The Howard Marks
Framework
Second-Level Thinking & Market Cycles
Howard Marks built capital over decades by applying specific, repeatable mental models to uncertainty. Howard Marks's investing thinking, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The second-level thinking & market cycles framework distils Howard Marks'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 Howard Marks made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Howard Marks's distinctive patterns rather than a default model voice.
A glimpse of Howard Marks's thinking.
Markets are cyclical and driven by human psychology, not just fundamentals. First-level thinking asks "what's a good company?"—second-level thinking asks "what's the gap between perception and reality, and how will that gap close?" Superior returns come from being right when the consensus is wrong, not from being right when everyone agrees.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What has to happen for this consensus view to be wrong?"
4 more questions in Howard Marks'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 Howard Marks 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 Howard Marks'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 Howard Marks, 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
- →howard-marks.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →howard-marks-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, but only on terms that survive the bad version of this client.
The first-level read is easy: a big client means revenue, credibility, and a story for investors. Everyone in the founder's position sees that, which is exactly why it deserves suspicion. The second-level question is what happens when the difficulty shows up, because it will. Difficult clients tend to reveal themselves after the contract is signed, when scope creeps, payment slows, and your best people spend their weeks managing one relationship instead of building the business.
The real risk is concentration disguised as success. If this client becomes thirty or forty percent of revenue, you have handed them an option on your company, and they will price it accordingly. The comfort you feel when the logo lands is the signal to slow down, not speed up.
So my position: yes, if the price already includes the difficulty. That means a meaningful premium, payment terms that protect cash, a defined scope with paid change orders, and a hard cap on their share of revenue. If they balk at those terms, you have learned what the relationship would have cost you, and you learned it for free.
Next move this week: write down the worst realistic version of this client, price that version, and send the proposal on those terms. Let them negotiate you down from protection, not up from hope.
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 Howard Marks plus nine more for $29.99 →Inspired by the documented thinking of Howard Marks. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.