OpenClaw Medical Skills

GitHub Stars GitHub Forks GitHub Issues Skills Count License Platform

The largest open-source medical AI skill library for OpenClaw.

869 curated skills Β· Clinical Β· Genomics Β· Drug Discovery Β· Bioinformatics Β· Medical Devices

English | δΈ­ζ–‡

What Is This?

OpenClaw Medical Skills is a curated collection of 869 AI agent skills covering the full spectrum of biomedical and clinical research. These skills are designed for OpenClaw / NanoClaw β€” Claude-based personal AI assistant frameworks β€” and transform a general-purpose AI agent into a powerful medical and scientific research companion.

Each skill is a self-contained module (a SKILL.md file) that:

  • Teaches the agent specialized domain knowledge and workflows
  • Connects to real databases, APIs, and computational tools
  • Produces structured, clinically or scientifically relevant outputs

We benefit from the open-source community. The full collection of resources can be found here: Awesome LLM Resources

Why This Collection Matters

Without Skills With OpenClaw Medical Skills
Generic AI responses about medicine Real PubMed / ClinicalTrials.gov / FDA queries
No bioinformatics capability RNA-seq, scRNA-seq, GWAS, variant calling pipelines
No drug intelligence ChEMBL, DrugBank, DDI prediction, pharmacovigilance
No clinical documentation SOAP notes, discharge summaries, prior auth decisions
No genomics support VCF annotation, ACMG classification, PRS calculation
No regulatory guidance FDA, CE mark, IEC 62304, ISO 14971 compliance

This collection aggregates skills from 12+ open-source skill repositories spanning academic research tools, clinical workflows, regulatory frameworks, and cutting-edge AI-driven protein design β€” giving your AI agent capabilities comparable to a team of specialized research scientists.

Installation

Requirements

  • OpenClaw installed and running, or NanoClaw as an alternative
  • Git (for cloning this repo)

For OpenClaw Users

OpenClaw loads skills from two locations:

Priority Path Scope
High <workspace>/skills/ Per-workspace (recommended)
Low ~/.openclaw/skills/ Global, shared across all agents

Method 1 β€” Clone and Copy (Recommended)

# Clone this repository (skills only β€” skips large data files)
git clone --depth=1 --no-checkout https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills.git
cd OpenClaw-Medical-Skills
git sparse-checkout init --cone
git sparse-checkout set skills
git checkout main

# Install to your workspace skills directory
cp -r skills/* <your-workspace>/skills/

# Or install globally (available to all agents)
cp -r skills/* ~/.openclaw/skills/

Note: Some skills bundle large data files (databases, datasets). The sparse-checkout method above avoids downloading them. If you need the full repo including all data, install Git LFS first, then run git clone https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills.git.

Skills are picked up automatically on the next session. No restart needed.

Method 2 β€” OpenClaw CLI

If you use the OpenClaw plugin registry, you can search and install individual skills from there. For bulk install from this collection, Method 1 is faster.

openclaw plugins install <skill-slug>    # install a single skill
openclaw plugins update                  # update all installed skills

Method 3 β€” Configure Extra Directories

To point OpenClaw at a cloned copy of this repo permanently, add it to ~/.openclaw/openclaw.json:

{
  "plugins": {
    "local": ["/path/to/OpenClaw-Medical-Skills"]
  }
}

This mounts the entire collection without copying files.

Method 4 β€” Install Selected Skills Only

Pick skills relevant to your domain:

# Example: clinical + drug discovery stack
SKILLS=(
  "clinical-reports"
  "tooluniverse-drug-research"
  "tooluniverse-pharmacovigilance"
  "clinicaltrials-database"
  "biomedical-search"
  "tooluniverse-drug-drug-interaction"
)

for skill in "${SKILLS[@]}"; do
  cp -r OpenClaw-Medical-Skills/skills/$skill ~/.openclaw/skills/
done

For NanoClaw Users

NanoClaw loads skills into agent containers at startup from container/skills/.

# Clone and copy into NanoClaw container skills directory
git clone https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills.git
cp -r OpenClaw-Medical-Skills/skills/* /path/to/nanoclaw/container/skills/

# Rebuild the container to apply
cd /path/to/nanoclaw
./container/build.sh

Verification

After installation, ask your agent:

What medical and clinical skills do you have available?

