AIPOCH Medical Research Skills

Add Skills. Run Your Research.

500+ Agent Skills for Medical Research · Evidence Insights · Protocol Design · Data Analysis · Academic Writing

⭐ If you find this repository useful, consider giving it a star! It helps more researchers discover Medical Research Agent Skills and supports the continued development of this library.

💡New: We are launching Awesome ​Med​ Research Skills — a curated collection of medical research Agent Skills, featuring 102 high-quality skills. Each skill embeds professional medical research logic. Explore here.

🤔 What it is?

AIPOCH is a curated library of 500+ Medical Research Agent Skills designed to work with Claude Code, OpenClaw, Hermes Agent and other AI agents.

It supports the research workflow across four core areas: Evidence Insights, Protocol Design, Data Analysis, and Academic Writing.

Equip your AI agent with Medical Research Skills, and turn it into a capable medical research assistant.

AIPOCH also introduces Medical ​Skill Auditor​​— a structured evaluation framework designed to assess the quality of Medical Research Agent Skills. Its core function is to perform a comprehensive quality check on a Skill before it is officially deployed to users. You can view evaluation results for selected AIPOCH skills here.

What is awesome-med-research-skills?

Awesome ​Med Research Skills is a curated collection of medical research Agent Skills, currently including 102 high-quality skills.

We aim to help researchers more effectively organize questions, connect evidence, and advance research. To achieve this, we encode professional medical research logic into these agent skills:

• Literature ​authenticity​​​ constraints​: Implementing hard rules

• ​Research type identification​: We first determine the study type, then execute different logical pathways

• Medical-specific prompt logic

Key Features of Awesome Med Research Skills

🧩 Modular Skill Architecture for Team Scaling

• Skills are composable, replaceable, and extensible, suitable for both individual use and team collaboration

• Can be assembled from single-task execution to multi-step workflow pipelines

🧬 Built for Real Medical Research Scenarios

• Covers real workflows: topic selection, literature search, study design, writing, graphical abstracts, and more

• Not adapted from generic content templates — designed specifically for medical research contexts.

🗂️ Skills Overview

All skills in AIPOCH are ​originally designed and developed in-house​, built to reflect medical research workflows and standards.

The library is primarily organized into five categories: ​Evidence Insights, Protocol Design, ​Data Analysis, Academic Writing​, and Others.

📚Category Highlights

🔍 Evidence Insight e.g., search strategy design, database selection, evidence-level prioritization, critical appraisal, literature synthesis and gap identification.

🧪 Protocol Design e.g., experimental design generation, study type selection, causal inference planning, statistical power calculation, validation strategy.

📊 Data Analysis e.g., R/Python bioinformatics code generation, statistical modeling, data cleaning pipelines, machine learning workflows, result visualization.

✍️ Academic Writing e.g., SCI manuscript drafting, methods/results/discussion writing, meta-analysis narrative, cover letters, abstract generation.

🌍 Other (General / Non-Research) all general skills that do not fall into categories 1–4.

📌 Total Skills in Library: 500+ and growing

🎬 AIPOCH Medical Research Skills — Demo

🚀 How to Start?

⚙️ Requirements

​Host Platform​: OpenClaw (installed and running) or any compatible AI Agent framework that supports Skill integration.

If you don't have OpenClaw,please follow the official OpenClaw setup guide.

​Git​: Required for cloning the repository. Git LFS

🦞 Connect with OpenClaw

Method 1:

I'm a human

curl -sL https://aipoch.com/skill.md > ./skills/aipoch.md

• Run the command to initialize setup

• Select 'OpenClaw' as your target agent

• Follow the prompts to link your library

I'm an agent

Read https://aipoch.com/skill.md and follow the instructions to join Aipoch

• Download the integration guide

• Manually configure your agent's skill path

• Verify the connection in your dashboard

Method 2:

🦞 Install into OpenClaw Plug-in

OpenClaw is a self-hosted AI agent gateway. You can install all AIPOCH skills into OpenClaw with a single command.

macOS / Linux / WSL:

bash <(curl -s https://raw.githubusercontent.com/aipoch/medical-research-skills/main/scientific-skills/scripts/openclaw-install.sh)

Windows (Git Bash):

curl -s https://raw.githubusercontent.com/aipoch/medical-research-skills/main/scientific-skills/scripts/openclaw-install.sh -o /tmp/install.sh
bash /tmp/install.sh

The script will:

• Clone this repository into a temporary directory

• Copy all SKILL.md skill folders into ~/.openclaw/skills/

• Skip any skills that are already installed

After installation, restart your gateway to pick up the new skills:

openclaw gateway restart

Tip: Run with --dry-run first to preview what will be installed without making any changes.

bash <(curl -s https://raw.githubusercontent.com/aipoch/medical-research-skills/main/scientific-skills/scripts/openclaw-install.sh) --dry-run

Note: Skills are installed to ~/.openclaw/skills/ by default (visible to all agents). To install into a specific workspace instead, set the environment variable before running:

OPENCLAW_SKILLS_DIR=~/.openclaw/workspace/skills bash <(curl -s https://raw.githubusercontent.com/aipoch/medical-research-skills/main/scientific-skills/scripts/openclaw-install.sh)

🧠 AIPOCH Medical Skill Auditor

🧩What is Medical Skill Auditor?

Skill Evaluator is a standardized tool designed to assess the quality of Agent Skills. Its core function is to perform a comprehensive quality check on a Skill before it is officially deployed to users.

⚙️How does Medical Skill Auditor Work?

🚫Veto Gates

To enforce strict quality control, Skill Auditor is designed with two layers of veto mechanisms. Any failure in these checks may lead to immediate rejection of a skill.

Skill ​Veto

• Operational Stability

• Structural Consistency

• Result Determinism

• System Security

Research ​Veto

• Scientific Integrity

• Practice Boundaries

• Methodological Ground

• Code Usability

🧰 Core Capability

Evaluates a skill’s design and contract against key dimensions such as Functional Suitability, Reliability, Performance & Context, Agent Usability, Human Usability, Security, Agent-Specific and Maintainability.

📊 Medical Task

Assesses actual outputs of a skill with layered criteria.

For skill testing, the AI automatically generates inputs. The number of inputs in specific categories will increase or decrease depending on the complexity of the skill. The following 7 inputs represent the most comprehensive version.

• Canonical

• Variant A

• Edge

• Variant B

• Stress

• Scope Boundary

• Adversarial

Skill Complexity Classification

Label Code/Rank Definition

Simple S Narrow task scope