hypothesis-generation
Structured hypothesis formulation from observations. Use when you have experimental observations or data and need to formulate testable hypotheses with predictions, propose mechanisms, and design experiments to test them. Follows scientific method framework. For open-ended ideation use scientific-brainstorming; for automated LLM-driven hypothesis testing on datasets use hypogenic.
Author
Category
Business AnalysisInstall
Download and extract to your skills directory
Copy command and send to AI Agent for auto-install:
Scientific Hypothesis Generation — hypothesis-generation
Skill Overview
The scientific hypothesis generation skill provides researchers and data analysts with a systematic framework for formulating hypotheses. Starting from experimental observations and data, it generates testable scientific hypotheses, designs validation experiments, explores competing explanations, and supports complete LaTeX report writing and visualization generation.
Use Cases
1. Research Data Analysis and Hypothesis Formulation
When you have experimental data or observational results and need to convert them into verifiable scientific hypotheses, this skill—through literature synthesis and systematic analysis—helps you discover patterns from the data, propose mechanistic explanations, and generate a hypothesis framework that meets scientific methodology standards.
2. Experimental Design and Hypothesis Testing
When you need to design experiments to validate a research question, this skill offers multiple experimental design patterns (including laboratory experiments, observational studies, clinical trials, etc.). It helps you formulate testable predictions, select appropriate control groups, identify potential confounders, and evaluate sample sizes and statistical methods.
3. Multiple-Hypothesis Evaluation and Mechanism Exploration
When a research phenomenon has multiple possible explanations, this skill helps you generate 3–5 competing hypotheses and evaluate their quality across dimensions such as falsifiability, parsimony, and explanatory power. It also designs experiments to distinguish between different hypotheses, making it especially suitable for mechanism studies and interdisciplinary exploration.
Core Capabilities
1. Systematic Hypothesis Generation Workflow
This capability provides a complete scientific methodology framework, from understanding the phenomenon, conducting literature searches, and synthesizing evidence, to generating multiple competing hypotheses. Each hypothesis includes a mechanistic explanation, supporting evidence, and core assumptions, and supports quality assessment (testability, falsifiability, parsimony, etc.), ensuring that the generated hypotheses meet research standards.
2. Experiment Design and Prediction Formulation
For each hypothesis, this capability designs concrete validation experiments, including multiple modes such as laboratory experiments (in vitro/in vivo/computational), observational studies (cross-sectional/longitudinal/case-control), and clinical trials. It also generates quantitative, testable predictions that clearly specify expected results, validation conditions, and observations that could falsify the hypotheses.
3. Professional Reporting and Visualization Support
This capability generates a LaTeX template for professional hypothesis reports, including a 4-page main text with color-coded organization and a detailed appendix. It supports 50+ reference citations and integrates the scientific-schematics skill to automatically generate high-quality visualizations such as mechanism diagrams, experimental workflow charts, and prediction decision trees, directly suitable for academic publication.
Frequently Asked Questions
How can I generate scientific hypotheses from experimental observation data?
This skill follows a systematic process: first clarify your observed phenomenon and the boundary of its scope, then conduct a literature search (supporting PubMed and general scientific literature search) to synthesize existing evidence. Next, generate 3–5 competing hypotheses (each provides a mechanistic explanation rather than a simple description). Finally, evaluate the quality of the hypotheses and design validation experiments. The entire process is based on a scientific methodology framework to ensure testability and falsifiability.
How do I assess the strengths and weaknesses of multiple competing hypotheses?
This skill evaluates hypothesis quality across six dimensions: testability (whether it can be verified experimentally), falsifiability (what observations would overturn it), parsimony (whether it is the simplest explanation), explanatory power (how many phenomena it can explain), scope (how broadly it covers observations), and consistency (whether it aligns with established principles). Each hypothesis clearly marks its advantages and limitations and designs specific experiments to distinguish competing hypotheses.
How are hypothesis reports written and visualized?
This skill provides complete LaTeX templates and style packages to generate a professional report. The report includes a 4-page main text organized with color-coded structure (executive summary, competing hypotheses, testable predictions, key comparisons) and a detailed appendix (literature review, experimental design, quality assessment, and supplementary evidence). The report supports 50+ reference citations and integrates the scientific-schematics skill to automatically generate high-quality figures such as mechanism diagrams and experimental workflow charts. It outputs professional documentation that meets academic publication standards.