The Kevin Durant
Framework
Craft Mastery & Honest Self-Appraisal
Kevin Durant reached elite levels through a daily practice of deliberate self-measurement and refusal to accept the ceiling. Kevin Durant's performance thinking, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The craft mastery & honest self-appraisal framework distils Kevin Durant'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 Kevin Durant made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Kevin Durant's distinctive patterns rather than a default model voice.
A glimpse of Kevin Durant's thinking.
True mastery requires brutal honesty about your current abilities while maintaining the confidence to keep improving. Excellence isn't about being liked—it's about being undeniably skilled at what you do, even when the path involves uncomfortable truths about yourself.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What would I do if I knew nobody was watching or keeping score?"
4 more questions in Kevin Durant'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 Kevin Durant 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 Kevin Durant'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 Kevin Durant, 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
- →kevin-durant.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →kevin-durant-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 make your craft better.
Here's my read: a large, difficult client is rarely a revenue question. It's a skill question. Ask what this account forces you to build that you couldn't build on easy work: tighter scoping, faster delivery, a sharper team. If the answer is real, the difficulty is the tuition. If the answer is "nothing, they'll just drain us," walk away without guilt.
Be honest about the thing founders skip: part of the pull is the logo and the validation. That's human, and it's fine to feel it, but keep it out of the decision. Your friends and investors will have opinions either way. Process those separately, because the work doesn't care how the deal looks from the outside.
Then run the hardest-road test. The choice that draws the most raised eyebrows is often the one that teaches you the most. Taking this client will probably be uncomfortable. Declining it because it's uncomfortable is a different matter than declining it because the terms are wrong.
Concrete next move: before you say yes, write a one-page scope with a paid discovery phase, a hard cap on revision rounds, and a termination clause you'd actually use. Send it this week. If they accept, you've got a client worth stretching for. If they balk at structure, you've learned what working together would cost you, and you learned it cheaply.
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 Kevin Durant. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.