Business & Strategy Skill
Brand Strategy Framework
Audit and build a brand's identity with five academic frameworks (Brand Onion, Trust Equation and JTBD) producing a scored assessment instead of guesswork.
$15
Mental Models OS
Orchestrate decision-making with 80 mental models organized as a lattice model selection…
A decision-making operating system built on 80 mental models organized as a lattice. It classifies your problem, selects the right two-to-four models, applies them in a sequenced chain, and enforces anti-overstacking discipline so you frame decisions clearly without falling into analysis paralysis.
$15 one-time
Add to a kit → Prices include 20% VAT. · Forged on real agency work · one-time, no lock-in
- Type Skill
- Category Business & Strategy
- Delivery Email · instant
- License One-time
Inside the run · no black box
See the actual work before you buy it.
Eighty mental models help nobody until the right four are chained in order. Decisions get classified by type, matched to a chain template, and resolved with a visible reasoning trail instead of an opaque verdict.
- Classifies the decision into one of eight types (strategy or pivot, debug or root cause, pricing, churn risk, security, content and marketing, system scaling, multi-domain ambiguity), because the type determines which models earn a seat.
- Picks the matching chain template from the library: for example debug runs Hanlon's Razor then Occam then 5 Why then a Bayesian posterior, pricing runs Opportunity Cost then Marginal Utility then Anchoring then Comparative Advantage. If no template fits, it builds a custom chain capped at four models.
- Runs the anti-overstacking gate before applying anything: maximum four models per chain, at least two different categories represented (an all-statistics chain is an echo chamber), and trivial problems are rejected outright because a typo fix does not deserve a premortem.
- Applies the models sequentially, each model's output feeding the next as input: an Inversion premortem produces failure scenarios, the Bayes step anchors them against base rates, the Second-Order step traces what the fix itself will cause.
- Aggregates the chain into one concrete recommendation and writes a one-sentence justification per model used, so the decision never arrives as an opaque verdict but as a visible reasoning trail.
- Persists the chain history and the final decision to memory, building a searchable record of which model combinations were used on which problem class and what they concluded.
One power source. 6 lines out.
mental-models-os · core
core active · 6 lines
- ✓ framing a complex strategy
Framing a complex strategy or pivot decision with multiple variables
- ✓ running root-cause analy…
Running root-cause analysis on a bug, regression, or churn spike
- ✓ building hypotheses before
Building hypotheses before an A/B test or audit
- ✓ pricing and packaging de…
Pricing and packaging decisions weighed across economic models
- ✓ multi-domain ambiguity w…
Multi-domain ambiguity where one call touches several areas
- ✓ security and risk decisi…
Security and risk decisions that demand premortem thinking
Yours to keep.
Drag time forward. Watch what stays.
Forever
That's what owning means.
The rented stack
ai writing tool: subscription
expired · access lostanalytics suite: subscription
expired · access lostdesign platform: subscription
expired · access lost(nothing left)
Your forge
-
Break single-model tunnel vision by cross-framing every decision
license: perpetual -
Avoid analysis paralysis with a hard four-model ceiling per chain
license: perpetual -
Make decisions transparent: each model carries a one-line justification
license: perpetual -
Reach better calls faster with pre-built chains for common decision types
license: perpetual
subscriptions expire · deeds don't
Everything in the box.
Pick a piece up. Watch it work.
An 80-model catalog across eight categories with definitions and use cases
6 parts · one working system · ships instantly by email
This wasn't forged for everyone.
- Not for you if you'd rather rent a tool than own one.
- Not for you if you want someone else to run your stack.
- Not for you if you're happy guessing.
Founders, strategists, and operators who make high-stakes, multi-variable decisions and want a disciplined framework instead of gut feel.
then this was forged for you.Works with
Universal by design: these run in any AI. Delivered in the open Agent Skills + MCP format (native in Claude); ChatGPT, Gemini, Cursor and Copilot adapt the same files their own way.
- Claude Native format
- ChatGPT Adapts via open standards
- Gemini Adapts via open standards
- Cursor Adapts via open standards
- Copilot Adapts via open standards
Catch what's on your mind.
the air is clear. nothing between you and the forge.
catch a spark: the forge will answer
-
Is this only for business strategy calls, or does it help with technical decisions too?
The pre-built chains cover both: root-cause analysis on bugs and regressions, security premortems, and A/B test hypothesis building sit next to strategy, pricing, and churn chains. The decision tree routes by decision type, not by department.
-
How does it decide which of the 80 models apply to my problem?
It classifies the problem first, then a chain decision tree maps the decision type to a sequenced set of two to four models, each carrying a one-line justification. Eight pre-built chain templates handle the most common cases without you assembling anything.
-
Will it make the decision for me?
No. The output schema captures the models used, their order, the justification, and a recommendation, but the call stays yours. It frames the decision clearly; it does not replace judgment.
-
How is it delivered?
By email right after purchase: ready to run, downloaded instantly, no setup wait.
-
One-time or subscription?
A one-time purchase; no subscription or hidden fees. VAT (20%) is included.
-
Can I get a refund?
As a digital product, it can’t be refunded once downloaded. That’s why we show exactly what’s inside and who it’s for, right here.