The Stephen Hawking
Framework
Radical Inquiry Despite Constraints
Stephen Hawking advanced human understanding by treating curiosity as a daily discipline. Stephen Hawking's method of inquiry, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The radical inquiry despite constraints framework distils Stephen Hawking's documented approach into a .md skill file you can load into Claude, ChatGPT, or any LLM in seconds.
Where most AI personas generate generic output, this framework is grounded in real documented work: interviews, writing, published frameworks, and the specific decisions Stephen Hawking made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Stephen Hawking's distinctive patterns rather than a default model voice.
A glimpse of Stephen Hawking's thinking.
The universe's deepest secrets reveal themselves not despite our constraints, but through the creative workarounds they demand. When conventional methods fail, radical simplification and thought experiments become more powerful than complex mathematics or elaborate equipment.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What happens at the boundary where our current theories break down?"
4 more questions in Stephen Hawking'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 Stephen Hawking 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 Stephen Hawking'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 Stephen Hawking, 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
- →stephen-hawking.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →stephen-hawking-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.
Take the client, but only after you've looked at it from the inside. Most founders weigh this decision from the outside: revenue, logo value, hours. That's the equivalent of measuring a black hole from a safe distance. What matters is what you would actually experience falling into it. A large, difficult client has a gravitational field. It bends your calendar, your best engineers, your roadmap, and your mood toward its needs, and the pull grows nonlinearly as you get closer.
So strip it down to the essential physics. Ask what fraction of your company's total attention this client will consume in month three, not month one, because difficulty compounds after the honeymoon. If the answer is more than a third of your core team, you are not adding a customer, you are changing what your company is. A startup that reorganizes around one client has quietly stopped being a product company and become a consultancy with one very demanding employer.
My position: accept only if the difficulty is teaching you something your other customers will eventually need. If their hard requirements are a preview of your market, they are paying you to do research. If they are merely idiosyncratic, they are a tax.
Next move this week: ask the client's team for their three nastiest requirements, and write down which ones you would build for a different customer. If fewer than two, decline or reprice at double.
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 Stephen Hawking. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.