Your agent should list the installed skills with their capabilities.

Skills Overview

Category Count Highlights
General & Core 10 Browser/search, document tools, and developer workflow utilities
Medical & Clinical 119 Clinical reports, CDS, oncology, imaging, and healthcare AI
Scientific Databases 43 Genomics/protein/drug databases and biomedical knowledge retrieval
Bioinformatics (gptomics) 239 Variant analysis, sequencing QC, DE, pathways, single-cell, and epigenomics
Omics & Computational Biology 59 Single-cell/spatial, proteomics, cheminformatics, and protein design tools
ClawBio Pipelines 21 Orchestration pipelines for scRNA, GWAS, ancestry, and structural workflows
BioOS Extended Suite 285 Extended agent suite for oncology, immunology, clinical AI, and infrastructure
Data Science & Tools 93 Statistics, visualization, automation, simulation, and scientific tooling
Total 869

Table of Contents

General & Core

Medical & Clinical

Scientific Databases

Bioinformatics (gptomics bio-* suite)

Omics & Computational Biology

ClawBio Pipelines

BioOS Extended Suite

Data Science & Tools

Skills List

🧰 General & Core

General Tools

Skill Description
agent-browser Browse the web for any task β€” research topics, read articles, interact with web apps, fill forms, take screenshots, extract data, and test web pages. Use whenever a browser would be useful.
find-skills Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities.
multi-search-engine Multi search engine integration with 17 engines (8 CN + 9 Global). Supports Baidu, Bing, 360, Sogou, WeChat, Google, DuckDuckGo, WolframAlpha and more. Supports advanced operators, time filters, site search. No API keys required.
wikipedia-search Search and fetch structured content from Wikipedia using the MediaWiki API for reliable, encyclopedic information. Supports multi-language queries.
deep-research Execute autonomous multi-step deep research on any topic. Searches multiple sources, reads full content, synthesizes findings, and produces a structured report. Use for comprehensive research, literature reviews, competitive analysis, or topic deep-dives.
pdf Comprehensive PDF toolkit β€” extract text and tables, create new PDFs, merge/split documents, handle forms, OCR scanned PDFs. Use when working with any .pdf file.
docx Create, edit, and analyze Word documents (.docx). Supports tracked changes, comments, formatting preservation, and text extraction. Use for drafting, redlining, or extracting content from Word files.
xlsx Spreadsheet creation, editing, and analysis. Supports formulas, formatting, data analysis, and visualization. Use for any .xlsx, .xlsm, .csv, or .tsv task.
pptx Presentation creation, editing, and analysis. Supports layouts, speaker notes, templates, and design. Use for any .pptx file.
doc-coauthoring Guide users through a structured workflow for co-authoring documentation. Use when writing documentation, proposals, technical specs, decision docs, or similar structured content.

