LiteratureScientific Writing & PublishingFreedomIntelligence/OpenClaw-Medical-SkillsLiterature Review
BI

biomni-research-agent

Maintainer FreedomIntelligence · Last updated April 1, 2026

BioMni research-focused agent with literature, database, and analysis integration.

OpenClawNanoClawDiscoveryReadingbiomni-research-agent🧠 bioos extended suiteresearch infrastructure & agentsbiomni

Original source

FreedomIntelligence/OpenClaw-Medical-Skills

https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills/tree/main/skills/biomni-research-agent

Maintainer
FreedomIntelligence
License
MIT
Last updated
April 1, 2026

Skill Snapshot

Key Details From SKILL.md

2 min

Key Notes

  • A general-purpose biomedical AI agent capable of executing complex research workflows using over 150 tools and databases.
  • Biomni is a "General-Purpose" biomedical agent. Unlike specialized skills (e.g., just for folding proteins), Biomni acts as a high-level orchestrator that can break down complex open-ended research questions into solvable sub-tasks using a vast library of tools.
  • Complex Questions: "What are the potential drug targets for Alzheimer's related to mitochondrial dysfunction?
  • Multi-Step Research: Tasks requiring literature search, data retrieval, and analysis in sequence.
  • Exploratory Analysis: When the exact path to the answer isn't known and requires "reasoning.

Source Doc

Excerpt From SKILL.md

Core Capabilities

  1. Tool Use: Access to 150+ tools, 105 software packages, and 59 databases.
  2. Hypothesis Generation: Can formulate scientific hypotheses and plan experiments to test them.
  3. Plan & Execute: Breaks down queries into a dependency graph of tasks.
  4. Database QA: High accuracy (74.4%) in querying biomedical databases.

Workflow

  1. Query Parsing: The agent analyzes the user's natural language request.
  2. Tool Selection: It selects relevant tools (e.g., "Search GWAS Catalog", "Run GO Enrichment", "Fetch Uniprot Data").
  3. Execution Loop:
    • Step 1: Get data.
    • Step 2: Analyze data.
    • Step 3: Refine plan based on intermediate results.
  4. Synthesis: Combines all findings into a comprehensive answer.

Example Usage

User: "Identify genes associated with Type 2 Diabetes that are also expressed in the pancreas and have approved drugs."

Agent Action:

  1. Tool: OpenTargets -> Get T2D associated genes.
  2. Tool: GTEx -> Filter for high expression in Pancreas.
  3. Tool: DrugBank -> Intersect with drug targets.
  4. Result: Returns a list of genes (e.g., GLP1R, DPP4) and their drugs.

Use cases

  • **Complex Questions**: "What are the potential drug targets for Al.

Not for

  • Do not treat this catalog entry as a substitute for the full upstream workflow.

Related skills

Related skills

Back to directory
BI
LiteratureScientific Writing & Publishing

bio-longread-alignment

Align long reads using minimap2 for Oxford Nanopore and PacBio data. Supports various presets for different read types and applications. Use…

OpenClawNanoClawDiscovery
FreedomIntelligence/OpenClaw-Medical-SkillsView
BI
LiteratureScientific Writing & Publishing

bio-machine-learning-atlas-mapping

Map query cells to reference atlases with scANVI or Symphony.

OpenClawNanoClawDiscovery
FreedomIntelligence/OpenClaw-Medical-SkillsView
BI
LiteratureScientific Writing & Publishing

bio-methylation-bismark-alignment

Bisulfite sequencing read alignment using Bismark with bowtie2/hisat2. Handles genome preparation and produces BAM files with methylation in…

OpenClawNanoClawDiscovery
FreedomIntelligence/OpenClaw-Medical-SkillsView
BI
LiteratureScientific Writing & Publishing

bio-microbiome-taxonomy-assignment

Taxonomic classification of ASVs using reference databases like SILVA, GTDB, or UNITE. Covers naive Bayes classifiers (DADA2, IDTAXA) and ex…

OpenClawNanoClawDiscovery
FreedomIntelligence/OpenClaw-Medical-SkillsView