LabClaw – Operating Layer for LabOS (Stanford-Princeton AI Co-Scientists)

LabClaw is a skill library, not a monolithic software package. You can install the full collection or copy only the skill folders that match your research workflows.

---

Overview

LabClaw packages 240 production-ready SKILL.md files for biomedical AI workflows across biology, lab automation, vision/XR, drug discovery, medicine, data science, literature research, and scientific visualization. Each skill teaches an OpenClaw-compatible agent when to use a tool, how to call it, and what kind of output to produce.

The collection is designed for researchers who want a practical, modular skill layer instead of a generic prompt bundle. You can use it as a broad starter library, or cherry-pick only the subfolders relevant to your lab, team, or project.

At a Glance

Representative Workflows

3-Second Quick Start

Just send the message to OpenClaw:

install https://github.com/wu-yc/LabClaw

Use Cases

In Lab (with XR):

Repository Layout

LabClaw/
├── README.md
├── README.zh-CN.md
└── skills/
    ├── bio/          # 86 skills: genomics, proteomics, single-cell, systems biology, databases
    ├── vision/       # 5 skills: hand tracking, 3D pose, segmentation, egocentric
    ├── pharma/       # 36 skills: cheminformatics, docking, target discovery, pharmacology
    ├── med/          # 22 skills: clinical research, precision medicine, oncology, imaging
    ├── general/      # 54 skills: statistics, ML, writing, reproducibility, quality control
    ├── literature/   # 33 skills: search, databases, grants, patents, citations
    └── visualization/ # 4 skills: scientific visualization, matplotlib, seaborn, plotly

Related Repositories

These projects are especially relevant if you want to place LabClaw in the broader biomedical-agent ecosystem:

Full Skill Catalog

The original catalog is preserved below, but grouped into collapsible sections to make browsing easier on GitHub.

---

---

Skill Format

Every SKILL.md follows a consistent structure:

# Skill Name
## Overview        — what this skill enables
## When to Use     — trigger conditions for the AI agent
## Key Capabilities — specific tools, APIs, parameters
## Usage Examples  — concrete code or workflow examples

Credits

Skills curated by Yingcheng (Charles) Wu, Jinglin Jian, Zhe Zhao at Le Cong Lab of Stanford & Mengdi Wang Lab at Princeton.

We really thank K-Dense for the support.

License

MIT License

Star History