marketing-mix-modeling-end-to-end-pipeline — Claude Code skill
marketing-mix-modeling-end-to-end-pipeline is a Claude Code skill that builds a Python marketing mix model from weekly spend and revenue, accounting for adstock and saturation.
no license 128 installs ★ 12 updated 2026-10-09
npx skills add reason-machines/marketing-skills --skill marketing-mix-modeling-end-to-end-pipeline -a claude-codeWhat marketing-mix-modeling-end-to-end-pipeline does
This skill guides the construction of an econometric Marketing Mix Model (MMM) from weekly media spend and revenue files. It accounts for delayed campaign effects through geometric adstock and captures diminishing returns via Hill saturation curves.
Under the hood, the workflow structures Python scripts around pandas and numpy. Media parameters and external controls feed into an OLS regression using statsmodels, followed by constrained budget optimization executed by scipy.
The transformation order is rigid. Saturation functions must be applied directly to adstocked signals rather than raw costs, otherwise regression coefficients become unreliable.
What it helps with
- model advertising carryover effects via geometric adstock decay
- capture diminishing returns across channels using Hill curves
- run OLS regression on media spend and control variables
- optimize channel budget allocations under spend constraints
Example prompts for the agent
- Build an MMM pipeline for data/dt_simulated_weekly.csv with adstock and saturation
- Apply geometric adstock transformation to TV and search spend columns
- Optimize channel budget allocations based on the fitted OLS coefficients
How to install marketing-mix-modeling-end-to-end-pipeline
1Skills CLI (Vercel)
npx skills add reason-machines/marketing-skills --skill marketing-mix-modeling-end-to-end-pipeline -a claude-code2Manually: put the files in place
~/.claude/skills/marketing-mix-modeling-end-to-end-pipeline/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/marketing-mix-modeling-end-to-end-pipeline/
1Skills CLI (Vercel)
npx skills add reason-machines/marketing-skills --skill marketing-mix-modeling-end-to-end-pipeline -a codex2Manually: put the files in place
.agents/skills/marketing-mix-modeling-end-to-end-pipeline/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add reason-machines/marketing-skills --skill marketing-mix-modeling-end-to-end-pipeline -a cursor2Manually: put the files in place
.cursor/skills/marketing-mix-modeling-end-to-end-pipeline/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install reason-machines/marketing-skills skills/marketing-mix-modeling-end-to-end-pipeline2Manually: put the files in place
.github/skills/marketing-mix-modeling-end-to-end-pipeline/SKILL.md1Skills CLI (Vercel)
npx skills add reason-machines/marketing-skills --skill marketing-mix-modeling-end-to-end-pipeline -a gemini-cli2Platform CLI
gemini skills install https://github.com/reason-machines/marketing-skills --path skills/marketing-mix-modeling-end-to-end-pipelineManually: put the files in place
.devin/skills/marketing-mix-modeling-end-to-end-pipeline/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add reason-machines/marketing-skills --skill marketing-mix-modeling-end-to-end-pipeline -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about marketing-mix-modeling-end-to-end-pipeline
How to install marketing-mix-modeling-end-to-end-pipeline in Claude Code?
Run npx skills add reason-machines/marketing-skills --skill marketing-mix-modeling-end-to-end-pipeline -a claude-code.
What does marketing-mix-modeling-end-to-end-pipeline do?
It provides a Python pipeline covering adstock carryover, Hill saturation curves, OLS regressions, and constrained budget optimization.
What Python dependencies are required?
You need pandas, numpy, statsmodels, scipy, and visualization tools like matplotlib or seaborn.