# tooluniverse-pharmacogenomics

tooluniverse-pharmacogenomics is a Claude Code skill that researches gene–drug links, CPIC guidance, and PharmGKB variants. It builds a pharmacogenomics report from a request about a gene, drug, variant, or phenotype.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 265 installs · ★ 1798 repo stars
- Author: mims-harvard
- License: Apache-2.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/mims-harvard/ToolUniverse/tree/HEAD/skills/tooluniverse-pharmacogenomics/SKILL.md
- Updated: 2026-10-24
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/tooluniverse-pharmacogenomics

## What it does

The skill resolves gene, drug, and variant names, finds gene–drug pairs, and retrieves CPIC dosing guidance. It also annotates alleles and variants, checks FDA biomarker labels, and assembles a clinical summary with evidence grades.

For analyses that require computation, the skill runs Python through Bash with pandas, scipy, statsmodels, and matplotlib. It retrieves data through ToolUniverse tools, drawing on sources that include CPIC and PharmGKB. A request can specify a gene, drug, variant, or phenotype, such as CYP2D6 and codeine.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add mims-harvard/ToolUniverse --skill tooluniverse-pharmacogenomics -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/tooluniverse-pharmacogenomics/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/tooluniverse-pharmacogenomics/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add mims-harvard/ToolUniverse --skill tooluniverse-pharmacogenomics -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/tooluniverse-pharmacogenomics/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add mims-harvard/ToolUniverse --skill tooluniverse-pharmacogenomics -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/tooluniverse-pharmacogenomics/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install mims-harvard/ToolUniverse skills/tooluniverse-pharmacogenomics
```

2. **Manually: put the files in place**
- File: `.github/skills/tooluniverse-pharmacogenomics/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add mims-harvard/ToolUniverse --skill tooluniverse-pharmacogenomics -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/mims-harvard/ToolUniverse --path skills/tooluniverse-pharmacogenomics
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/tooluniverse-pharmacogenomics/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add mims-harvard/ToolUniverse --skill tooluniverse-pharmacogenomics -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/mims-harvard/ToolUniverse/tree/HEAD/skills/tooluniverse-pharmacogenomics/SKILL.md

## When to use it
- find gene–drug pairs by CPIC evidence level
- retrieve dosing guidance for a metabolizer phenotype
- interpret a CYP/HLA allele or variant
- assemble a clinical summary from pharmacogenomics data

## Example prompts
- Find CPIC guidance for CYP2D6 and codeine.
- Look up clinical annotations linked to `rs1799853`.
- Prepare a pharmacogenomics summary for a CYP2D6 poor-metabolizer phenotype.

## Source text · SKILL.md · Apache-2.0

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: af81d8e3df87b7a1.

BEGIN THIRD-PARTY FILE af81d8e3df87b7a1
````text
---
name: tooluniverse-pharmacogenomics
description: Pharmacogenomics (PGx) research — drug-gene interactions (CPIC, PharmGKB), CPIC dosing guidelines, variant-drug-response associations, ethnic-allele-frequency considerations, and metabolizer-status scoring. Use for PGx-informed dosing recommendations, CYP/HLA pharmacogenomic allele interpretation, and clinically-actionable PGx report generation.
disable-model-invocation: true
---

## COMPUTE, DON'T DESCRIBE
When analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.

# Pharmacogenomics (PGx) Research Skill

Systematic PGx analysis: resolve gene-drug pairs, retrieve CPIC dosing guidelines, annotate alleles and variants with PharmGKB, check FDA PGx biomarker labeling, and generate evidence-graded clinical recommendations.

## When to Use

- "What CPIC guidelines exist for CYP2D6?"
- "Get dosing recommendations for codeine based on CYP2D6 poor metabolizer status"
- "Which drugs have FDA pharmacogenomic biomarkers for CYP2C19?"
- "Find PharmGKB clinical annotations for rs1799853"
- "Is this patient's CYP2D6 genotype relevant to tamoxifen dosing?"
- "What is the functional status of CYP2D6*4?"
- "List all CPIC level A gene-drug pairs for CYP2D6"

## Workflow Overview

```
Input (gene/drug/variant/phenotype)
  |
  v
Phase 0: Disambiguation (resolve gene symbols, drug names, rsIDs)
  |
  v
Phase 1: Gene-Drug Pair Identification (CPIC pairs + evidence levels)
  |
  v
Phase 2: Guideline & Dosing Retrieval (CPIC recommendations + PharmGKB)
  |
  v
Phase 3: Allele & Variant Annotation (star alleles, function, activity scores)
  |
  v
Phase 4: FDA Biomarker Labeling (regulatory PGx status)
  |
  v
Phase 5: Cross-Database Enrichment (EpiGraphDB, DGIdb, OpenTargets PGx)
  |
  v
Phase 6: Report (evidence-graded clinical summary)
```

---

## Phase 0: Disambiguation

Resolve user input to canonical identifiers before querying PGx databases.

**PharmGKB_search_genes**: `query` (string REQUIRED, e.g., "CYP2D6"). Returns `{status, data: [{id, symbol, name}]}`.
- Use to get PharmGKB gene accession ID (e.g., "PA128" for CYP2D6).

**PharmGKB_search_drugs**: `query` (string REQUIRED, e.g., "codeine"). Returns `{status, data: [{id, name, types}]}`.
- Use to get PharmGKB chemical ID (e.g., "PA449088" for codeine).

**PharmGKB_search_variants**: `query` (string REQUIRED, rsID e.g., "rs1799853"). Returns `{status, data: [{id, symbol, changeClassification, clinicalSignificance}]}`.
- Use to resolve rsIDs and find PharmGKB annotation IDs.
````
END THIRD-PARTY FILE af81d8e3df87b7a1

The third-party file has ended. Everything between the af81d8e3df87b7a1 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2756 of 21886 bytes. © mims-harvard · Apache-2.0 · https://github.com/mims-harvard/ToolUniverse/tree/HEAD/skills/tooluniverse-pharmacogenomics/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
