Hypothesis Generation

This is for generating testable scientific hypotheses with proper rigor. It walks you through a structured process: literature search (PubMed for biomedical, general search for other domains), synthesizing evidence, generating 3-5 competing mechanistic explanations, evaluating them against quality criteria like falsifiability and parsimony, then designing experiments to test them. The output is a LaTeX report with color-coded boxes for hypotheses and predictions, capped at 4 pages with detailed appendices. One notable requirement: you must generate at least 1-2 scientific schematics using AI-generated diagrams. It's opinionated about structure, which is either helpful scaffolding or constraining depending on whether you want that level of prescribed workflow.

skills.sh installs: 396
GitHub stars: 33.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add davila7/claude-code-templates --skill hypothesis-generation --agent claude-code

Installs into .claude/skills of the current project.

Files

Scientific Hypothesis Generation

Overview

Hypothesis generation is a systematic process for developing testable explanations. Formulate evidence-based hypotheses from observations, design experiments, explore competing explanations, and develop predictions. Apply this skill for scientific inquiry across domains.