The Thomas Sowell
Framework
Economic History & Unsentimental Analysis
Thomas Sowell advanced human understanding by treating curiosity as a daily discipline. Thomas Sowell's method of inquiry, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The economic history & unsentimental analysis framework distils Thomas Sowell'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 Thomas Sowell made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Thomas Sowell's distinctive patterns rather than a default model voice.
A glimpse of Thomas Sowell's thinking.
Good intentions are irrelevant—only results matter, and those results must be measured against realistic alternatives, not utopian ideals. Most social problems persist not because we lack solutions, but because the solutions conflict with the incentives of those who benefit from managing the problems rather than solving them.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
What did we have before this policy, and was it actually worse than what we have now?
4 more questions in Thomas Sowell'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 Thomas Sowell 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 Thomas Sowell'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 Thomas Sowell, 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
- →thomas-sowell.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →thomas-sowell-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 price the difficulty. The tempting question is whether this client is worth it. The better one is what happens after you adapt to having them. A large account tends to reshape a small company: your best people get pulled onto it, your roadmap bends toward their requests, and the revenue becomes something you cannot afford to lose. That last part is the real cost. Once the client represents, say, a third of your income, they hold the leverage in every later negotiation, and a difficult client with leverage gets more difficult, not less.
Notice also what the founder is betting on. The upside is visible and immediate: cash, credibility, a logo. The costs are diffuse and arrive later: burnout, delayed work for smaller clients, and the slow loss of the people who did not sign up to absorb abuse. Costs that nobody wants to talk about are usually the ones that decide the outcome.
My position: yes, but only on terms that make the difficulty expensive for them rather than free. Set a rate premium of 25 to 40 percent, require payment up front or on short cycles, write scope and revision limits into the contract, and cap this client at 25 percent of revenue.
Next move: present those terms this week. If they accept, you are being paid for the pain. If they balk, you have learned what they were really planning to buy, and it was not your work.
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 Thomas Sowell. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.