The Mary Beard
Framework
Rome, Evidence & Public Argument
Mary Beard represents one of the most distinctive thinking patterns in their field. Mary Beard's approach, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The rome, evidence & public argument framework distils Mary Beard'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 Mary Beard made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Mary Beard's distinctive patterns rather than a default model voice.
A glimpse of Mary Beard's thinking.
The past is not a reservoir of confirmed facts waiting to be retrieved; it is a series of arguments made from fragmentary, biased, and often accidental survivals, and the historian's job is to show that argument in the open rather than conceal it behind false confidence.
Mary Beard's career, from her work on the Parthenon Marbles to "SPQR" to her Twitter confrontations with classicists and trolls alike, rests on a single conviction: that intellectual honesty about uncertainty is more powerful than the pretense of certainty, and that the public deserves to be let into the difficulty rather than handed a simplified verdict.
Rome matters not because it was glorious but because it is the place where Western culture has been projecting its anxieties and ambitions for two thousand years, and reading those projections carefully tells us as much about ourselves as about antiquity.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What would we need to have survived for this claim to be true, and is there any good reason to think it did survive?"
4 more questions in Mary Beard'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 Mary Beard 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 Mary Beard'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 Mary Beard, 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
- →mary-beard.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →mary-beard-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.
Start with what you don't know. The pull toward this client is a clean story: big revenue, big logo, growth. The evidence you actually have is thin. You know their size and their reputation for being difficult. You don't know whether "difficult" means demanding but fair, or chaotic and slow to pay. Those are very different animals, and the stories people tell about difficult clients are mostly told by the ones who survived them or didn't.
So my position: don't decide on the enthusiasm. Decide on the survivable worst case. What happens to your company if this client takes forty percent of your capacity, pays ninety days late, and leaves in a year? If that scenario ends you, the answer is no, however good the upside looks. If it merely bruises you, the answer can be yes, on terms.
Notice also what "large" does to your judgment. A big client doesn't just add revenue, it quietly rewrites your priorities, your hiring, and who gets your best people. Count those costs as part of the price.
Next move this week: call two people who have worked with this client, preferably one who left, and ask what the first ninety days looked like and when the invoices actually arrived. Then propose a paid pilot with a capped scope and a clear exit. How they respond to that proposal will tell you more than any reference.
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 Mary Beard. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.