πŸ₯ Medical & Clinical

Medical Tools

Skill Description
pubmed-search Search PubMed for scientific literature. Use when the user asks to find papers, search literature, look up research, find publications, or asks about recent studies.
medical-research-toolkit Query 14+ biomedical databases for drug repurposing, target discovery, clinical trials, and literature research. Access ChEMBL, PubMed, ClinicalTrials.gov, OpenTargets, OpenFDA, OMIM, Reactome, KEGG, UniProt, and more through a unified MCP endpoint.
medical-specialty-briefs Generate daily or on-demand medical research briefs for any medical specialty. Searches latest research from top-tier journals (NEJM, Lancet, JAMA, BMJ, Nature Medicine), delivers concise summaries with 1-sentence takeaways and direct links. Use when user asks for medical news, research updates, or specialty-specific updates (endocrinology, cardiology, oncology, neurology, etc.).
usmle Prepare for US medical licensing exams with progress tracking, weak area analysis, question bank management, and residency match planning. Covers Step 1/2 CK/Step 3, IMG-specific guidance, score prediction, and wellbeing support.
medical-entity-extractor Extract medical entities (symptoms, medications, lab values, diagnoses) from patient messages.
patiently-ai Simplifies medical documents for patients. Takes doctor's letters, test results, prescriptions, discharge summaries, and clinical notes and explains them in clear, personalised language.
biomedical-search Complete biomedical information search combining PubMed, preprints, clinical trials, and FDA drug labels. Powered by Valyu semantic search.
medical-imaging-review Write comprehensive literature reviews for medical imaging AI research. Use when writing survey papers, systematic reviews, or literature analyses on imaging topics.
fhir-developer-skill FHIR API development guide for building healthcare endpoints (Patient, Observation, Encounter, Condition, MedicationRequest). Use when developing or integrating FHIR REST APIs.
clinical-trial-protocol-skill Generate clinical trial protocols for medical devices or drugs. Use when designing clinical studies, creating FDA submission documentation, or developing protocols for investigational products.
prior-auth-review-skill Automate payer review of prior authorization (PA) requests. Assesses medical necessity, validates against coverage policies, and generates PA decisions.
clinical-reports Write comprehensive clinical reports β€” case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, CSR), and patient documentation (SOAP, H&P, discharge summaries). HIPAA/FDA/ICH-GCP compliant.
clinicaltrials-database Query ClinicalTrials.gov via API v2. Search trials by condition, drug, location, status, or phase. Retrieve trial details by NCT ID, export data for clinical research and patient matching.
clinical-decision-support Generate clinical decision support (CDS) documents for pharmaceutical and clinical research β€” patient cohort analyses, treatment recommendation reports with GRADE evidence grading, biomarker integration, and statistical outputs (hazard ratios, survival curves).
tooluniverse-clinical-trial-design Strategic clinical trial design feasibility assessment. Evaluates patient population sizing, biomarker prevalence, endpoint selection, comparator analysis, safety monitoring, and regulatory pathways. Use when planning Phase 1/2 trials or assessing trial feasibility.
tooluniverse-disease-research Generate comprehensive disease research reports covering epidemiology, mechanisms, diagnostics, treatments, and ongoing trials. Use when asking about diseases, syndromes, or needing systematic disease analysis.
tooluniverse-literature-deep-research Deep literature research with target disambiguation, evidence grading, and structured theme extraction. Resolves gene/protein IDs, identifies synonyms, synthesizes biological models, and generates testable hypotheses. Use for thorough literature reviews or target profiles.
tooluniverse-clinical-guidelines Search and retrieve clinical practice guidelines from 12+ sources (NICE, WHO, ADA, AHA/ACC, NCCN, SIGN, CPIC, etc.). Covers cardiology, oncology, diabetes, pharmacogenomics, and more. Use when asking about treatment recommendations or standard of care.
tooluniverse-drug-research Comprehensive drug research reports covering identity, pharmacology, targets, clinical trials, safety, pharmacogenomics, and ADMET. Use for drug profiling, safety assessment, or clinical development research.
tooluniverse-drug-repurposing Identify drug repurposing candidates using target-based, compound-based, and disease-driven strategies. Finds new indications for approved drugs by analyzing targets, bioactivity, and safety profiles.
tooluniverse-drug-drug-interaction Drug-drug interaction prediction and risk assessment. Analyzes CYP450/transporter mechanisms, severity classification, and provides management strategies. Supports polypharmacy analysis (3+ drugs) and alternative drug recommendations.
