Scientist & Thinker Thinking Frameworks
Scientific reasoning and inquiry frameworks from the thinkers who expanded human knowledge — captured as .md skill files.
Scientific thinking is less about having the right answer than about resisting the wrong process. The thinkers in this collection — Richard Feynman's habit of explaining ideas back to himself in the simplest possible terms, Marie Curie's two-decade extraction of radium from tons of pitchblende, Charles Darwin's slow accumulation of observational evidence before publishing, Daniel Kahneman's experimental discovery of how judgement actually works, Leonardo da Vinci's notebooks that treated every domain as one continuous investigation — left behind documented methods of inquiry. Their frameworks are not interchangeable: Feynman teaches by stripping language; Curie teaches by tolerating tedium; Kahneman teaches by trusting evidence over intuition. This collection captures those methods as .md skill files for Claude, ChatGPT, and any LLM. Use them when stress-testing a claim that everyone seems to accept, designing an experiment, or working out whether your own confident reasoning is correctly calibrated.
How scientist & thinkers think
- Feynman technique — explain the idea in plain language until the gap between what you know and what you can say closes
- First principles reasoning — strip a problem to its physical constants, then rebuild the argument from there
- Slow hunches — protect early ideas long enough for evidence to accumulate, but never long enough to fall in love with them
- System 1 and 2 — distinguish the fast intuitive judgement from the slow effortful one and use each where it belongs
- Negative result — treat experiments that disconfirm a hypothesis as worth as much as the ones that confirm it
Frameworks in this category
Richard Feynman
First Principles & Teaching via Curiosity
Albert Einstein
Thought Experiments & Imagination
Charles Darwin
Observation, Patience & Slow Hunches
Carl Sagan
Wonder, Skepticism & Communication
Stephen Hawking
Radical Inquiry Despite Constraints
Carl Jung
Shadow Work, Archetypes & The Self
Sigmund Freud
The Unconscious & Analytical Thinking
Aristotle
Virtue Ethics & Systematic Inquiry
Alan Turing
Computational Thinking & Problem Reduction
Nikola Tesla
Visionary Invention & Pattern Recognition
Isaac Newton
Solitary Genius & Mathematical Rigor
Plato
Dialogue, Forms & The Examined Life
Friedrich Nietzsche
Will to Power & Perspectivism
Bertrand Russell
Logical Rigor & Moral Courage
Socrates
Questioning & Epistemic Humility
Marie Curie
Rigour, Endurance & Uncharted Research
Ada Lovelace
Imagination in Computation & First-Principles Algorithmic Thought
Rosalind Franklin
Rigorous Experimentation & Intellectual Ownership
Hedy Lamarr
Parallel Identities & Inventive Systems Thinking
Rachel Carson
Clear-Eyed Observation & Public Warning
Jane Goodall
Patient Observation & Interspecies Empathy
Katherine Johnson
Mathematical Precision & Quiet Authority
Fei-Fei Li
AI as Scientific Tool & Dataset-First Thinking
Daniel Kahneman
System 1/2 Thinking & Cognitive Bias
Leonardo da Vinci
Curiosity, Notebooks & Cross-Disciplinary Genius
Galileo Galilei
Empirical Courage & Measurement
Michael Faraday
Self-Taught Experimentation & Clarity
James Clerk Maxwell
Unifying Synthesis & Mathematical Elegance
Archimedes
Geometric Intuition & Applied Mechanics
Jennifer Doudna
CRISPR Gene Editing & Scientific Courage
Frances Arnold
Directed Evolution & Bio-Engineering Mindset
Donna Strickland
Laser Physics & Patient Experimentalism
Emmanuelle Charpentier
Collaborative Science & CRISPR Discovery
Geoffrey Hinton
Deep Learning & Neural Network Vision
Yann LeCun
Convolutional Thinking & Open Science
Andrew Ng
AI Pedagogy & Democratising Machine Learning
Demis Hassabis
Games to AGI & Scientific Imagination
Terence Tao
Mathematical Play & Collaborative Rigour
John von Neumann
Game Theory, Computation & Rapid Synthesis
Srinivasa Ramanujan
Intuitive Leaps & Mathematical Mysticism
Kurt Gödel
Incompleteness & Rigorous Self-Reference
John Maynard Keynes
Demand-Side Economics & Pragmatic Stewardship
Milton Friedman
Monetarism & Free-Market Clarity
Esther Duflo
Randomised Trials & Evidence-Based Poverty Work
Thomas Sowell
Economic History & Unsentimental Analysis
Amartya Sen
Capability Approach & Development Ethics
Richard Dawkins
Gene's-Eye View & Confident Materialism
When to use these frameworks
- Stress-testing a confident claim — your own or someone else's — for hidden assumptions
- Designing an experiment, A/B test, or pilot programme where the result has to mean something
- Reading a study and deciding whether its conclusions actually follow from its evidence
- Working through a complex decision where intuition and analysis disagree
- Communicating a technical idea to an audience that doesn't share your background
Start here
Richard Feynman
First Principles & Teaching via Curiosity
Adjacent thinking
Frequently asked questions
Which scientist framework is best for someone outside scientific work?
Feynman and Kahneman. The Feynman technique — explain it in plain language until you can't fudge the bits you don't understand — is the single most portable scientific habit; it works for management decisions, technical writing, and learning anything new. Kahneman's System 1/System 2 framework gives you a vocabulary for noticing when fast intuition is failing you, which applies in any context with high-stakes judgement.
Are these useful for product or business decisions?
Yes. Working backwards from observation rather than forward from belief is the core scientific habit, and it pays off heavily in product work — A/B test design, user research analysis, market sizing, postmortems. Negative-result discipline (the willingness to accept that your hypothesis was wrong) is rare in commercial environments and disproportionately valuable when you can sustain it.
Can these replace formal scientific training or peer review?
No. Real scientific work runs through peer review for a reason — domain experts catch errors no framework will. These frameworks help you think more rigorously about evidence and avoid the most common reasoning mistakes, but they don't substitute for trained methodological judgement in a specific discipline. They're a useful complement to scientific training, not a stand-in for it.
Why include philosophers and economists in a science collection?
The boundary between science and structured thinking is blurrier than the categorisation suggests. Aristotle and Plato established systematic inquiry; Russell brought logical rigour to philosophy; Kahneman and Sen formalised parts of economics into testable claims. The frameworks here are unified by method — careful reasoning under uncertainty — rather than by department. Include them under whichever heading helps you find what you need.
Save when you build a bundle.
Mix and match across categories. 4 for $14.99 (save 25%) or 10 for $29.99 (save 40%).
Browse all 459 frameworks →