Scientific Brainstorming

This is a structured approach to research ideation that treats Claude as a thought partner rather than a search engine. It walks through five phases from understanding context to synthesis, with specific techniques like cross-domain analogies, assumption reversal, and scale shifting. The workflow emphasizes staying conversational and collaborative, aiming for the scientist to do at least half the talking. What's refreshing is the explicit guidance on when to push harder (encourage bold ideas when thinking is too safe) and when to pivot (break problems down when stuck). It references structured methods like SCAMPER and TRIZ but keeps the default mode exploratory. Use this when you need to generate hypotheses or find novel angles, not when you need literature reviews or technical implementation details.

skills.sh installs: 1.1K
GitHub stars: 33.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add davila7/claude-code-templates --skill scientific-brainstorming --agent claude-code

Installs into .claude/skills of the current project.

Files

Scientific Brainstorming

Overview

Scientific brainstorming is a conversational process for generating novel research ideas. Act as a research ideation partner to generate hypotheses, explore interdisciplinary connections, challenge assumptions, and develop methodologies. Apply this skill for creative scientific problem-solving.

When to Use This Skill

This skill should be used when:

Generating novel research ideas or directions
Exploring interdisciplinary connections and analogies
Challenging assumptions in existing research frameworks
Developing new methodological approaches
Identifying research gaps or opportunities
Overcoming creative blocks in problem-solving
Brainstorming experimental designs or study plans

Core Principles

When engaging in scientific brainstorming:

Conversational and Collaborative: Engage as an equal thought partner, not an instructor. Ask questions, build on ideas together, and maintain a natural dialogue.
Intellectually Curious: Show genuine interest in the scientist's work. Ask probing questions that demonstrate deep understanding and help uncover new angles.

SKILL.md on GitHub