The Marie Curie
Framework
Rigour, Endurance & Uncharted Research
Marie Curie advanced human understanding by treating curiosity as a daily discipline. Marie Curie's method of inquiry, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The rigour, endurance & uncharted research framework distils Marie Curie'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 Marie Curie made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Marie Curie's distinctive patterns rather than a default model voice.
A glimpse of Marie Curie's thinking.
True discovery requires isolating variables others cannot see, then subjecting them to relentless measurement until patterns emerge. The work itself—not recognition—validates the path, and precision compounds over time into insights that reshape entire fields.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What measurement would definitively prove or disprove this hypothesis?"
4 more questions in Marie Curie'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 Marie Curie 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 Marie Curie'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 Marie Curie, 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
- →marie-curie.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →marie-curie-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 on the size of the contract; decide on what the difficulty is made of. "Large but difficult" is a mixture, and a mixture can be separated. Until you've done that, you're choosing on noise.
Take the difficulty apart one variable at a time. Is it the scope, which keeps shifting? The people, who are slow to decide or hostile to your team? Payment behavior? Or technical demands that stretch you but would make you better? These are different problems with different prices. A hard client who pays on time and defines success clearly is an expensive education. A client who disputes invoices is a slow leak that no revenue figure justifies.
Here is where I land. Take it only if you can name the specific source of difficulty and show it is bounded. Unbounded difficulty, where the client's behavior is the unknown, will consume your best people for a year and leave you with a revenue line you cannot afford to lose. Concentration risk plus unpredictability is how founders end up working for one customer.
The concrete next move: before signing, run a paid, small, time-limited pilot, four to six weeks, with written success criteria. Measure what happens at the edges: how fast they respond, how they handle a missed deadline, whether they pay the first invoice cleanly. If the pilot reveals the difficulty is bounded, scale up with confidence. If it reveals chaos, you learned that for the price of a pilot, not a year.
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
Ten builders whose methods outlasted the rooms that doubted them
Get Marie Curie plus nine more for $29.99 →Inspired by the documented thinking of Marie Curie. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.