Biomedical Skills

SKILL.md files for cancer bioinformatics. Drop one into your project and your AI coding agent handles TCGA data, normalization, and statistics correctly.

Works with Claude Code · Cursor · Codex CLI · Gemini CLI

</div>

graph LR
    A["Browse skills"] --> B["Copy SKILL.md<br>to your project"] --> C["Agent reads<br>domain protocols"] --> D["Correct code with<br>tested parameters"]
    style A fill:#1a1a2e,stroke:#00d9ff,color:#fff,stroke-width:2px
    style B fill:#1a1a2e,stroke:#4ecdc4,color:#fff,stroke-width:2px
    style C fill:#1a1a2e,stroke:#ff6b6b,color:#fff,stroke-width:2px
    style D fill:#1a1a2e,stroke:#87b13f,color:#fff,stroke-width:2px

Skills

Skill	Description	Tests
`cancer-multiomics`	Multi-omics analysis for TCGA/GEO — expression (DESeq2), mutation (maftools), CNV (GISTIC2), methylation (minfi, DMRcate)	TCGA-LUAD
`immune-deconvolution`	Tumor microenvironment estimation via immunedeconv — quanTIseq, EPIC, CIBERSORT, xCell, MCP-counter, TIMER, ESTIMATE, tumor purity correction	TCGA-BRCA
`survival-analysis`	Time-to-event analysis — Kaplan-Meier (ggsurvfit), Cox PH (survival), competing risks (tidycmprsk), RMST (survRM2), optimal cutpoints, forest plots	TCGA-GBM
`single-cell-atlas`	Full scRNA-seq pipeline — QC, doublet detection, normalization, batch integration (Harmony, scVI), Leiden clustering, annotation (CellTypist), pseudobulk DE, trajectory (scVelo, Monocle3), cell communication (CellChat, LIANA), TF activity (decoupleR). Seurat v5 + scanpy	—

Quick start

git clone https://github.com/zamushwani2/biomedical-ai-skills.git

Copy a skill into your project:

# Claude Code
cp skills/cancer-multiomics/SKILL.md your-project/.claude/skills/

# Cursor
cp skills/cancer-multiomics/SKILL.md your-project/.cursor/skills/

# Any agent that reads SKILL.md
cp skills/cancer-multiomics/SKILL.md your-project/SKILL.md

What's a SKILL.md?

A file that gives AI coding agents domain knowledge for a specific field. The agent reads it before generating code and follows tested protocols instead of guessing at parameters.

Without a skill: agent runs DESeq2 without pre-filtering, skips lfcShrink(), uses wrong contrast syntax. With a skill: agent pre-filters low-count genes, applies apeglm shrinkage, handles TCGA barcodes correctly.

Contributing

See CONTRIBUTING.md and SECURITY.md.

License

MIT