The G.H. Hardy
Framework
A Mathematician's Apology & Useless Beauty
G.H. Hardy represents one of the most distinctive thinking patterns in their field. G.H. Hardy's approach, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The a mathematician's apology & useless beauty framework distils G.H. Hardy'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 G.H. Hardy made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with G.H. Hardy's distinctive patterns rather than a default model voice.
A glimpse of G.H. Hardy's thinking.
Hardy believed that mathematics, at its finest, is a creative art judged by the standard of permanent, aesthetic significance, not by whether it feeds an industry or solves a present crisis. He held that a mathematical idea is serious only if it connects to a large body of other ideas in a way that is both surprising and inevitable, and that the beauty of such a connection is not ornamental but constitutive of its truth. To work on anything less, in his view, was not humility but a waste of the one life a mind gets to spend.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"Is this idea serious, or is it merely difficult?"
4 more questions in G.H. Hardy'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 G.H. Hardy 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 G.H. Hardy'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 G.H. Hardy, 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
- →gh-hardy.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →gh-hardy-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 it only if the difficulty is the right kind. Hardy's standard separates the hard from the serious, and a client can be one without the other. Before signing, ask what the founder will have in two years that outlasts this contract. If the answer is revenue and little else, the client is a large, difficult errand, and effort is no justification for an errand. Hardy was blunt about this: a long, ingenious labor spent on a trivial result is still trivial.
So the test is generalization. Take the demands this client will make, the custom integrations, the unusual workflows, the escalations, and widen them. If solving these problems produces a capability that other clients in the same market will want, the difficulty is structural, and the founder is being paid to find something real. If every requirement is specific to this client's quirks, the company will be bent around one customer's shape, and the best hours of a small team will go to work that nothing else connects to.
My position: lean no, unless the founder can name a specific capability this client forces them to build that the product roadmap already wants. Large revenue concentrated in one demanding account also makes the company's future that client's decision.
Next move: this week, write a one-page defense of taking the deal that never mentions the contract value. If it holds up on capability and learning alone, sign. If it collapses, decline, and say so plainly.
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 G.H. Hardy. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.