cndoin

Med Biostat Skill — AI skill for Claude Code

AI community

Evidence-first bioinformatics & medical research skill for AI agents.

How to install Med Biostat Skill

This entry records only its repository, not the path inside it, so there is no exact command to give. Open cndoin/med-biostat-skill and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Med Biostat Skill does

Evidence-first bioinformatics & medical research skill for AI agents. 41 analysis methods — Mendelian randomization, fine-mapping, single-cell, WGCNA, meta-analysis, causal inference, EWAS, GxE — with algorithms bundled from open-source projects. Runs on Claude Code, Codex and WorkBuddy.

Alternatives in AI

Fine Tuning — ai-research-skills Axolotl, LLaMA-Factory, PEFT, Unsloth 5.4k ★
Deepreasoning — A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning traces with Anthr 5.4k ★
Vllm Mlx — High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon 1.5k ★

README

**An evidence-first workflow skill for bioinformatics and medical research — 41 analysis methods that AI agents can actually run.**

[![Version](https://img.shields.io/badge/version-1.7.0-0d9488)](VERSION) [![License: MIT](https://img.shields.io/badge/License-MIT-8b5cf6.svg)](LICENSE) [![Python 3.9+](https://img.shields.io/badge/python-3.9%2B-2563eb)](#requirements) [![Self-check](https://img.shields.io/badge/self--check-216%20%2F%20219-16a34a)](tests/run_all.py) [![Checks](https://github.com/cndoin/med-biostat-skill/actions/workflows/checks.yml/badge.svg)](https://github.com/cndoin/med-biostat-skill/actions/workflows/checks.yml) [![Agents](https://img.shields.io/badge/agents-Claude%20Code%20%7C%20Codex%20%7C%20WorkBuddy%20%7C%20Cursor-18181b)](#install-into-your-ai-agent)

**English** · [简体中文](README.zh-CN.md) · [日本語](README.ja.md)

[Quick start](#quick-start) · [Analysis methods](#analysis-methods) · [Install into your agent](#install-into-your-ai-agent) · [License](#license)

![biostat-copilot overview](assets/banner.png)

What it is

A **cross-agent research skill** for medical and bioinformatics work. Install it into Claude Code, Codex, or WorkBuddy, and when you ask something like *"analyse this GWAS summary statistics"*, *"is this gene causally linked to cataract"*, or *"double-check whether my results are right"*, it loads **automatically** and runs the analysis inside a fixed methodological framework — instead of letting the model improvise code.

The problem it solves is not "can the AI write the code". It is **caliber** (口径) — the definition a number was computed under.

λGC has two legitimate definitions; mixing them yields two different numbers for the same file.
How missing values are handled changes every downstream concl