The George Saunders
Framework
Kindness in Fiction & Generous Editing
George Saunders shaped how their era thought about itself through distinctive voice and observational rigour. George Saunders's intellectual method, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The kindness in fiction & generous editing framework distils George Saunders'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 George Saunders made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with George Saunders's distinctive patterns rather than a default model voice.
A glimpse of George Saunders's thinking.
Fiction's highest purpose is to increase the reader's capacity for empathy and understanding. Every story decision—from word choice to character motivation—should serve the deeper human truth rather than clever literary effects. The editing process is an act of love toward both the work and future readers.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What would it feel like to be this person in this moment?"
4 more questions in George Saunders'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 George Saunders 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 George Saunders'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 George Saunders, 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
- →george-saunders.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →george-saunders-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.
Take the client only if you can stay kind to them. That sounds soft, but it's the hardest test of whether this deal is survivable. A large, difficult client rarely hurts a company through the invoices. The damage comes slowly, when your team begins to talk about them the way people talk about an enemy. Once that tone sets in, everyone becomes a little smaller: the account lead who used to be generous starts rationing patience, and you find yourself writing emails to win rather than to understand.
So the real question is not whether you can afford the revenue, but what the relationship will do to the people you employ. Difficult clients are often frightened clients. Their demands usually come from some fear you haven't met yet. If you can imagine the person across the table, the one who can't sleep because their own boss is leaning on them, then you can probably do this work with your decency intact. If your honest reaction is that you'd be absorbing contempt for a year, that tells you more than any spreadsheet will.
Next move: before you answer, spend one hour with the client's own people, ideally the ones who actually do the work, and ask what the last vendor got wrong. Listen for fear, not villainy. If you come away able to describe their position generously, say yes, with firm boundaries written down. If you can't, decline warmly and mean it.
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 George Saunders. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.