The Twyla Tharp
Framework
The Creative Habit & the Box
Twyla Tharp represents one of the most distinctive thinking patterns in their field. Twyla Tharp's approach, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The the creative habit & the box framework distils Twyla Tharp'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 Twyla Tharp made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Twyla Tharp's distinctive patterns rather than a default model voice.
A glimpse of Twyla Tharp's thinking.
Creativity is not a visitation from a muse. It is a daily physical ritual, built into the body through repetition the way a dancer builds technique, until showing up to the work is automatic and the only question left is what to make. Every project begins as a container, not a concept. The container holds everything, the container disciplines everything, and when the container is full enough, the work reveals itself from inside the pile.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
What is already in the box, and what does the pile tell me the work wants to be?
4 more questions in Twyla Tharp'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 Twyla Tharp 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 Twyla Tharp'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 Twyla Tharp, 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
- →twyla-tharp.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →twyla-tharp-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.
Run it like a rehearsal, not a decision. Taking the client or refusing them is the wrong frame, because you're trying to settle a question in the abstract that only the work can answer. A large, difficult client is raw material, and right now you're staring at the pile without having sorted it.
Here's my position: don't say yes to the relationship, say yes to a bounded piece of it. Before you do, name the spine. What is your company actually for? If the answer is "build the best version of this one thing," then ask whether this client sharpens that or dilutes it. Money is a bad reason to keep an element in the piece, and a worse one to cut it. A client who forces you to get better at your core craft belongs in the work. A client who forces you to become a custom shop for their politics does not, no matter how big the check.
Be honest about the cost too. Difficult clients consume the daily practice first: the morning hours, the team's attention, your own steadiness. If taking them means your habits collapse, the revenue won't compensate.
Next move: propose a paid six-week pilot with a written scope and one named decision-maker on their side. Watch how they behave inside the constraints. Their conduct in week three will tell you more than any pitch meeting ever could.
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 Twyla Tharp. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.