应系统。可通过 DSH 内置的插件命令一键安装，遵循 MIT 许可开源，用户也可从源码手动安装开发版本。

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-science-workbench（poplarity/dsh-science-workbench）
仓库：https://github.com/poplarity/dsh-science-workbench
本站详情页：https://www.yhbd.top/plugins/poplarity-dsh-science-workbench/
本站登记：类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 10 · 最近提交 2026-08-26 · 主语言 JavaScript

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

10 stars - an early-stage project星标 10，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 dsh-science-workbench

把 poplarity/dsh-science-workbench 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

8.5 KB · 缓存于 2026-08-25 04:55:04 · 8.5 KB

dsh-science-workbench

English | 中文

A reproducible science workbench plugin for the DeepSeek Harness. It blends the best of three worlds:

Jupyter — cells and inline figures you can see and re-run;
Claude Science — an agent as the execution engine;
Nextflow / nf-core — every artifact carries full provenance.

Core promise: every figure and artifact is traceable and replayable. You can always answer “it = which code + which inputs + which environment + which params/seed”, and re-run it in one click.

✨ Features

Code → figure → feedback → redraw — the agent runs a self-contained cell to produce figures shown inline; you attach structured feedback to a figure, and bio_rerun_cell regenerates a derived version (v1 → v2 → v3).
One ledger per project — a plain-text manifest.json is the single source of truth: cells, artifacts, provenance and feedback history.
Reproducible by construction — self-contained scripts, a fresh subprocess per cell, environment.lock, SHA-256 input/output hashes and a fixed seed.
Git-versioned automatically — each project is git init-ed on creation and auto-committed at every step (never pushed).
Cross-platform — the Host shell layer speaks bash on macOS/Linux and PowerShell on Windows; Python resolves to python on Windows and python3 on POSIX.

🛠 Tools

Nine agent-facing tools, plus a browser workbench:

Tool	What it does
`bio_init_project`	Create/open a project: `code/ data/ figures/` + `manifest.json` + `environment.lock` + `git init`.
`bio_run_cell`	Run one self-contained cell, discover figures, register artifacts with hashes, commit.
`bio_rerun_cell`	Re-run a cell with edited code as a derived version (lineage recorded).
`bio_add_feedback`	Attach structured feedback to an artifact (this is how a “redraw it” note becomes history).
`bio_get_project`	Return a project summary: cells, artifacts, provenance and feedback.
`bio_list_projects`	List all projects under the projects root.
`bio_set_projects_dir`	Set the root directory where projects live (persisted across restarts).
`bio_delete_cell`	Delete a cell and its produced artifacts (script + figures).
`bio_mark_cell`	Mark a cell as a final (成品) artifact, or unmark it — flagged in the workbench and index.

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 poplarity/dsh-science-workbench 的 README.md。在 GitHub 查看原文 →