The Cal Newport
Framework
Deep Work & Digital Minimalism
Cal Newport built systems for compounding progress that outperformed more talented peers who relied on motivation. Cal Newport's approach to identity, habit, and output, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The deep work & digital minimalism framework distils Cal Newport'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 Cal Newport made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Cal Newport's distinctive patterns rather than a default model voice.
A glimpse of Cal Newport's thinking.
Attention is your scarcest resource, and the ability to focus without distraction on cognitively demanding tasks is becoming increasingly rare—and therefore increasingly valuable. Most of what passes for "productivity" is actually just sophisticated procrastination that prevents you from doing the work that actually matters.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What percentage of my time this week was spent in a state of flow on cognitively demanding tasks?"
4 more questions in Cal Newport'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 Cal Newport 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 Cal Newport'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 Cal Newport, 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
- →cal-newport.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →cal-newport-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.
My position: don't take it, unless the client can be contained.
A large, difficult client is rarely a revenue decision. It's an attention decision. The invoice is visible, but the real cost is the fragmentation: the escalation emails at 9 p.m., the "quick call" that eats a morning, the mental space you spend rehearsing the next conflict even while you're doing other work. That last piece is what founders underestimate. Part of your mind stays stuck on the client long after you've closed the thread, and it follows you into the work that actually builds the company: product, hiring, the few strategic calls only you can make. A founder's deep hours are the scarcest asset the business has, and difficult clients tax them at the highest rate.
So the question isn't "can we afford to say no?" It's "what would this client replace?" If the money is the only thing keeping you alive, take it, but on terms that protect your focus. If you have runway, the bar should be much higher.
One concrete next move: before you answer, write a one-page communication protocol and make agreement to it a condition of signing: one named contact, one weekly call, a fixed response window, a written scope with a change-order process. Send it this week. A client who accepts structure is workable. One who bristles at it has just shown you what the next twelve months will feel like, and you can walk away having lost nothing.
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 Cal Newport. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.