Bioinformatics Agent Skills
17 skills for computational biology: RNA-seq, single-cell, protein structure, docking, literature and figures
- 75 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Scripts call external services: PubMed, PubChem, HDOCK, AlphaFold DB
- The HDOCK docking skill sends protein structures to an external server
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/bioinformatics-agent-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Scripts call external services: PubMed, PubChem, HDOCK, AlphaFold DB
- The HDOCK docking skill sends protein structures to an external server
This is third-party code. Review the repository files before installing.
What it does
A collection of 17 independently installable skills in the Agent Skills standard, built from an archive of more than 200 research scripts. Each skill has a `SKILL.md` with trigger conditions and workflow, a `scripts/` folder with executables and the `methodology.md` and `troubleshooting.md` references that justify parameter choices and diagnose typical failures. Coverage: bulk RNA-seq (`bulk-rnaseq` with FastQC, Salmon and DESeq2), ENA data download, single-cell analysis, PDB parsing and secondary structure, protein-ligand interactions through PLIP, molecular dynamics with RMSD and RMSF, AlphaFold DB structures, docking through HDOCK and LightDock, inter-chain contacts with PyMOL visualization, antimicrobial peptide design and screening, literature search across PubMed, OpenAlex and Semantic Scholar, NCBI BioProject metadata, PDF full-text extraction through GROBID and publication figures. Skills can be copied into `~/.claude/skills/`, installed as a Python package with `pip install -e .` and a shared `biopipe` command, or run as plain scripts. The algorithms are pure Python, so they work without heavy libraries such as scanpy or OpenMM.
Who it is for. Bioinformaticians and computational biologists who analyze transcriptomes, protein structures and literature together with an agent.
Good fit when
- Run RNA-seq data from quality control to differential expression and explain why `padj` came out `NA`
- Choose a mitochondrial gene threshold for single-cell data without losing live cells
- Compute molecular dynamics results: RMSD, RMSF, hydrogen bonds
- Pick target-discovery papers out of thousands and prepare an ROC curve for a reviewer
Not a fit when
- You need a cluster pipeline with a job queue: the skills run scripts and do not orchestrate
- You need clinical or diagnostic analysis: the set is for research and not intended for medical decisions
- You need methods outside the listed areas, such as metagenomics: there is no skill for them
Example request
Run bulk RNA-seq from FASTQ to differential expression with the bulk-rnaseq skill and explain which quality control parameters you choseLimitations
The HDOCK, AlphaFold DB, PubChem and literature search skills call external services over HTTP, so they need network access and depend on those services being up. Native programs such as FastQC, Salmon, DSSP, PyMOL and GROBID are not bundled and are installed separately, and the pure Python versions cover only part of the tasks. Parameters in `methodology.md` reflect the author's experience and should be checked against tool documentation for your own work. The project is active: the last commit was on 27 October 2026.
How to disable. Delete the relevant skill folders from `~/.claude/skills/`. If you installed the package, run `pip uninstall` for it. Results live wherever you pointed `--output`.
FAQ
How do I install the set in Claude Code?
Clone the repository and copy the folders from `skills/` into `~/.claude/skills/`, then restart Claude Code. A skill triggers from the task description, for example a request to run an RNA-seq analysis.
Are API keys needed?
No, the README says there are no cloud services, keys or databases to configure. Some skills simply call open APIs such as PubMed and PubChem.
What is biopipe?
The unified entry point in the Python package. `biopipe --list` shows every skill and `biopipe bulk-rnaseq --help` prints help for one.
Does it work without scanpy and OpenMM?
Yes. The core algorithms are pure Python: single-cell analysis runs without scanpy and DCD trajectories parse without OpenMM.
How are the skills themselves checked?
`scripts/validate_skills.py` and seven CI pipelines check conformance to the Agent Skills standard, syntax, tests and a scan for secrets and vulnerable dependencies.
Discussion
No questions or reviews yet.
