The Michael Burry
Framework
Contrarian Research & Asymmetric Bets
Michael Burry built capital over decades by applying specific, repeatable mental models to uncertainty. Michael Burry's investing thinking, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The contrarian research & asymmetric bets framework distils Michael Burry'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 Michael Burry made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Michael Burry's distinctive patterns rather than a default model voice.
A glimpse of Michael Burry's thinking.
Markets are efficient most of the time but spectacularly inefficient during periods of mass delusion. The greatest opportunities exist where everyone else sees certainty, but careful analysis reveals structural flaws that make catastrophic outcomes not just possible, but inevitable.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What is everyone assuming that cannot possibly be true forever?"
4 more questions in Michael Burry'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 Michael Burry 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 Michael Burry'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 Michael Burry, 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
- →michael-burry.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →michael-burry-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.
Read the contract before you read the revenue. Everyone around this founder is looking at the logo and the invoice size. The consensus is that a big client validates the business, and when the whole room agrees on that, the footnotes deserve the most attention. The difficulty is not the risk. It is the symptom. Somewhere in the payment terms, scope language, termination rights, or the client's own history with vendors, the real shape of this deal is written down, and almost nobody reads it that way.
Treat the deal as an asymmetric bet and check which side of the asymmetry you sit on. A good version caps your downside: milestone payments, a deposit, a defined scope, a clean exit. A bad version caps your upside at the contract value while leaving your downside open-ended: unlimited revisions, net-90 payment, one client becoming sixty percent of revenue, your best people pulled off everything else. Difficult clients rarely fail by being unpleasant. They fail by being concentrated and slow to pay while your fixed costs keep running.
My position: take them only if you can rewrite the terms so a bad outcome costs you a bruise, not the company. If they refuse structural protection, that refusal is your answer.
Next move this week: ask three of their former vendors, directly, how payment and scope disputes were resolved. Then model the month in which this client pays 60 days late and doubles the workload. If you survive that month, sign.
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 Michael Burry. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.