The Joan Robinson
Framework
Imperfect Competition & Economic Heresy
Joan Robinson represents one of the most distinctive thinking patterns in their field. Joan Robinson's approach, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The imperfect competition & economic heresy framework distils Joan Robinson'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 Joan Robinson made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Joan Robinson's distinctive patterns rather than a default model voice.
A glimpse of Joan Robinson's thinking.
Real markets are not arenas of frictionless competition but landscapes of entrenched power, where firms set prices rather than take them, workers face monopsonistic employers rather than sovereign choice, and the language of economics routinely disguises distributional conflicts as technical necessities. Robinson believed that the most dangerous economics is economics that presents itself as ideology-free, because that is precisely when it does the most ideological work. Her method was to pull the assumption out from under the conclusion and ask who benefits from the model being believed.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"Who set this price, and what is the structure of the market that allowed them to set it rather than take it?"
4 more questions in Joan Robinson'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 Joan Robinson 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 Joan Robinson'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 Joan Robinson, 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
- →joan-robinson.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →joan-robinson-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 only if you can name who sets the price. A large, difficult client is rarely a revenue question. It is a market-structure question. If this one would account for a third or more of your income, you are no longer a seller facing a market. You are a supplier facing a single buyer, and that buyer will set your terms, your hours, and eventually your margins. The "difficulty" is usually the first visible sign of that power: scope creep, slow payment, demands you cannot refuse because you cannot afford to lose them.
Founders tend to read this as a skills problem: if we get better at managing them, it will be fine. It is a structural problem, and better management will not fix it. Notice, too, that the usual advice to "learn from a demanding client" conveniently omits who captures the gains from your learning.
My position: accept, but only on terms that cap their leverage. Limit them to a fixed share of revenue, say 30 percent. Price the difficulty explicitly, with a premium for rush work and a change-order fee for scope growth. Insist on payment terms that do not make you their lender.
Next move: before replying to them, list your other three most likely buyers and what each would pay. If that list is empty, you are not choosing a client. You are choosing a landlord.
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 Joan Robinson. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.