sagirimo/BioDSH--packages-dsh-biodsh ↗★ 63
dsh-biodsh
BioDSH for DeepSeek Harness: a bioinformatics agent preset with BioDSH skills, a 2000+ skill library, automatic skill selection and a convergence guard 适合医学与湿实验科研人员进行单细胞QC、聚类及差异表达分析等任务。
インストール
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:sagirimo/BioDSH#68437e5c14710cf18a73e7616d254b3bd2f4005d&path:packages/dsh-biodshドキュメント
README 全文を読む ↗dsh-biodsh
中文 | English
BioDSH for DeepSeek Harness: a bundle that adds a BioDSH agent preset for bioinformatics work. Your other presets are not changed.
The BioDSH preset is the standard preset of your dsh release plus:
| Part | What it does |
|---|---|
| BioDSH persona | Answers for doctors and wet-lab scientists, in the user's language; keeps raw data untouched; reports what was actually computed. |
| BioDSH skills | 17 validated BioDSH workflows in the session skill catalog: single-cell QC, clustering, annotation and treatment response; bulk RNA-seq limma-voom; survival (KM, Cox), regression with robust SEs and ANOVA designs, each checked against R; workflow building, and more. |
| Skill library | 2000+ community bioinformatics, clinical and data skills. Kept out of the catalog so it stays small and cacheable; the model searches it with the skill_library tool, and you can still run any of them with /name. |
| Skill selection | On each new message, a model reads the whole catalog (BioDSH skills and library) and injects the one or two skills that fit the request, in the same form as /name. |
| Convergence guard | In a long turn, asks the agent to wrap up (480 s, or 40 steps) and then to answer without tools (780 s, or 60 steps); ends a turn past 80 steps. |
Install
Requires DeepSeek Harness 0.2.1 or later and pnpm on PATH (dsh's plugin manager runs pnpm).
-
Command line
dsh plugin --profile web add dsh-biodsh -
Web UI: open Plugins, choose Install, enter
dsh-biodsh. -
Ask the agent (Creator mode): "install the dsh-biodsh bundle".
Restart dsh after installing, then pick BioDSH in the agent preset menu, or make it the default:
# ~/.dsh/cordis.patch.yml
- id: agent-preset-registry
config:
default: biodsh
BioDSH (PTC) (biodsh-ptc) is the same preset with programmatic tool calling, like dsh's own ptc preset: the model calls tools from one program per step, so writing a script, running it and checking its output take one step instead of three. On 15 development tasks it cut the median from 23 to 16 steps and from 129 s to 97 s at the same accuracy.
Configure
The bundle adds a settings namespace biodsh (a Host row, so you never edit the preset itself). Change it in ~/.dsh/settings.yaml, on the Settings page, or with settings.mutate; most fields apply to the next step without a restart.
# ~/.dsh/settings.yaml
biodsh:
selectProvider: deepseek-official # skill selection model; empty = same route as the agent
selectModel: deepseek-flash
selectMaxInject: 2
guardSoftSeconds: 480 # ask to wrap up (time is the main signal; steps are a backstop)
guardSoftSteps: 40
guardHardSeconds: 780 # ask for a final answer without tools
guardHardSteps: 60
guardMaxSteps: 80 # end the turn (0 = no cap)
library: true # 2000+ skill library and the skill_library tool (restart to apply)
Versions
A dsh agent preset restates its full plugin list, so each dsh-biodsh release is built against one dsh release (dshTarget in package.json) by scripts/build.mjs, which copies the standard preset of that release and changes only the persona and the three BioDSH rows. scripts/install-test.mjs installs a build through dsh's own plugin manager in a fresh home and runs a real turn on the preset.
Licenses
BioDSH code and skills: MIT. Skills under skills/library come from community repositories and keep their own licenses; see each skill's folder.
中文说明
为 DeepSeek Harness 增加一个 BioDSH 智能体预设,用于生信分析。你原有的预设不受影响。
BioDSH 预设 = 你当前 dsh 版本的标准预设,再加上:
- BioDSH 人设:面向医生和湿实验科学家,跟随用户语言作答,不改原始数据,如实报告实际算了什么。
- BioDSH 官方技能:17 个经过验证的流程(单细胞质控/聚类/注释/治疗响应、bulk RNA-seq limma-voom、生存分析 KM/Cox、稳健标准误回归、方差分析设计等,统计类均与 R 逐项对照),出现在会话技能目录里。
- 技能库:2000+ 社区技能,不放进目录(目录保持小而稳定,利于缓存)。模型用
skill_library工具检索,你也可以用/技能名直接调用。 - 技能精选:每条新消息,用模型对照全部技能选出最合适的一两个,以
/name同样的形式注入。 - 收敛护栏:长任务到 480 秒(或 40 步)先提醒收尾,780 秒(或 60 步)要求直接作答;超过 80 步停止本轮。
设置:在 ~/.dsh/settings.yaml 写 biodsh: 一段(字段见上方英文说明),或在设置页修改,大多数改动下一步就生效。
安装:需要 DeepSeek Harness 0.2.1 及以上,并且 PATH 里有 pnpm。
- 命令行:
dsh plugin --profile web add dsh-biodsh - 网页:「插件」→「安装」,输入
dsh-biodsh
装好后重启 dsh,在智能体预设菜单里选 BioDSH,或按上面的 YAML 设为默认。
BioDSH (PTC)(biodsh-ptc)是同一预设加上程序化工具调用(同 dsh 自带的 ptc 预设):模型每步写一段程序来调用工具,写脚本、运行、检查输出一步完成。在 15 道开发题上,步数中位数从 23 降到 16,耗时从 129 秒降到 97 秒,正确率不变。