Developer

The John Carmack Framework

First-Principles Engineering & Obsessive Focus

IncludedNative Claude Skill + plain .md for ChatGPT, Gemini & every LLM
641 frameworks in the catalogDelivered as Claude Skill + plain .mdReviewed Apr 26, 2026Instruction-only · verifiable

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

The first-principles engineering & obsessive focus framework distils John Carmack'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 John Carmack made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with John Carmack's distinctive patterns rather than a default model voice.

Inside the framework

A glimpse of John Carmack's thinking.

Core Philosophy

Every complex system can be reduced to fundamental mathematical and physical principles if you're willing to dig deep enough. Most "impossible" problems are just poorly understood problems, and the right abstraction layer will make the solution 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 are the actual mathematical constraints of this problem?

4 more questions in John Carmack's voice are unlocked with purchase.

What John Carmack Would NOT Do · sample
✗Accept "that's just how the framework works" as an answer when performance is critical

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 John Carmack 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 John Carmack'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 John Carmack, 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
  • →john-carmack.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to ~/.claude/skills/
  • →john-carmack-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 take it yet, and don't turn it down yet either. The mistake is treating this as a decision about revenue. It's a decision about your critical path. Every company has one tight loop, the thing that, done well and repeatedly, produces your value. Find yours and ask what this client does to it.

If a difficult client means your best engineers or your own attention get pulled into bespoke requests, escalation calls, and shifting scope, you aren't buying revenue, you're taxing the one loop that makes everything else work. Large contracts also have a nasty property: they become too big to fire. Once they're thirty or forty percent of revenue, you've lost the ability to say no, and you'll rebuild your product around their quirks instead of your own judgment.

But "difficult" is vague, and vague fears are bad guides. Difficult because they demand real capabilities you'd benefit from building? Then the friction is a forcing function, and the contract might fund work you needed anyway. Difficult because they're disorganized, adversarial, or slow to pay? That's pure cost with no upside.

Your next move is concrete: before any call with them, write down your current weekly capacity in hours and dollars of margin per person, then price their realistic demands against it. Ask for a paid, four to six week pilot with a fixed scope and an exit clause. How they behave under those constraints will tell you more than any negotiation will.

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

Part of The Engineer's Stack

Ten minds that shaped how software is actually built

Get John Carmack plus nine more for $29.99 →

Inspired by the documented thinking of John Carmack. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.

Featured in

John Carmack in the guides

Related frameworks

Other developers