SkillAgentSearch skills...

OpenClaw Medical Skills

The largest open-source medical AI skills library for OpenClaw🦞.

Install / Use

npx skills add FreedomIntelligence/OpenClaw-Medical-Skills

Installs into whichever agent you are using.

About this skill

Quality Score

0/100

Supported Platforms

Claude Code
Claude Desktop

README

OpenClaw Medical Skills

<div align="center">

GitHub Stars GitHub Forks GitHub Issues Skills Count License Platform

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

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

English | 中文

</div>

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 — Claude-based personal AI assistant frameworks — 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 — 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 — Clone and Copy (Recommended)

# Clone this repository (skills only — 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 — 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 — 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 — 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

Related Skills

View on GitHub
GitHub Stars2.9k
CategoryDevelopment
Updated4h ago
Forks410

Languages

Python

Security Score

85/100

Audited on Aug 8, 2026

No findings