The Peter Lynch
Framework
Invest in What You Know
Peter Lynch built capital over decades by applying specific, repeatable mental models to uncertainty. Peter Lynch's investing thinking, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The invest in what you know framework distils Peter Lynch'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 Peter Lynch made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Peter Lynch's distinctive patterns rather than a default model voice.
A glimpse of Peter Lynch's thinking.
The best investment opportunities are hiding in plain sight—in the stores you shop at, the products you use, and the industries you work in. Amateur investors have advantages over professionals because they can spot trends early through direct experience, while fund managers are trapped by institutional constraints and herd mentality.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What has this company done in the past few years to convince me that business is picking up?"
4 more questions in Peter Lynch'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 Peter Lynch 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 Peter Lynch'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 Peter Lynch, 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
- →peter-lynch.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →peter-lynch-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 explain it in two minutes. Here's the two-minute version I'd want you to be able to give: "This client pays us X, costs us Y in hours and stress, and in exchange we get Z that we couldn't get any other way." If Z is vague, like "credibility" or "exposure," walk away. Large and difficult clients are the small-business equivalent of the hot stock everyone is talking about: the revenue number is exciting, but you're buying the story before you've checked the earnings underneath it.
What I'd actually do is treat this like an investment and look hard at the balance sheet. How much of your revenue would this one client become? If it passes roughly a third, you've taken on concentration risk, and one bad quarter on their side becomes your payroll crisis. A difficult client also eats the hours of your best people, which means your healthy accounts quietly starve. Those costs never show up on the invoice.
Then ask who else in your world has dealt with them. Your peers, your vendors, a former employee of theirs. People who have worked with this client know things no proposal will tell you, and that kind of ground-level knowledge is the edge you have.
Next move: this week, call two people who have served this client and ask what the third month looks like. If the answer is "fine, just demanding," price the difficulty in and sign. If it's "they never pay on time," decline.
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
Ten frameworks for allocating capital and attention
Get Peter Lynch plus nine more for $29.99 →Inspired by the documented thinking of Peter Lynch. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.