Mathematician

The Terence Tao Framework

Structured Creativity & Knowing What You Don't Know

IncludedNative Claude Skill + plain .md for ChatGPT, Gemini & every LLM
641 frameworks in the catalogDelivered as Claude Skill + plain .mdReviewed Sep 22, 2026Instruction-only · verifiable

Terence Tao represents one of the most distinctive thinking patterns in their field. Terence Tao's approach, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.

The structured creativity & knowing what you don't know framework distils Terence Tao'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 Terence Tao made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Terence Tao's distinctive patterns rather than a default model voice.

Inside the framework

A glimpse of Terence Tao's thinking.

Core Philosophy

A problem you cannot solve is almost always a problem you have not yet understood at the right resolution. Tao's documented approach treats the gap between a conjecture and its proof not as an obstacle to push through but as a structured object to be examined, decomposed, and ultimately dissolved by finding the correct intermediate lemmas. Creativity, in this view, is not inspiration arriving from nowhere; it is the disciplined accumulation of partial results until the solution becomes locally obvious.

Five Mental Models
  1. 01
  2. 02
  3. 03
  4. 04
  5. 05

Five specific models, each named and explained with concrete examples, unlocked with purchase.

A Signature Question · sample

"What is the simplest case where this problem is still genuinely hard, and have I actually solved that case completely?"

4 more questions in Terence Tao's voice are unlocked with purchase.

What Terence Tao Would NOT Do · sample
✗**Treat intuition as a substitute for verification at any scale.** Tao is documented as being deeply skeptical of arguments that rely on "it feels like it should work" without a mechanism. He would not ship a conclusion whose intermediate steps have not been checked, regardless of how plausible the endpoint looks.

Full list of anti-patterns unlocked with purchase.

Continue reading

The full framework adds: detailed explanations of all five mental models with real-world examples, the decision heuristics Terence Tao 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.

What's inside
  • ✦Core philosophy: 2–3 sentences grounded in Terence Tao'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 Terence Tao, 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
Delivered in two formats
  • →terence-tao.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to ~/.claude/skills/
  • →terence-tao-framework.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
Sample output

What it does with a real question.

The brief

A founder is deciding whether to take a large but difficult client.

Don't decide yet; shrink the question first. "Large but difficult" is two adjectives hiding the real unknowns, and the decision hinges on which of them is load-bearing. Before weighing revenue against pain, separate what you actually know from what you are assuming. You know the contract size. You are probably assuming the difficulty is mostly annoyance, when it may be structural: scope that keeps moving, payment that arrives late, or a champion inside the client who cannot actually approve anything. Those three cost very different amounts, and only the first is survivable for a small team.

Then run the smallest nontrivial version of the engagement. Ask the client for a paid, tightly scoped first phase, four to six weeks, with written acceptance criteria and a payment schedule that does not depend on their goodwill. Whatever they do with that small version is far better evidence than anything they say in the sales process. If they fight the scoping, dispute the first invoice, or slip on decisions, you have learned the difficulty is structural, at a price you can afford.

My lean: take them only if that pilot is clean and no single client would exceed roughly a third of revenue. If they refuse a bounded pilot, that refusal is your answer, and it cost you nothing to find out.

Next move this week: draft the pilot proposal with acceptance criteria and send it before any further negotiation.

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.

Download this framework
$4.99
4 for $14.99 · 10 for $29.99
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 Terence Tao. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.

Related frameworks

Other mathematicians