The Stephen Curry
Framework
Range-Extension & Repetition
Stephen Curry reached elite levels through a daily practice of deliberate self-measurement and refusal to accept the ceiling. Stephen Curry's performance thinking, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The range-extension & repetition framework distils Stephen Curry'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 Stephen Curry made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Stephen Curry's distinctive patterns rather than a default model voice.
A glimpse of Stephen Curry's thinking.
Mastery comes from practicing at distances and difficulties beyond what the game demands. Every shot attempt is data collection for muscle memory. What looks impossible today becomes automatic tomorrow through obsessive repetition at the edge of your range.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"How can I make this practice rep harder than anything I'll face in the game?"
4 more questions in Stephen Curry'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 Stephen Curry 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 Stephen Curry'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 Stephen Curry, 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
- →stephen-curry.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →stephen-curry-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, but only on terms that stretch you without breaking you. A large, difficult account is the business equivalent of shooting from five feet behind the line: if your team can deliver under that pressure, every normal client afterward will feel like an open look. The difficulty is not the risk. The risk is taking it before your fundamentals are sound.
So the real question is whether your core delivery is already clean at your current range. If your best clients get consistent, repeatable results from you and your processes hold when you are not in the room, you have earned the right to extend. If you are still improvising on your current accounts, a hard client will expose every flaw at once and you will build bad habits under stress, the way a shooter does when he chases distance with broken mechanics.
Assuming your foundation is solid, structure the deal so the extension is deliberate. Negotiate a paid 60-day pilot with a narrow scope and written success metrics, then expand only when you hit them. Cap their share of your revenue near 30 percent so one bad quarter cannot sink you.
Next move: this week, write down the three things this client will demand that your team has never done before. Pick the one you can practice now, run a dry rehearsal of it internally, and see how many clean reps it takes before you sign anything.
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 Stephen Curry. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.