Biomni

What it does

When your agent uses it

• Conducting multi-step biomedical research including CRISPR screening design
• Single-cell RNA-seq analysis
• ADMET prediction
• GWAS interpretation

Example prompts

• “/biomni”

Requirements

• Python 3
• Docker
• A credential in ANTHROPIC_API_KEY

Workflow steps

6 steps, taken from the step headings in SKILL.md.

1. 1Agent Initialization
2. 2Task Execution Workflow
3. 3Common Task Patterns
4. 4Data Integration
5. 5MCP Server Integration
6. 6Evaluation Framework

What it can do on your machine

Read from SKILL.md and the folder at commit c0ca7da. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 2 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • uv

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • github.com
  • huggingface.co
  • biomni.stanford.edu
  • biorxiv.org

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • ANTHROPIC_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Biomni loads about 2.4k tokens when it runs, and up to ~14k if it reads all its reference files. Until then it costs about 115 tokens; SKILL.md has 595 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~115

When it runs · the whole SKILL.md, loaded when a task matches

~2.4k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~14k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:41

  Configure API keys (store in `.env` file or environment variables):

• NoteMentions a .env fileSKILL.md:290

  # Or check .env file in working directory

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from davila7/claude-code-templates at commit c0ca7da, republished under its MIT licence (© davila7). 595 words, ~2,444 tokens.

name

biomni

description

Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis. Use this skill when conducting multi-step biomedical research including CRISPR screening design, single-cell RNA-seq analysis, ADMET prediction, GWAS interpretation, rare disease diagnosis, or lab protocol optimization. Leverages LLM reasoning with code execution and integrated biomedical databases.

uv pip install biomni --upgrade

export ANTHROPIC_API_KEY="your-key-here"
# Optional: OpenAI, Azure, Google, Groq, AWS Bedrock keys

from biomni.agent import A1

# Initialize agent with data path and LLM choice
agent = A1(path='./data', llm='claude-sonnet-4-20250514')

# Execute biomedical task autonomously
agent.go("Your biomedical research question or task")

# Save conversation history and results
agent.save_conversation_history("report.pdf")

from biomni.agent import A1
from biomni.config import default_config

# Basic initialization
agent = A1(
    path='./data',  # Path to data lake (~11GB downloaded on first use)
    llm='claude-sonnet-4-20250514'  # LLM model selection
)

# Advanced configuration
default_config.llm = "gpt-4"
default_config.timeout_seconds = 1200
default_config.max_iterations = 50

# Step 1: Initialize agent
agent = A1(path='./data', llm='claude-sonnet-4-20250514')

# Step 2: Execute task with natural language query
result = agent.go("""
Design a CRISPR screen to identify genes regulating autophagy in
HEK293 cells. Prioritize genes based on essentiality and pathway
relevance.
""")

# Step 3: Review generated code and analysis
# Agent autonomously:
# - Decomposes task into sub-steps
# - Retrieves relevant biological knowledge
# - Generates and executes analysis code
# - Interprets results and provides insights

# Step 4: Save results
agent.save_conversation_history("autophagy_screen_report.pdf")

agent.go("""
Design a genome-wide CRISPR knockout screen for identifying genes
affecting [phenotype] in [cell type]. Include:
1. sgRNA library design
2. Gene prioritization criteria
3. Expected hit genes based on pathway analysis
""")

agent.go("""
Analyze this single-cell RNA-seq dataset:
- Perform quality control and filtering
- Identify cell populations via clustering
- Annotate cell types using marker genes
- Conduct differential expression between conditions
File path: [path/to/data.h5ad]
""")

agent.go("""
Predict ADMET properties for these drug candidates:
[SMILES strings or compound IDs]
Focus on:
- Absorption (Caco-2 permeability, HIA)
- Distribution (plasma protein binding, BBB penetration)
- Metabolism (CYP450 interaction)
- Excretion (clearance)
- Toxicity (hERG liability, hepatotoxicity)
""")

agent.go("""
Interpret GWAS results for [trait/disease]:
- Identify genome-wide significant variants
- Map variants to causal genes
- Perform pathway enrichment analysis
- Predict functional consequences
Summary statistics file: [path/to/gwas_summary.txt]
""")

# MCP servers can provide:
# - FDA drug databases
# - Web search for literature
# - Custom biomedical APIs
# - Laboratory equipment interfaces

# Configure MCP servers in .biomni/mcp_config.json

from biomni.eval import BiomniEval1

evaluator = BiomniEval1()

# Evaluate on specific task types
score = evaluator.evaluate(
    task_type='crispr_design',
    instance_id='test_001',
    answer=agent_output
)

# Access evaluation dataset
dataset = evaluator.load_dataset()

# Always save conversation history for reproducibility
agent.save_conversation_history("results/project_name_YYYYMMDD.pdf")

# Include in reports:
# - Original task description
# - Generated analysis code
# - Results and interpretations
# - Data sources used

# Manually trigger data lake download
agent = A1(path='./data', llm='your-llm')
# First .go() call will download data

# Verify environment variables
echo $ANTHROPIC_API_KEY
# Or check .env file in working directory

from biomni.config import default_config
default_config.timeout_seconds = 3600  # 1 hour

© davila7, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (scripts, references) in cli-tool/components/skills/scientific/biomni of davila7/claude-code-templates.

• SKILL.md
• references/api_reference.md
• references/llm_providers.md
• references/use_cases.md
• scripts/generate_report.py
• scripts/setup_environment.py

Open the folder on GitHubat commit c0ca7da

Used in 8 other repositories

We found 20 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 8 other GitHub owners. This page covers the copy in davila7/claude-code-templates, which our catalogue first saw on October 7, 2026.

• jimmc414/Kosmoskosmos-claude-scientific-skills/scientific-skills/biomni
• Microck/ordinary-claude-skillsskills_all/biomniskills_categorized/academic/biomni+10 more
• aiskillstore/marketplaceskills/davila7/biomniskills/k-dense-ai/biomni
• wu-yc/LabClawskills/bio/biomni
• FreedomIntelligence/OpenClaw-Medical-Skillsskills/biomni
• BioTender-max/awesome-bio-agent-skillsskills/openclaw/biomni
• infometa/workbuddyskillsplugins/codebuddy-plugins-official/external_plugins/scientific-skills/biomni
• ai4nucleome/BioMaster.opencode/bioskills/openclaw-biomni