Run bioinformatics analysis workflows with bioSkills
Use bioSkills to give an agent domain-specific bioinformatics procedures, tool choices, and guardrails for omics analysis workflows.
npx skills add agentskillexchange/skills --skill run-bioinformatics-analysis-workflows-with-bioskills
bioSkills is a large SKILL.md collection for bioinformatics work with coding agents. It covers repeatable analysis lanes such as RNA-seq, single-cell analysis, variant calling, genomics, proteomics, microbiome, CRISPR screens, metabolomics, workflow management, data visualization, and clinical biostatistics. The value is in giving an agent procedure-level instructions, tool choices, QC checks, and caveats before it touches scientific data or writes analysis code.
What this skill actually does
Invoke this instead of asking a general coding assistant for bioinformatics help when the operator needs domain-specific workflow guardrails, reproducible analysis steps, and clear boundaries around interpretation. The scope is scientific workflow guidance for agents; it is not a listing for every underlying biology package, not a laboratory LIMS, and not a claim that the agent can replace expert review of clinical or research conclusions.
Inputs and prerequisites: A SKILL.md-compatible coding agent plus the relevant local scientific tooling for the selected workflow, such as R, Python, command-line bioinformatics tools, workflow engines, and analysis data.
Setup notes: Clone https://github.com/GPTomics/bioSkills into the skills location used by the target agent, then invoke the relevant SKILL.md file for the bioinformatics workflow being performed. Install workflow-specific scientific packages only as required by the selected skill.
Source and verification boundary: use https://github.com/GPTomics/bioSkills as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.