home / skills / openclaw / skills / bioskills

bioskills skill

/skills/djemec/bioskills

This skill installs the full bioSkills collection of 425 bioinformatics tools to enable rapid setup of comprehensive analysis workflows.

npx playbooks add skill openclaw/skills --skill bioskills

Review the files below or copy the command above to add this skill to your agents.

Files (3)
SKILL.md
4.3 KB
---
name: bioskills
description: "Installs 425 bioinformatics skills covering sequence analysis, RNA-seq, single-cell, variant calling, metagenomics, structural biology, and 56 more categories. Use when setting up bioinformatics capabilities or when a bioinformatics task requires specialized skills not yet installed."
metadata: {"openclaw":{"requires":{"bins":["git"],"anyBins":["python3","Rscript"]},"os":["darwin","linux"],"emoji":"🧬"}}
---

# bioSkills Installer

Meta-skill that installs the full bioSkills collection (425 skills across 62 categories) for bioinformatics analysis.

## Installation

Run the bundled install script to download and install all bioSkills:

```bash
bash scripts/install-bioskills.sh
```

Or install only specific categories:

```bash
bash scripts/install-bioskills.sh --categories "single-cell,variant-calling,differential-expression"
```

## What Gets Installed

| Category Group | Categories | Skills |
|----------------|-----------|--------|
| Sequence & Alignment | sequence-io, sequence-manipulation, alignment, alignment-files, database-access | 40 |
| Read Processing | read-qc, read-alignment | 11 |
| RNA-seq & Expression | differential-expression, rna-quantification, expression-matrix | 14 |
| Single-Cell & Spatial | single-cell, spatial-transcriptomics | 25 |
| Variant Analysis | variant-calling, copy-number, phasing-imputation | 21 |
| Epigenomics | chip-seq, atac-seq, methylation-analysis, hi-c-analysis | 25 |
| Metagenomics & Microbiome | metagenomics, microbiome | 13 |
| Genomics & Assembly | genome-assembly, genome-annotation, genome-intervals, genome-engineering, primer-design | 29 |
| Regulatory & Causal | gene-regulatory-networks, causal-genomics, rna-structure | 13 |
| Temporal & Ecological | temporal-genomics, ecological-genomics | 11 |
| Immunology & Clinical | immunoinformatics, clinical-databases, tcr-bcr-analysis, epidemiological-genomics | 25 |
| Specialized Omics | proteomics, metabolomics, alternative-splicing, chemoinformatics, liquid-biopsy | 36 |
| RNA Biology | small-rna-seq, epitranscriptomics, clip-seq, ribo-seq | 20 |
| Phylogenetics & Evolution | phylogenetics, population-genetics, comparative-genomics | 16 |
| Structural & Systems | structural-biology, systems-biology | 11 |
| Screens & Cytometry | crispr-screens, flow-cytometry, imaging-mass-cytometry | 22 |
| Pathway & Integration | pathway-analysis, multi-omics-integration, restriction-analysis | 14 |
| Infrastructure | data-visualization, machine-learning, workflow-management, reporting, experimental-design, long-read-sequencing | 39 |
| Workflows | End-to-end pipelines (FASTQ to results) | 40 |

## After Installation

Once installed, skills are automatically triggered based on the task at hand. Example requests:

- "I have RNA-seq counts from treated vs control samples - find the differentially expressed genes"
- "Call variants from this whole genome sequencing BAM file"
- "Cluster my single-cell RNA-seq data and find marker genes"
- "Predict the structure of this protein sequence"
- "Run a metagenomics classification on these shotgun reads"

## Source

GitHub: https://github.com/GPTomics/bioSkills

## Related Skills

After installation, 425 individual skills become available across these categories:
sequence-io, sequence-manipulation, database-access, alignment, alignment-files,
variant-calling, phylogenetics, differential-expression, structural-biology,
single-cell, pathway-analysis, restriction-analysis, methylation-analysis,
chip-seq, metagenomics, long-read-sequencing, read-qc, read-alignment,
rna-quantification, genome-assembly, genome-intervals, data-visualization,
expression-matrix, copy-number, proteomics, flow-cytometry, population-genetics,
multi-omics-integration, spatial-transcriptomics, machine-learning,
workflow-management, microbiome, metabolomics, phasing-imputation,
primer-design, hi-c-analysis, imaging-mass-cytometry, atac-seq,
crispr-screens, reporting, experimental-design, clinical-databases,
tcr-bcr-analysis, small-rna-seq, epitranscriptomics, clip-seq, ribo-seq,
genome-engineering, systems-biology, epidemiological-genomics,
immunoinformatics, comparative-genomics, alternative-splicing,
chemoinformatics, liquid-biopsy, genome-annotation, gene-regulatory-networks,
causal-genomics, rna-structure, temporal-genomics, ecological-genomics, workflows

Overview

This skill installs the full bioSkills collection: 425 bioinformatics skills spanning 62 categories, from sequence analysis to structural biology. It provides a one-step way to add a comprehensive set of specialized capabilities so downstream tasks trigger the appropriate skill automatically. Use it to provision a complete bioinformatics skillset or install only selected categories when you need targeted functionality.

How this skill works

The installer runs a bundled script that downloads and registers every skill or an explicit subset of categories you specify. After installation, individual skills are available to the agent and are automatically matched to user tasks (for example RNA-seq analysis, variant calling, or single-cell clustering). You can limit installation to named categories to save time and disk space.

When to use it

  • Setting up a new bioinformatics agent or environment that needs broad capabilities
  • Preparing for an analysis pipeline that may require multiple specialized tools (e.g., single-cell + differential expression)
  • When a task requires a skill not yet installed and you want to add the whole collection
  • Provisioning reproducible analysis environments across projects or teams
  • Testing or benchmarking many bioinformatics skills at once

Best practices

  • Install only the categories you need to reduce download and install time
  • Run the installer from a stable network connection and sufficient disk space
  • Verify installed categories by checking the skill registry or a post-install list
  • Pin specific versions for reproducibility if running analyses across time
  • Use isolated environments (containers or virtualenvs) to avoid dependency conflicts

Example use cases

  • Install all skills on a server to support diverse user requests across genomics, metagenomics, and proteomics
  • Install only single-cell, differential-expression, and rna-quantification for an scRNA-seq project
  • Provision a CI test runner that validates pipelines across many categories
  • Add long-read-sequencing and genome-assembly skills before running de novo assembly experiments
  • Quickly enable structural-biology and protein-folding requests on demand

FAQ

Can I install only specific categories?

Yes. The installer supports a --categories option so you can list comma-separated category names to install a targeted subset.

What happens after installation?

Installed skills are registered and automatically triggered based on incoming tasks; you can immediately request analyses like variant calling, differential expression, or single-cell clustering.