hypogenic
Automated hypothesis generation and testing using large language models. Use this skill when generating scientific hypotheses from datasets, combining literature insights with empirical data, testing hypotheses against observational data, or conducting systematic hypothesis exploration for research discovery in domains like deception detection, AI content detection, mental health analysis, or other empirical research tasks.
npx skills add FreedomIntelligence/OpenClaw-Medical-Skills --skill hypogenic --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Hypogenic enables automated hypothesis generation and testing using large language models. It supports three approaches: HypoGeniC (data-driven), HypoRefine (literature and data integration), and Union methods (mechanistic combination of literature and data-driven hypotheses). It facilitates generating hypotheses from observational data, integrating literature insights, and running inference on generated hypotheses through a CLI and a Python API.
How it works
The skill exposes three core workflows:
- HypoGeniC: start with a data subset, generate candidate hypotheses, iteratively refine them based on performance, and replace weak hypotheses from challenging examples.
- HypoRefine: extract insights from papers (typically ~10 papers), generate theory-grounded hypotheses from literature, generate data-driven hypotheses from data, and refine both banks iteratively.
- Union Methods: combine literature-only hypotheses with outputs from HypoGeniC or HypoRefine to achieve broader coverage and reduced redundancy.
Installation and usage are via CLI commands and a Python API:
- CLI: hypogenic_generation and hypogenic_inference with prompts, model options, and dataset paths.
- Python API: BaseTask(config_path, extract_label) with methods generate_hypotheses(method, num_hypotheses) and inference(hypothesis_bank, test_data).
Key features include support for API-based or local LLMs, Redis caching, parallel processing, template-based prompts, and configurable extraction logic for domain-specific labels.
When to use it
Use when you need to:
- Generate scientific hypotheses from observational data
- Systematically test multiple competing hypotheses
- Combine literature insights with empirical patterns
- Accelerate research discovery in domains like deception detection, AI content detection, mental health indicators, or other empirical tasks.
What it can touch
- Tools: claude-code (declared)
- CLI and Python API access to hypothesis generation and inference.
- Optional dependencies mentioned: Redis (caching), s2orc-doc2json (literature PDFs), GROBID (PDF preprocessing).
Caveats
- The description lists dependencies and workflows but does not provide guarantees about accuracy or outcomes.
- Requires external datasets and configuration (config.yaml, dataset JSON formats) to operate.
- Literature processing requires setting up GROBID and processing PDFs as described.
# Hypogenic ## Overview Hypogenic provides automated hypothesis generation and testing using large language models to accelerate scientific discovery. The framework supports three approaches: HypoGeniC (data-driven hypothesis generation), HypoRefine (synergistic literature and data integration), and Union methods (mechanistic combination of literature and data-driven hypotheses). ## Quick Start Get started with Hypogenic in minutes: ```bash # Install the package uv pip install hypogenic # Clone example datasets git clone https://github.com/ChicagoHAI/HypoGeniC-datasets.git ./data # Run basic hypothesis generation hypogenic_generation --config ./data/your_task/config.yaml --method hypogenic --num_hypotheses 20 # Run inference on generated hypotheses hypogenic_inference --config ./data/your_task/config.yaml --hypotheses output/hypotheses.json ``` **Or use Python API:** ```python from hypogenic import BaseTask # Create task with your configuration task = BaseTask(config_path="./data/your_task/config.yaml") # Generate hypotheses task.generate_hypotheses(method="hypogenic", num_hypotheses=20) # Run inference results = task.inference(hypothesis_bank="./output/hypotheses.json") ``` ## Whe
- Overview
- Quick Start
- When to Use This Skill
- Key Features
- Core Capabilities
- 1. HypoGeniC: Data-Driven Hypothesis Generation
- 2. HypoRefine: Literature and Data Integration
- 3. Union Methods
- Installation
- Dataset Format
- Configuration
- Literature Processing (HypoRefine/Union Methods)
- CLI Usage
- Hypothesis Generation
Install the package uv pip install hypogenic Clone example datasets git clone https://github.com/ChicagoHAI/HypoGeniC-datasets.git ./data Run basic hypothesis generation hypogenic_generation --config ./data/your_task/config.yaml --method hypogenic --num_hypotheses 20 Run inference on generated hypotheses hypogenic_inference --config ./data/your_task/config.yaml --hypotheses output/hypotheses.json For HypoGeniC examples For HypoRefine/Union examples
What does the hypogenic skill do?
Automated hypothesis generation and testing using large language models. Use this skill when generating scientific hypotheses from datasets, combining literature insights with empirical data, testing hypotheses against observational data, or conducting systematic hypothesis exploration for research discovery in domains like deception detection, AI content detection, mental health analysis, or other empirical research tasks.
How do I install it?
Run `npx skills add FreedomIntelligence/OpenClaw-Medical-Skills --skill hypogenic --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From FreedomIntelligence/OpenClaw-Medical-Skills, a repository with 2,909 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.