biomni

Execute end-to-end biomedical research workflows with generated analysis code.

21|2|Updated Dec 8, 2025
One-click install
npx skills add https://github.com/silverstein/claude-scientific-skills-desktop --skill biomni-silverstein
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: biomni
Source: https://github.com/silverstein/claude-scientific-skills-desktop/tree/main/corpus/biomni
Command: npx skills add https://github.com/silverstein/claude-scientific-skills-desktop --skill biomni-silverstein

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Biomni helps you turn open-ended biomedical research questions into end-to-end analyses, including planning, data processing, and evidence-grounded reporting, without you manually wiring every step.

Core Features & Use Cases

  • Multi-step biomedical agent workflows: Decompose tasks and iteratively execute analysis steps for genomics, drug discovery, molecular biology, and clinical interpretation.
  • Code generation and execution: Create and run analysis pipelines programmatically for tasks like CRISPR screen design, single-cell RNA-seq processing, and GWAS interpretation.
  • Biomedical knowledge retrieval: Use integrated biomedical datasets and literature sources to support reasoning and improve result relevance.
  • Cross-domain coverage: Supports common workflows such as rare disease diagnostics, ADMET prediction, pathway enrichment, and protocol optimization.

Quick Start

Tell the biomni skill: "Design a genome-wide CRISPR knockout screen for genes regulating autophagy in HEK293 cells, prioritize targets using pathway relevance and essentiality, and return an interpreted sgRNA library plan."

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 analysis and GWAS interpretation workflows end-to-end?

Automate single-cell RNA-seq and GWAS workflows by decomposing biomedical research tasks into subproblems and iteratively generating, executing, and retrieving data over integrated biomedical databases to produce evidence-grounded reports.

Can I use an autonomous agent to design a CRISPR knockout screen and prioritize gene targets?

Yes, an autonomous agent can design genome-wide CRISPR knockout screens, prioritize targets using pathway relevance and essentiality, and return an interpreted sgRNA library plan without manual pipeline wiring.

What biomedical data and environment do I need to run autonomous genomics research tasks?

You need an installed biomni environment with configured LLM API keys, an initialized autonomous agent, and a specified biomedical data lake path for retrieval and code execution.

Does this support drug discovery workflows like ADMET prediction and pathway enrichment?

Yes, it supports drug discovery workflows including ADMET prediction, pathway enrichment, rare disease diagnostics, and lab protocol optimization across common research scenarios and data modalities.

What is the best way to process open-ended biomedical research questions without manually coding every analysis step?

Decompose open-ended biomedical questions into multi-step agent workflows that autonomously handle planning, data processing, code generation, and evidence-grounded reporting to deliver end-to-end analyses.

Are there limitations when executing clinical genomics diagnostics autonomously?

Autonomous clinical genomics diagnostics depend on the quality of the initialized data lake and integrated databases, requiring an installed biomni environment and valid LLM API keys to execute analysis code and retrieval successfully.