Related
SkillsAround 200 skills for Claude Code on bioinformatics, chemistry and biostatistics, from RNA-seq analysis to molecular docking
166 skills for scientific work: bioinformatics, cheminformatics, clinical data, geospatial analysis and 100+ databases
A Google DeepMind skill collection for science tasks: access to biology and chemistry databases, literature search and structural biology
ClawBio is a library of 110 agent skills for bioinformatics: genomics, pharmacogenomics and population genetics, reproducible.
43 skills for healthcare and life sciences: genomics, clinical data, drug discovery, CDISC and claims analytics
37 skills for computational drug discovery: from target selection and docking to ADMET and the clinical record.
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| Bioinformatics Agent Skills (this card) | no | 75 | ||
| Scientific Agent Skills | no | 56,977 | 166 skills for science, from cheminformatics to geodata | |
| ClawBio | no | 1,182 | 110 skills on genomics, pharmacogenomics and population genetics | |
| BioMCP | no | not required | 678 | one binary and an MCP mode for 70 biomedical sources |
README in short
The README explains that the set grew out of a private archive of research scripts, then gives three install routes and tables of skills by area with key capabilities. Project principles, the repository layout and a developer section close it.
README badge
Original SKILL.md
---
name: bulk-rnaseq
description: "This skill should be used when running bulk RNA-seq differential expression analysis: FastQC/trimming, Salmon quantification, counts matrix construction, DESeq2 statistics, GO/KEGG enrichment and publication figures. 用于 bulk 转录组（RNA-seq）差异表达分析全流程。"
license: MIT
compatibility: "Python 3.9+; numpy, scipy, pandas required. Optional: matplotlib (figures), Rscript + Bioconductor DESeq2 (r backend), fastqc/fastp/salmon (external tools)"
metadata:
version: "1.0"
last-reviewed: "2026-10-25"
skill-author: sinder
---
## Overview
本技能把 bulk RNA-seq 的原始 FASTQ 一路处理到可发表的差异表达结论：先做质控与接头去除，再用 Salmon 做转录本定量并汇总成基因水平整数 counts，随后运行 DESeq2 风格负二项 Wald 检验得到差异基因列表，接着做 GO/KEGG 超几何富集，最后输出火山图、MA 图、PCA 图、热图与文字报告。
差异表达统计提供 **双后端**：`--backend python` 使用内置的纯 NumPy/SciPy 实现（size factor 归一化、Cox-Reid 离散度估计、趋势拟合、MAP 收缩、Wald 检验、BH 校正），`--backend r` 调用 Rscript 上的 Bioconductor DESeq2。两者输出同一套列名的结果表，可直接互换对比。
## When to Use This Skill
- 用户要做 bulk 转录组差异表达分析（关键词：RNA-seq、bulk RNA-seq、转录组、差异表达、DEG、DESeq2、Salmon、counts matrix）
- 用户已有 Salmon/STAR 的定量结果，需要构建 counts 矩阵并做差异表达
- 用户需要 GO / KEGG 富集分析（关键词：GO 富集、KEGG 富集、pathway enrichment、功能富集）
- 用户需要 RNA-seq 的标准发表级图表（火山图、MA 图、PCA、热图）
- 用户想在没有 R / Bioconductor 的环境里得到可靠的 DESeq2 风格结果
不适用：单细胞数据（用 `single-cell-rnaseq`）、仅做原始 reads 可视化、蛋白组与代谢组分析。
> **上游衔接**：如果还没有 FASTQ 文件，可先用 [`ena-download`](../ena-download/) 技能按
> SRA/ENA accession 下载原始测序数据（支持断点续传与 MD5 校验），再交给本技能做定量与差异分析。
## Quick Start
```bash
# 完整流程（需要 fastqc / fastp / salmon 在 PATH 中）
export PYTHONPATH="$PWD/packages"
python skills/bulk-rnaseq/scripts/run_pipeline.py \
--input /data/fastq \
--output /results/rnaseq \
--transcriptome /ref/transcriptome.fa \
--tx2gene /ref/tx2gene.tsv \
--metadata /data/metadata.csv \
--go-annotation /ref/go_annotation.csv \
--group-a treated --group-b control
# 跳过外部工具，直接从已有 Salmon 结果开始