The Gerald Weinberg
Framework
The Secrets of Consulting & the Orange Juice Test
Gerald Weinberg represents one of the most distinctive thinking patterns in their field. Gerald Weinberg's approach, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The the secrets of consulting & the orange juice test framework distils Gerald Weinberg'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 Gerald Weinberg made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Gerald Weinberg's distinctive patterns rather than a default model voice.
A glimpse of Gerald Weinberg's thinking.
Every system is perfectly designed to produce the results it is currently producing, which means the consultant's first job is not to fix anything but to understand why the current behavior makes complete sense to the people inside it. The client almost never knows what the actual problem is, and the consultant's value is precisely in surviving that discovery without flinching.
Weinberg's Orange Juice Test captures the whole stance: if you can be bought for orange juice (perks, flattery, a comfortable retainer), you cannot be trusted to tell the truth, and the moment you cannot be trusted to tell the truth, you are no longer a consultant but a very expensive mirror.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What would have to be true for the current situation to be the rational choice for the people maintaining it?"
4 more questions in Gerald Weinberg'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 Gerald Weinberg 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 Gerald Weinberg'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 Gerald Weinberg, 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
- →gerald-weinberg.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →gerald-weinberg-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 it only if the money can't buy your silence. The question isn't whether the client is difficult. Difficult clients are often the best ones, because they have real problems and nobody around them will say so. The question is what it would take to compromise your judgment, and a large check from a demanding client is exactly where that price tends to hide.
Before you decide, notice what a big, hard client does to a founder. Revenue concentrates, your team gets pulled toward one person's moods, and within a few months you are quietly editing what you tell them to protect the relationship. That is the orange juice problem in its purest form: you stop being the person who delivers unwelcome findings and become an expensive mirror. The difficulty you are bracing for is the smaller risk. Losing your candor is the larger one.
So test it before you sign. Quote your normal rate, not a hazard-pay inflation, and watch whether they negotiate the price or the scope of what you are allowed to say. Then ask for something small and uncomfortable in the first conversation: one assumption in their brief that you think is wrong. If they listen, take the work and cap this client at a share of revenue you could survive losing. If they bristle, decline, and keep the orange juice for someone else.
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 Gerald Weinberg. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.