biomni

Execute complex biomedical research tasks across genomics and drug discovery.

Updated Jan 10, 2026
One-click install
npx skills add https://github.com/robinbarvaag/poynt --skill biomni-robinbarvaag
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: biomni
Source: https://github.com/robinbarvaag/poynt/tree/main/.github/skills/biomni
Command: npx skills add https://github.com/robinbarvaag/poynt --skill biomni-robinbarvaag

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates complex, multi-step biomedical research tasks, enabling researchers to rapidly analyze data, design experiments, and synthesize knowledge across diverse domains.

Core Features & Use Cases

  • Autonomous Task Execution: Decomposes and executes complex queries across genomics, drug discovery, molecular biology, and clinical analysis.
  • Integrated Data Access: Leverages ~11GB of curated biomedical databases and literature.
  • Code Generation & Execution: Dynamically creates and runs analysis pipelines.
  • Use Case: Design a CRISPR screen, analyze single-cell RNA-seq data, predict drug ADMET properties, or interpret GWAS results with a single natural language prompt.

Quick Start

Initialize the agent with your preferred LLM and execute your research task using the go method.

Frequently Asked Questions about biomni

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate single-cell RNA-seq data analysis with an AI agent?

Automating single-cell RNA-seq data analysis is achieved through an autonomous AI agent that decomposes complex queries, generates code, and integrates data from curated biomedical databases to execute multi-step research pipelines. You simply initialize the agent with your preferred LLM and provide a natural language prompt.

Can I predict drug ADMET properties using natural language prompts?

Predicting drug ADMET properties with natural language prompts is supported by the autonomous biomedical research agent framework. The agent dynamically creates and runs analysis pipelines by leveraging integrated data access to extensive biomedical databases and literature.

What Python environment setup is required for biomedical research automation?

Biomedical research automation requires a Python environment with the biomni package installed and configured LLM API keys. You must initialize the agent with your preferred LLM before executing complex research tasks across genomics, drug discovery, and clinical analysis.

Does this AI agent integrate external biomedical databases for GWAS result interpretation?

The AI agent integrates approximately 11GB of curated biomedical databases and literature to facilitate GWAS result interpretation and other clinical analysis tasks. This integrated data access enables the agent to synthesize knowledge and execute multi-step reasoning across diverse biomedical domains.

What are the limitations of using an autonomous agent for molecular biology research?

Limitations of using an autonomous agent for molecular biology research include its reliance on a pre-configured Python environment, specific LLM API keys, and the boundaries of its ~11GB curated database. It dynamically generates and executes code, which requires a properly configured runtime environment to function correctly.