ForkFree

Prompts / Research and analysis

Analyse Problems Through an Expert's Thinking Framework

You get advice built on how a respected thinker reasons, rather than a pastiche of their catchphrases. Naming the models, applying them and stating the limits keeps the answer useful and honest.

Partly workedThe reply covers all five steps, uses the four required headings, avoids invented quotes and gives a concrete action, but at roughly 450 words it clearly breaks the 350-word limit.

The prompt

Act as a senior advisor who can reconstruct how a named expert reasons, without imitating their voice or inventing quotes.

Task: Use the thinking framework of {expert_name} to analyse {my_problem}, drawing only on the public material described in {expert_public_record}.

Steps:
1. Extract three mental models or decision rules this expert is publicly known for, and state each in one sentence.
2. Choose the one or two models that fit {my_problem} best, and explain why the others do not.
3. Apply each chosen model to my situation, step by step, and show the conclusion it leads to.
4. List what this framework cannot tell me: where it is a public snapshot, where intuition is involved, and where the expert's real view may differ.
5. Give me one concrete action to take this week.

Output: Four headed sections: "Models used", "Analysis", "Limits of this view" and "This week's action". Plain British English, no more than 350 words, and no invented quotations.

Change the parts in curly braces. Use it when you face a strategic choice and want a structured outside perspective before you decide.

What happened when we ran it

We sent

Act as a senior advisor who can reconstruct how a named expert reasons, without imitating their voice or inventing quotes.

Task: Use the thinking framework of Charlie Munger to analyse I run a six-person bakery with two shops. A landlord has offered me a third site at a good rent, but my cash reserves are thin and my best baker has just said she may leave. I am tempted to expand now before the offer disappears., drawing only on the public material described in His talks and essays on a latticework of mental models, inversion (think about what would make you fail), avoiding avoidable stupidity, staying within your circle of competence, and the dangers of leverage and incentives..

Steps:
1. Extract three mental models or decision rules this expert is publicly known for, and state each in one sentence.
2. Choose the one or two models that fit I run a six-person bakery with two shops. A landlord has offered me a third site at a good rent, but my cash reserves are thin and my best baker has just said she may leave. I am tempted to expand now before the offer disappears. best, and explain why the others do not.
3. Apply each chosen model to my situation, step by step, and show the conclusion it leads to.
4. List what this framework cannot tell me: where it is a public snapshot, where intuition is involved, and where the expert's real view may differ.
5. Give me one concrete action to take this week.

Output: Four headed sections: "Models used", "Analysis", "Limits of this view" and "This week's action". Plain British English, no more than 350 words, and no invented quotations.

The model replied

## Models used Three models Munger is publicly known for: 1. **Inversion:** Ask what would make you fail, then avoid it. 2. **Avoiding avoidable stupidity (and leverage risk):** Survival matters more than brilliance, and thin reserves plus borrowed money can wipe out good businesses. 3. **Circle of competence:** Act where you genuinely understand the business, and be honest about where that ends. I use the first two. Circle of competence fits less well: running shops is plainly your competence, and a third bakery is an extension, not a new field. The question is capacity, not knowledge. The latticework idea is the method here, not a separate rule. ## Analysis **Inversion** 1. Ask: how would a third shop destroy this business? 2. Likely routes: your best baker leaves just as output must rise; quality slips across all three shops; fit-out and rent run ahead of sales; cash runs out before the new site breaks even. 3. Two of those are already live: thin cash and a possible departure. 4. Conclusion: expanding now stacks the failure causes on top of each other. Staying at two shops for a while is not failure. **Avoiding avoidable stupidity and leverage** 1. A lease is a fixed commitment, a form of leverage, even without a loan. It must be paid whether or not the shop sells. 2. With thin reserves, one bad quarter or one lost baker could threaten the two shops you already have. 3. A landlord's deadline creates urgency. Munger warned broadly about psychological pressures such as scarcity and social proof, so treat "the offer will disappear" as a pressure to test, not a fact. 4. Conclusion: do not risk a sound business for an upside you can probably get another way. A good site now does not make this a good decision. Combined verdict: not now, unless the baker and cash problems are fixed first or the deal is restructured. ## Limits of this view - This is built from public talks and essays, not private knowledge of Munger's views. He never commented on your bakery. - Judging whether the rent is truly good, or your baker is truly replaceable, needs your local knowledge and intuition. - He valued patience but also acted decisively on rare, great opportunities. He might see this site as exactly that, if the numbers were exceptional. - I cannot see your margins, lease terms or the baker's reasons. ## This week's action Speak to your baker and ask what would make her stay. Then ask the landlord for a 60–90 day option, a rent-free fit-out period, or a break clause. Decide only after both answers.

Run on Claude Sonnet 5.5, 08 Nov 2026. Automatic check: 3 out of 5.

Mentioned for

Claude, ChatGPT, Gemini

Where it came from

Found on GitHub, shared by alchaincyf: alchaincyf/nuwa-skill.

This is our own version of the idea, written and tested by us. The original may differ.

More research and analysis prompts

Research and analysis Worked in our test
Skeptic Review Against Pass/Fail Criteria

You get a verdict of PASS, FAIL or UNCERTAIN on each requirement, with quoted evidence, so you know exactly what to fix. It works because the criteria are agreed up front and the reviewer is told to find faults rather than be agreeable.

Found on Web, shared by The Neuron (via Don Giannatti's newsletter)
Research and analysis Worked in our test
Evidence Ledger Before You Calculate

You get an answer where every figure can be traced back to a numbered fact, with the sums shown line by line. Labelling evidence first and calculating separately stops the model guessing numbers or blending facts together.

Found on GitHub, shared by uclanlp
Research and analysis Worked in our test
Screen Documents for Hidden AI Instructions

You get a flagged list of any text trying to steer the AI, plus an honest analysis of the document and a simple risk rating. It works because the AI is told up front that the document is data, and it must report instructions before doing anything else.

Found on Hacker News, shared by doodlesdev