tooluniverse-rare-disease-diagnosis Differential diagnosis for rare diseases based on phenotype and genetic data. Matches symptoms to HPO terms, identifies candidate diseases from Orphanet/OMIM, and interprets variants of uncertain significance.
tooluniverse-pharmacovigilance Analyze drug safety signals from FDA adverse event reports, label warnings, and pharmacogenomic data. Calculates PRR/ROR, identifies serious adverse events, and assesses pharmacogenomic risk.
tooluniverse-clinical-trial-matching Patient-to-trial matching for precision medicine and oncology. Ranks trials from ClinicalTrials.gov by molecular eligibility, clinical criteria, biomarker alignment, and geographic feasibility with a quantitative Trial Match Score (0-100).
literature-review Systematic literature reviews across multiple databases (PubMed, arXiv, bioRxiv, Semantic Scholar). Produces professionally formatted reports with verified citations in APA, Nature, Vancouver styles.
tooluniverse-precision-oncology Actionable treatment recommendations for cancer patients based on molecular profile. Interprets tumor mutations, identifies FDA-approved therapies, clinical trials, and resistance mechanisms.
tooluniverse-cancer-variant-interpretation Clinical interpretation of somatic mutations in cancer. Given gene+variant (e.g., EGFR L858R, BRAF V600E), assesses oncogenicity, therapeutic implications, and trial eligibility.
tooluniverse-variant-analysis Production-ready VCF processing, variant annotation, and mutation analysis. Parses VCF files, annotates with ClinVar/gnomAD/COSMIC, and interprets clinical significance.
tooluniverse-variant-interpretation Systematic clinical variant interpretation from raw calls to ACMG-classified recommendations. Aggregates evidence from ClinVar, gnomAD, literature, and population databases.
tooluniverse-structural-variant-analysis Comprehensive structural variant (SV/CNV) analysis for clinical genomics. Classifies SVs, assesses pathogenicity, and interprets copy number alterations.
tooluniverse-polygenic-risk-score Build and interpret polygenic risk scores (PRS) for complex diseases using GWAS summary statistics. Calculates genetic risk profiles and interprets PRS percentiles.
tooluniverse-precision-medicine-stratification Patient stratification for precision medicine by integrating genomic, clinical, and therapeutic data. Identifies treatment-relevant subgroups and biomarker-driven therapy options.
tooluniverse-gwas-trait-to-gene Discover genes associated with diseases and traits using GWAS Catalog (500k+ associations) and Open Targets Genetics locus-to-gene predictions.
tooluniverse-gwas-drug-discovery Transform GWAS signals into drug targets and repurposing opportunities. Performs locus-to-gene mapping, druggability assessment, and existing drug identification.
tooluniverse-gwas-study-explorer Compare GWAS studies and assess replication across cohorts. Integrates NHGRI-EBI GWAS Catalog and Open Targets Genetics for cross-study meta-analysis.
tooluniverse-gwas-finemapping Identify and prioritize causal variants at GWAS loci using statistical fine-mapping. Computes posterior probabilities and credible sets for causal variant identification.
tooluniverse-gwas-snp-interpretation Interpret SNPs from GWAS studies by aggregating evidence from GWAS Catalog, Open Targets Genetics, and ClinVar. Retrieves variant-trait associations and functional annotations.
tooluniverse-phylogenetics Phylogenetics and sequence analysis β€” alignment processing, evolutionary tree construction, and evolutionary metrics for pathogens or species.
tooluniverse-epigenomics Epigenomics data processing β€” methylation array analysis (CpG filtering, differential methylation), chromatin accessibility, and histone modification analysis.
tooluniverse-rnaseq-deseq2 RNA-seq differential expression analysis using PyDESeq2. Performs normalization, dispersion estimation, Wald testing, LFC shrinkage, and pathway enrichment.
tooluniverse-single-cell Single-cell RNA-seq analysis using scanpy. Performs QC, normalization, PCA, UMAP, Leiden clustering, trajectory analysis, and cell type annotation.
tooluniverse-spatial-transcriptomics Spatial transcriptomics data analysis β€” maps gene expression in tissue architecture. Supports 10x Visium, MERFISH, seqFISH, and Slide-seq platforms.
tooluniverse-spatial-omics-analysis Computational analysis for spatial multi-omics data integration β€” spatially variable genes, domain annotation, and tissue-resolved omics.
tooluniverse-proteomics-analysis Mass spectrometry proteomics analysis β€” protein quantification, differential expression, PTMs, and protein-protein interaction network construction.
tooluniverse-metabolomics Metabolomics research β€” identifies metabolites and searches databases (HMDB 220k+ metabolites, MetaboLights, Metabolomics Workbench).
tooluniverse-metabolomics-analysis Metabolomics data analysis β€” metabolite identification, quantification, pathway analysis, and metabolic flux from LC-MS, GC-MS, or NMR data.
tooluniverse-multi-omics-integration Integrate transcriptomics, proteomics, epigenomics, genomics, and metabolomics for systems biology and precision medicine.
