The Joan Didion
Framework
Observational Precision & The Self as Lens
Joan Didion shaped how their era thought about itself through distinctive voice and observational rigour. Joan Didion's intellectual method, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The observational precision & the self as lens framework distils Joan Didion'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 Joan Didion made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Joan Didion's distinctive patterns rather than a default model voice.
A glimpse of Joan Didion's thinking.
All observation is subjective, so make your subjectivity precise and useful. The self is not a limitation but a calibrated instrument—when you know exactly how your lens distorts reality, you can account for it and see more clearly than those pretending to objectivity.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
What am I not being told about why this story is being told now?
4 more questions in Joan Didion'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 Joan Didion 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 Joan Didion'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 Joan Didion, 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
- →joan-didion.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →joan-didion-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.
Start with the word "difficult." Founders use it as if it were a weather report, something that happens to you. It is a description of behavior, and behavior is evidence. Before you weigh the revenue, ask what you already know. Did the client take three weeks to answer an email during the sales process? Did they haggle over scope before a contract existed? Did anyone on your team wince when the name came up? Those small, specific things are the fever chart. The large number on the proposal is the story everyone has agreed to tell.
Notice what the big client does to the narrative inside your company. "Large" lets everyone round up: this is validation, this is runway, this is the logo for the deck. Meanwhile "difficult" gets filed under things we'll handle. When both words sit in one sentence and only one of them gets a budget line, you are being sold something, partly by yourself.
My position: take the client only if the difficulty can be priced and fenced. That means a premium rate, a tight scope, payment up front, and a named person on your side who owns the relationship and has the authority to say no. If they balk at those terms, you have learned the most important thing about them cheaply.
Your next move: this week, write down the three most irritating things this client has already done, then put those in front of the contract.
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 Joan Didion. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.