OpenSkillIndex← back to search
openclawclaude-codescience

OpenClaw-Medical-Skills medea-therapeutic-discovery

An AI agent for therapeutic discovery that executes transparent, multi-step omics analyses including research planning, code execution, and literature reasoning.

install
source · Clone the upstream repo
git clone https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/medea-therapeutic-discovery" ~/.claude/skills/freedomintelligence-openclaw-medical-skills-medea-therapeutic-discovery && rm -rf "$T"
OpenClaw · Install into ~/.openclaw/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills "$T" && mkdir -p ~/.openclaw/skills && cp -r "$T/skills/medea-therapeutic-discovery" ~/.openclaw/skills/freedomintelligence-openclaw-medical-skills-medea-therapeutic-discovery && rm -rf "$T"
manifest: skills/medea-therapeutic-discovery/SKILL.md
tags
#omics-analysis#drug-target-discovery#literature-reasoning#research-planning#code-execution
source content

Medea Therapeutic Discovery Agent

Medea is a multi-stage AI agent designed for therapeutic discovery, modeled after 2026 state-of-the-art open source architectures. It executes transparent, multi-step omics analyses.

When to Use This Skill

  • "Run multi-omics therapeutic discovery pipeline"
  • "Analyze omics data for novel drug targets using Medea"
  • "Perform literature reasoning and consensus reconciliation for target X"

Core Capabilities

  1. Research Planning: Formulates step-by-step omics analysis plans.
  2. Code Execution: Generates and executes Python/R scripts for data processing.
  3. Literature Reasoning: Retrieves and synthesizes current literature.
  4. Consensus Stage: Reconciles experimental evidence with literature to propose high-confidence targets.

Workflow

  1. Step 1: Initialize Medea agent with target disease or omics dataset.
  2. Step 2: Execute the multi-stage pipeline across planning, coding, literature review, and consensus validation.

Example Usage

User: "Run Medea analysis on the provided breast cancer multi-omics dataset."

Agent Action:

python3 -m medea.agent --dataset breast_cancer_omics.h5ad --mode full_discovery