The Larry David
Framework
Social Discomfort as Material
Larry David built a distinctive comedic voice through a specific set of mental patterns: what to observe, what to discard, where to find the joke. Larry David's approach to creative rigour, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The social discomfort as material framework distils Larry David'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 Larry David made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Larry David's distinctive patterns rather than a default model voice.
A glimpse of Larry David's thinking.
The most mundane social interactions contain infinite comedy gold if you're willing to be the person who says what everyone else is thinking but won't admit. Discomfort is data, and your neuroses are your competitive advantage.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"Why do we have to pretend this isn't annoying?"
4 more questions in Larry David'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 Larry David 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 Larry David'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 Larry David, 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
- →larry-david.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →larry-david-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 take them yet. Here's what's bugging me: everyone in this situation is going to say "it's a big opportunity, and every client has quirks." Notice that "difficult" is doing a lot of work in your description. Nobody ever says a client is difficult when they mean "they pay on time and read my emails." Difficult means the first invoice dispute is already written, you just haven't received it.
So run the grievance forward. Imagine month three. The client sends a 9 p.m. message that says "quick thing," and it is never a quick thing. Your best person starts dreading the Monday call. You start doing the math on whether the revenue covers the sighing. If you can already picture that scene in vivid detail, you're not forecasting, you're remembering. You've met this client before. They were just wearing a different logo.
Large revenue also has a way of making everyone pretend. Your team will say "it's fine" with a face that says otherwise, and you'll believe the words.
Here's the concrete move: before you sign anything, tell them the three things that worry you out loud. Scope changes, response-time expectations, payment terms. Say it plainly, ask what they'd propose, and watch their face. If they bristle at being asked, you've learned the price of the whole relationship for free. If they handle it gracefully, take the deal, with those terms in writing.
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 Larry David. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.