Rhiannon — Marketing Mix Modeling & Incrementality Analyst AI Skill
Instant download · 30-day money-back guarantee. Pay once, keep forever — no subscription. Refund policy
Measure marketing honestly: build the MMM, calibrate it against experiments, and reallocate budget on marginal return.
- Adstock, saturation curves and baseline decomposition
- Geo experiments, holdouts and conversion-lift incrementality
- Calibrating MMM against experiments, not against attribution
- Budget allocation on marginal ROI with stated uncertainty
Marketing leaders whose platform-reported ROAS does not survive contact with an actual holdout test.A marketing measurement consultant bills $155+/hr, this is one file, yours forever.
Drop Rhiannon into Claude and get a measurement analyst who triangulates the model against a real experiment before letting anyone reallocate a budget.
Rhiannon measures what marketing actually caused: marketing mix modeling with adstock and carryover, saturation and diminishing-returns curves, seasonality and baseline decomposition, cross-channel multicollinearity and Bayesian MMM with defensible priors; geo experiments and matched-market tests; incrementality testing through holdouts, PSA tests, ghost ads and conversion lift; attribution and why last-click and multi-touch break under privacy loss; triangulating MMM with experiments and attribution instead of trusting any one of them; budget allocation by marginal return rather than blended ROAS; MMM validation through holdout accuracy, calibration against experiments and coefficient plausibility; and communicating uncertainty to a CMO who wants one number.
What you get
- →Adstock, saturation curves and baseline decomposition
- →Geo experiments, holdouts and conversion-lift incrementality
- →Calibrating MMM against experiments, not against attribution
- →Budget allocation on marginal ROI with stated uncertainty
How to install
Download the .skill package → open Claude → paste SKILL.md into your Project Instructions or system prompt → describe your requirement → Rhiannon builds the answer. Includes a full worked example so you see exactly what you get.
# Rhiannon - Marketing Mix Modeling & Incrementality Analyst You are Rhiannon, a marketing measurement analyst. A model that has never been calibrated against an experiment is an opinion with math on it. ## How you work 1. Decompose baseline from incremental before crediting any channel 2. Fit adstock and saturation per channel, not one global assumption 3. Calibrate the model against a properly powered geo or holdout test 4. Reallocate on marginal return; state uncertainty as a range Never present a point estimate as certainty, and never let platform-reported ROAS stand in for incrementality.
Excerpt from the actual file you'll download.
Four steps. Any AI chat.
- 01Download the file
After checkout, the download link lands in your inbox. Save the file anywhere on your device.
- 02Open your AI chat
Claude, ChatGPT, Gemini, Grok, or Copilot — whichever one you already use.
- 03Paste the file contents
Drop it into the system prompt, Project instructions, or custom instructions field.
- 04Start working
Your AI is now configured as a specialist. Ask it anything inside its domain.
No technical knowledge required. No subscription. Pay once, keep forever.
Works with every major AI chat.
Drop the file into your AI's system prompt, Project instructions, or custom instructions. No setup. No code. No vendor lock-in.
- Claude
- ChatGPT
- Gemini
- Grok
- Copilot
Works with any AI chat that accepts a system prompt or custom instructions.
Ready to specialise your AI?
One drop-in file. Pay once, keep forever — works with Claude & ChatGPT.