# GPTomics/bioSkills

a set of SKILLS.md for doing bioinformatics with agents like claude code

Repository: https://github.com/GPTomics/bioSkills
Canonical: https://ross.abutalabs.com/products/bioskills
Language: Python
License: MIT
License Family: permissive
Archived: true
Last push: 2026-08-15T13:48:11+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 38, longevity 16
- inputs: {"age_days": 230, "days_push": 18, "days_rel": 201, "gap_med": null, "n_releases_24m": 1}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1193, forks 213 (observed 2026-08-28T04:03:56.586665+00:00)

## What it is
A collection of SKILLS.md files that give AI coding agents (Claude Code, Codex, Gemini, etc.) expert knowledge for bioinformatics workflows, from sequence manipulation to single-cell RNA-seq and variant calling. It includes installers for various agent CLIs and is evaluated against the Bio-Task Bench dataset.

## Use cases
- teach claude code how to write bioinformatics code
- help an AI agent run single-cell RNA-seq analysis
- guide agents through variant calling workflows
- get idiomatic pysam and biopython code from an LLM
- install domain expertise skills into coding agents
- improve agent accuracy on computational biology tasks

## When to choose
- you use AI coding agents for genomics or computational biology work
- you want curated best-practice patterns for bioinformatics libraries like DESeq2, Seurat, or pysam
- you want a benchmarked starting point for agent skills you can fork and customize

## When to avoid
- you need actively maintained skills with bug fixes (the repo is archived)
- your domain is outside bioinformatics
- you want a runtime library rather than prompt/skill files

## Facets
- artifact type: learning-resource
- maturity: abandoned
- function: developer-tools, documentation, sdk
- domain: bioinformatics, artificial-intelligence, developer-tools, education
- platform: python, cli, cross-platform
- tags: agent-skills, claude-code, bioinformatics, skills-md, prompting, archived, ai-agents

## Member repositories
- GPTomics/bioSkills (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:56.586665+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:22:11.979608+00:00, confidence not recorded.
  - readme: https://github.com/GPTomics/bioSkills (fetched 2026-08-28T04:03:56.586665+00:00, sha d50d4ec027a5)
- Data as of 2026-08-30T08:39:29.467469+00:00.