biociao/dsh-science
Project Overview项目介绍
dsh-science is a native DSH plugin built exclusively for DeepSeek Harness, designed as a Claude Science-style research workbench for bioinformatics and life science projects. It can be installed in two ways: either as a profile bundle via the DSH CLI command dsh plugin add, or as a dedicated "Science Mode" agent preset. It ships with a ReAct research loop engine, versioned artifact management with full provenance tracking, an SSH-based remote compute engine for HPC clusters and lab workstations, and 11 specialized skills for end-to-end scientific workflows. All core components of the plugin are zero-dependency, relying only on Node.js built-ins and system OpenSSH binaries.
This plugin is targeted at bioinformatics researchers and developers who use DSH as their primary AI agent workflow tool for computational science projects. It implements a structured research workflow that follows the standard scientific method, from question formulation and hypothesis building through experimentation, analysis, and conclusion drawing. Users can add pre-configured SSH hosts from their ~/.ssh/config file, and long-running bioinformatics jobs can run detached on remote machines, surviving connection drops. Job statuses are automatically tracked, and output files can be pulled back to the local workspace when complete. It also includes a dedicated web UI for adding, editing, and managing remote SSH hosts directly within DSH.
dsh-science is released under the permissive MIT open source license, and is free to use, modify, and distribute for both commercial and non-commercial purposes. It ships with an included companion plugin dsh-model-tier that implements cross-provider model tiering, routing different types of requests to appropriate model tiers based on complexity. After installation, you will need to restart DSH’s web process to activate the remote hosts UI. All test scripts are included in the repository for CI validation, and they only write to temporary directories to avoid modifying your local DSH configuration. No extra third-party dependencies are required to run any part of the plugin.
这是一款专为DeepSeek Harness(DSH)打造的原生科研插件,提供Claude Science风格的科研工作台,面向基因组学、病原体研究、人类健康与生物信息学类项目开发。它内置ReAct研究循环引擎、带完整溯源信息的版本化工件管理、基于SSH的远程HPC计算引擎,还自带11个适配科研场景的专用技能,支持通过DSH原生插件命令一键安装。
它适合生物信息领域的科研人员和开发人员在DSH Agent框架下开展计算型科研项目,遵循“提出问题→建立假说→设计实验→观察结果→分析结论→提出新问题”的标准科研循环工作流。用户可以通过配置化方式添加远程工作站或HPC集群,支持离线 detached 任务运行,结果可自动拉回本地,还自带专属的远程主机可视化配置页面。
该插件核心依赖仅为Node.js内置模块与系统OpenSSH二进制文件,无额外第三方依赖,附带配套的dsh-model-tier模型路由分层模块,遵循MIT许可免费开源。安装后首次使用需要配置SSH主机信息,如果使用预设的科学模式,需要重启DSH的web进程以激活远程主机UI,用户还可根据需求选择按配置文件捆绑安装或按代理预设安装。
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(biociao/dsh-science)
仓库:https://github.com/biociao/dsh-science
本站详情页:https://www.yhbd.top/plugins/biociao-dsh-science/
本站登记:类型 plugin · 归类 原生 DSH 插件 · 许可证 MIT · ⭐ 42 · 最近提交 2026-09-17 · 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。
- 42 stars - an early-stage project星标 42,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
把 biociao/dsh-science 加入你的 DSH 配置(web profile)即可启用。
READMEREADME
dsh-science
A Claude Science–style research workbench for DeepSeek Harness — for genomics / pathogens / human health / bioinformatics projects.
One-liner: dsh-science — Claude Science-style research workbench for DSH: ReAct research-loop engine (research_* tools), versioned artifacts with provenance (artifact_* tools), an SSH remote-compute engine (remote_* tools, mirroring Claude Science's Computer / Remote compute clusters), and 11 science skills for genomics / pathogens / bioinformatics.
- ReAct research loop engine —
research_init/research_state/research_hypothesis/research_experiment/research_findings/research_phase/research_review/research_report, persisted in aresearch-manifest.jsonstate machine (Question → Hypothesis → Experiment → Observe → Analyze → Conclude → Next Question). - Versioned artifacts with provenance —
artifact_save/artifact_list/artifact_show/artifact_diff/artifact_verify/artifact_deprecate/artifact_reproduce: every result saved asartifacts/<name>/v<N>/with per-file SHA-256,artifact.jsonprovenance (command / inputs / environment / envFile) and an append-onlyprovenance.md. - Remote compute engine (SSH / HPC clusters) — 16 tools:
remote_host_add/remote_host_probe/remote_host_notes/remote_run/remote_status/remote_logs/remote_pull/remote_cancel/remote_execetc. Connect lab workstations or HPC clusters via~/.ssh/configaliases (nothing installed on the host, zero third-party deps). Long bioinformatics jobs run as detached processes on workstations or viasbatchon SLURM — they survive connection loss; submission asks for approval by default;remote_statusbatch-monitors and auto-transitions state (running → succeeded/failed/killed);remote_pullfetches outputs back (files over the size threshold stay on the host with their paths recorded). - Remote Hosts config UI (bundle/profile-level) — a Settings > 远程主机 page (the analog of Claude Science's Settings > Compute > SSH hosts): list/add/probe/edit/remove hosts, plus each project's access allowlist and job summary. Host-side REST API (
webServerroute/dsh-science/remote-hosts/*,engines/remote-hosts-ui.mjs) + client bundle (client/remote-hosts-ui/, built byscripts/build-client-bundle.mjs) sharing the same data files as the remote engine. Requires a web-process restart to activate (see docs/remote-hosts-ui.md). - Model Tier router (tiered, cross-provider) — via the companion bundle
dsh-model-tier: within one session, automatically routes auxiliary requests (session titles, compaction summaries) and subagent/background tasks to a light tier, keeps the main conversation on the default tier, and escalates complex work (deep subagent chains, very long inputs) to a strong tier — each tier may point at a different provider (e.g. strong GLM-5.3 / default deepseek-v4-flash / light minimax-M3), mirroring Claude Code's Opus/Sonnet/Haiku strategy. Built on DSH's nativeagent/request+llm/streamwaterfall extension points; a no-op when the tier's provider is unregistered. Installed automatically with dsh-science, but also standalone-installable into any profile (dsh plugin add dsh-model-tier). - 11 science skills — research-loop, science-project-setup, artifact-provenance, scientific-reviewer, literature-connector, parallel-delegation, manuscript-writing, bioinformatics-toolkit, conda-environments, data-inventory, remote-compute.
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 →
amlyczz/dsh-lark-link
Walvez/dsh-codex-sync
ryubyte/dsh-a2a
aiworkskills/dsh-wechat-article
LAN-TINA-WS/dsh-windows-shell-policy