The John Caples
Framework
Tested Advertising Methods
John Caples moved markets by understanding the specific psychology of attention and offer. John Caples's commercial thinking, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The tested advertising methods framework distils John Caples'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 Caples made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with John Caples's distinctive patterns rather than a default model voice.
A glimpse of John Caples's thinking.
Every advertisement is a scientific experiment where the market renders its verdict through dollars spent, not opinions given. Headlines are 80% of your ad's power—get them wrong and the best body copy in the world won't save you. Test everything, assume nothing, and let split-test results humble your creative ego.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What specific, measurable result will this headline produce compared to our control?"
4 more questions in John Caples'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 John Caples 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 John Caples'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 Caples, 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
- →john-caples.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →john-caples-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.
Don't decide on opinion. Run a test first.
A founder weighing a large, difficult client is staring at the headline number and guessing at the rest. That is how advertisers lose money too: they fall in love with the big order and never ask what it takes to fill it. The market answers these questions faster than your gut will, so make the client answer them before you sign.
Start with specificity. "Difficult" is a vague word, and vague words hide expensive problems. Write down what difficult means in measurable terms: how many revision rounds they demanded in the sales process, how long they took to answer a simple question, whether the contract is clean or full of net-90 payment terms and scope language that bends toward them. Then put a number on the large part. If this client is more than a quarter of your revenue, you aren't gaining a customer, you're acquiring a boss.
My position: take the work only if you can structure it as a small paid pilot, 60 to 90 days, with defined deliverables, a fixed scope, and payment up front or at short intervals. A client who truly values you will accept this. A client who fights the pilot has just shown you the entire relationship in miniature, at the cost of one negotiation instead of a year of margin.
Next move this week: send them the pilot proposal with the scope, price and payment schedule written out in plain numbers, and treat their response as your data.
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 John Caples. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.