bioinformatics

Indexes and fetches 400+ bioinformatics reference skills and runnable pipelines from bioSkills and ClawBio repositories.

Updated May 18, 2026
One-click install
npx skills add https://github.com/ossoolli/Nexum-Core --skill bioinformatics-ossoolli
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: bioinformatics
Source: https://github.com/ossoolli/Nexum-Core/tree/main/optional-skills/research/bioinformatics
Command: npx skills add https://github.com/ossoolli/Nexum-Core --skill bioinformatics-ossoolli

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Bioinformatics work spans hundreds of specialized domains, and no single skill can bundle correct parameters, tool flags, and validated pipelines for all of them. This gateway indexes two open-source bioinformatics skill libraries and fetches the exact domain guide you need on demand. ## Core Features & Use Cases - On-Demand Skill Fetching: Shallow-clone the bioSkills (385 reference guides) or ClawBio (33 runnable pipelines) repositories and read the specific SKILL.md or README for your task. - Domain Index: A categorized index covering genomics, variant calling, bulk and single-cell RNA-seq, spatial transcriptomics, epigenomics, metagenomics, pharmacogenomics, structural biology, proteomics, CRISPR screens, and more. - Use Case: You need to run a GATK variant calling workflow. Clone bioSkills, read variant-calling/gatk-variant-calling/SKILL.md, and follow its validated parameters and code patterns as expert reference material. ## Quick Start Ask the agent to fetch the bioSkills guide for DESeq2 differential expression and apply it to your count matrix.

Frequently Asked Questions about bioinformatics

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I find the right bioinformatics pipeline for my analysis?▼

Identify your domain in the skill index, then shallow-clone the relevant repository and read the specific skill file. bioSkills provides reference guides with code patterns and parameters, while ClawBio provides executable pipelines with demo flags.

What is the difference between bioSkills and ClawBio?▼

bioSkills contains 385 reference skills with code patterns, parameter guides, and decision trees in Python, R, and CLI. ClawBio contains 33 runnable pipeline skills with Python scripts, demos, and reproducibility bundles exporting report.md, commands.sh, and environment.yml.

Can I run ClawBio pipelines directly after cloning?▼

Yes, many ClawBio skills are executable and include --demo flags. Run pip install -r requirements.txt in the cloned repo first, and confirm the required bioinformatics tools are installed on your system.

Does this skill work on Windows?▼

No, the declared platforms are Linux and macOS. The underlying bioinformatics toolchain such as samtools, bcftools, and Bioconductor packages is also primarily supported on Unix-like systems.

What dependencies are needed for bioinformatics analysis?▼

Common dependencies include Python packages like biopython, pysam, anndata, and scanpy, R/Bioconductor packages like DESeq2 and edgeR, and CLI tools like samtools, bcftools, and minimap2 installable via apt, brew, or Bioconda.

Why should I be careful when downloading genomic data?▼

Genomic data files such as reference genomes, SRA datasets, and tool indices can be very large and quickly consume disk space. Plan storage capacity before downloading datasets or building alignment indices.