tooluniverse-multiomic-disease-characterization Systems-level disease characterization integrating genomics, transcriptomics, proteomics, pathway, and therapeutic layers.
tooluniverse-expression-data-retrieval Retrieve gene expression and omics datasets from ArrayExpress and BioStudies with quality assessment and structured reports.
tooluniverse-gene-enrichment Gene enrichment and pathway analysis using gseapy, PANTHER, STRING, Reactome. Supports GO enrichment, KEGG pathways, and 40+ ToolUniverse tools.
tooluniverse-systems-biology Systems biology and pathway analysis using Reactome, KEGG, WikiPathways, Pathway Commons, and BioModels. Network modeling and pathway simulation.
tooluniverse-protein-interactions Protein-protein interaction network analysis using STRING, BioGRID, and SASBDB. Maps interaction networks with confidence scores and functional modules.
tooluniverse-protein-structure-retrieval Retrieve protein structure data from RCSB PDB, PDBe, and AlphaFold with quality assessment and comprehensive structural profiles.
tooluniverse-protein-therapeutic-design Design novel protein therapeutics (binders, enzymes, scaffolds) using AI-guided de novo design β€” RFdiffusion, ProteinMPNN, and ESM.
tooluniverse-antibody-engineering Antibody engineering and optimization for therapeutics β€” humanization, affinity maturation, developability assessment, and immunogenicity prediction.
tooluniverse-immune-repertoire-analysis TCR/BCR repertoire analysis from sequencing data β€” clonality, diversity, V(D)J gene usage, clonal expansion, and antigen specificity prediction.
tooluniverse-immunotherapy-response-prediction Predict patient response to immune checkpoint inhibitors using multi-biomarker integration β€” TMB, MSI, PD-L1, TIL signatures, and HLA typing.
tooluniverse-infectious-disease Pathogen characterization and drug repurposing for infectious disease outbreaks. Identifies taxonomy, essential proteins, structural targets, and treatment options.
tooluniverse-crispr-screen-analysis CRISPR screen analysis for functional genomics β€” pooled or arrayed screens (knockout/activation/interference) to identify essential genes and hits.
tooluniverse-target-research Comprehensive biological target intelligence β€” protein info, structure, interactions, pathways, expression, variant landscape, and drug pipeline.
tooluniverse-network-pharmacology Compound-target-disease network analysis for drug repurposing, polypharmacology discovery, and systems pharmacology.
tooluniverse-statistical-modeling Statistical modeling on biomedical datasets β€” linear/logistic regression, mixed-effects models, survival analysis, and Bayesian methods.
tooluniverse-image-analysis Biomedical microscopy image analysis β€” colony morphometry, cell counting, fluorescence quantification, and statistical comparison of imaging data.
literature-search Comprehensive scientific literature search across PubMed, arXiv, bioRxiv, medRxiv using natural language queries powered by Valyu semantic search.
medrxiv-search Search medRxiv medical preprints with natural language queries powered by Valyu semantic search.
clinical-trials-search Search ClinicalTrials.gov with natural language queries β€” find trials by condition, enrollment status, and outcomes via Valyu.
drug-discovery-search End-to-end drug discovery platform combining ChEMBL, DrugBank, targets, and FDA labels via natural language Valyu search.
drug-labels-search Search FDA drug labels with natural language queries β€” indications, dosing, and safety data via Valyu.
chembl-search Search ChEMBL bioactive molecules database β€” compounds, assay data, and bioactivity via Valyu semantic search.
open-targets-search Search Open Targets drug-disease associations and target validation via Valyu semantic search.
patents-search Search global patents with natural language queries β€” prior art, patent landscapes, and innovation tracking via Valyu.
drugbank-search Search DrugBank comprehensive drug database β€” mechanisms, interactions, and safety data via Valyu semantic search.
arxiv-search Search arXiv preprints (biology, medicine, AI) using natural language queries powered by Valyu semantic search.
gwas-database Query NHGRI-EBI GWAS Catalog for SNP-trait associations by rs ID, disease/trait, or gene. Retrieve p-values and summary statistics for genetic epidemiology.
scikit-survival Survival analysis and time-to-event modeling in Python β€” Kaplan-Meier, Cox regression, log-rank tests, and censored data handling using scikit-survival.

Drug Safety & Chemical Biology

Skill Description
tooluniverse-adverse-event-detection Detect and analyze adverse drug event signals using FDA FAERS data, drug labels, disproportionality analysis (PRR, ROR, IC), and biomedical evidence. Generates quantitative safety signal scores (0-100).
tooluniverse-binder-discovery Discover novel small molecule binders for protein targets using structure-based and ligand-based approaches. Creates actionable reports with candidate compounds, ADMET profiles, and synthesis feasibility.
[tooluniverse-chemical-compound-retrieval](