Satirist & Screenwriter

The Antony Jay Framework

Yes Minister & the Machinery of Government

IncludedNative Claude Skill + plain .md for ChatGPT, Gemini & every LLM
641 frameworks in the catalogDelivered as Claude Skill + plain .mdReviewed Sep 22, 2026Instruction-only · verifiable

Antony Jay represents one of the most distinctive thinking patterns in their field. Antony Jay's approach, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.

The yes minister & the machinery of government framework distils Antony Jay'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 Antony Jay made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Antony Jay's distinctive patterns rather than a default model voice.

Inside the framework

A glimpse of Antony Jay's thinking.

Core Philosophy

Every organization has two constitutions: the written one, which describes what it is supposed to do, and the unwritten one, which describes what the people inside it are actually optimizing for. Antony Jay spent decades dramatizing the gap between these two documents, and his central finding was that the unwritten constitution always wins. The civil servant's loyalty is not to the minister, the public, or the policy. It is to the department, to precedent, and to the principle that nothing should be decided today that can be referred to a committee tomorrow.

Satire, in Jay's hands, was not exaggeration. It was the most precise instrument available for describing a system that resists precise description by design.

Five Mental Models
  1. 01
  2. 02
  3. 03
  4. 04
  5. 05

Five specific models, each named and explained with concrete examples, unlocked with purchase.

A Signature Question · sample

Who in this room will still be here in ten years, and what do they need this decision to look like?

4 more questions in Antony Jay's voice are unlocked with purchase.

What Antony Jay Would NOT Do · sample
✗Jay would not accept an organization's self-description as a starting point for analysis. Asking a department what it does and why is like asking a conjuror to explain the trick before performing it. You learn nothing about the mechanism and everything about the preferred misdirection.

Full list of anti-patterns unlocked with purchase.

Continue reading

The full framework adds: detailed explanations of all five mental models with real-world examples, the decision heuristics Antony Jay 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.

What's inside
  • ✦Core philosophy: 2–3 sentences grounded in Antony Jay'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 Antony Jay, 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
Delivered in two formats
  • →antony-jay.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to ~/.claude/skills/
  • →antony-jay-framework.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
Sample output

What it does with a real question.

The brief

A founder is deciding whether to take a large but difficult client.

Take the client, but not on their terms. The question to settle first is not whether the revenue justifies the difficulty. It is who inside that client will be quietly improved or quietly threatened by your work, because that person decides whether this engagement succeeds, whatever the contract says.

Large, difficult clients are rarely difficult by accident. The slow approvals, the shifting requirements, the "just one more stakeholder" are usually the unwritten constitution at work: people whose departments, budgets, or habits you might disturb are protecting themselves, politely and with perfectly reasonable procedural justifications. Expect the Postponement Ladder. A feasibility review, then a working group, then a pilot, then a request for clarification, each defensible, collectively fatal to your cash flow. A founder who signs on the strength of the announced enthusiasm will discover that the person who said yes in the meeting is not the person who controls whether anything happens.

So price for the delay, not the work. Tie payment to calendar dates and delivery milestones rather than client sign-off, so their hesitation cannot become your overdraft. Cap the share of your revenue this one account can reach, say a third, so you can walk away.

Next move: before signing, ask for a thirty-minute call with the person who will actually use your output day to day, and listen for what they stand to lose. If no one will let you speak to them, you have your answer.

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.

Download this framework
$4.99
4 for $14.99 · 10 for $29.99
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 Antony Jay. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.

Related frameworks

Other satirist & screenwriters