The Richard Feynman
Framework
First Principles & Teaching via Curiosity
Richard Feynman won a Nobel Prize in physics, played samba in Rio, cracked safes at Los Alamos, and drew nude portraits — and treated each pursuit with identical curiosity. His signature claim was that you cannot claim to understand something until you can explain it simply. This framework captures the Feynman Technique, his protocol against self-deception, and the play-as-engine principle that let him regenerate the curiosity required to solve genuinely hard problems.
A glimpse of Richard Feynman's thinking.
There is a vast difference between knowing the name of something and knowing something. Most "expertise" is fluency in vocabulary masquerading as understanding. The only honest test is whether you can explain the idea in simple terms, from the ground up, without leaning on the jargon. If you can't, you don't understand it — you've just memorised the labels.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
What do I actually understand here, versus just know the words for?
4 more questions in Richard Feynman's voice are unlocked with purchase.
Full list of anti-patterns unlocked with purchase.
The full framework adds: detailed explanations of all five mental models with real-world examples, the decision heuristics Richard Feynman actually used, remaining signature questions, the complete list of anti-patterns, a copy-paste activation prompt, and a worked example.
Unlocked the moment you purchase. ~2,000 words total. Delivered as a Claude Skill and plain .md within 60 seconds of checkout.
- ✦Core philosophy: 2–3 sentences grounded in Richard Feynman's documented worldview
- ✦Five signature mental models: each named, with concrete examples from their work
- ✦Decision heuristics: the concrete rules they actually used
- ✦Signature questions: five questions that sound like Richard Feynman, not a generic MBA
- ✦What they would NOT do: the anti-patterns this framework rejects
- ✦Copy-paste activation prompt: drop straight into Claude or ChatGPT
- ✦Worked example: the framework applied to a realistic scenario
- →richard-feynman.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →richard-feynman-framework.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
What it does with a real question.
A founder is deciding whether to take a large but difficult client.
Don't decide yet; run the cheap experiment first. "Large but difficult" is two labels, not two facts, and a decision made on labels is the easiest kind to fool yourself with. Large is only good if the revenue arrives and the margin survives. Difficult only matters if you can say what the difficulty actually is. Is it scope that keeps moving? A buyer who pays late? Demands your team can't meet without dropping everyone else? Each of those has a different mechanism and a different price.
Here's the trap: you want the big logo, and a founder who wants something is superb at collecting evidence for it. So flip it. Assume this client will hurt you, and ask what the specific failure would look like in month three. Maybe one engineer gets consumed, payment slips to ninety days, and your other clients quietly get worse service. Now ask whether you could survive that version of the story. If a single client above roughly a third of your revenue could sink you when they leave or squeeze you, that's your answer, no matter how flattering the contract looks.
The next move is small and fast. Offer a paid, tightly scoped pilot of four to six weeks with written deliverables and a payment schedule up front. Watch how they handle the boundaries. Their behavior in that window will tell you more than any amount of speculation in a conference room.
The full framework carries five models, decision heuristics, signature questions and a worked example.
Written by claude-sonnet-5-5 with this framework loaded, 2026-10-11. Checked automatically for length and for copied framework text.
Save up to 40% with a bundle
Works as a Claude Skill (.zip) and as a plain .md for ChatGPT, Gemini & every LLM
Delivered to your email within 60 seconds · Secured by Stripe
Price includes UK VAT where applicable
Inspired by the documented thinking of Richard Feynman. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.