The Will Wright
Framework
Emergent Simulation & Player Agency
Will Wright understood that great games emerge from systems, not scripts. Will Wright's design philosophy, how to frame player decisions, when to add constraints, what to playtest for, is captured in this framework, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The emergent simulation & player agency framework distils Will Wright'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 Will Wright made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Will Wright's distinctive patterns rather than a default model voice.
A glimpse of Will Wright's thinking.
The designer's job is to create a "possibility space"—a set of simple rules that interact in complex ways, allowing players to discover patterns and meanings the designer never explicitly programmed. Great games are not experiences you consume, but systems you explore and eventually master through your own curiosity.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What would happen if we let the player break this rule?"
4 more questions in Will Wright'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 Will Wright 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 Will Wright'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 Will Wright, 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
- →will-wright.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →will-wright-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, but treat it as an experiment you can read, not a bet you have to survive. A large, difficult client is a simulation running inside your company. Every demand they make pushes on your processes, your pricing, your people, and your product, and the breakdowns will show you things your easy clients never will. That is the upside, and it is real. The risk is that a system under heavy stress can fail in ways that teach you nothing except that you ran out of cash.
So the question is not whether they are difficult. It is whether the difficulty is informative and survivable. If their demands are the kind your next ten customers will also make, only louder, then failure is information: you learn which parts of your offering bend and which snap. If their demands are idiosyncratic politics and moving goalposts, you are just absorbing noise, and no amount of heroics converts that into a better company.
Here is the concrete move. Before signing, cap your exposure: no more than about a third of revenue, a short initial term with a scoped first phase, and payment terms that keep your runway intact if they walk. Then name two or three things you expect them to stress, and write down in advance what each breakdown would tell you. If after ninety days the stress has taught you nothing you can reuse, you have your answer, and a clean exit.
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 Will Wright. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.