# pymc-marketing-mmm-clv

A skill for Bayesian marketing analytics with PyMC: media mix modeling, customer lifetime value and BTYD models. Useful when you need channel contributions and ROAS.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 835 installs · ★ 12
- Author: reason-machines
- License: LicenseRef-Unknown · policy=link-only · description only; the file stays with the author
- Source: https://github.com/reason-machines/marketing-skills/tree/HEAD/skills/pymc-marketing-mmm-clv/SKILL.md
- Updated: 2026-10-09
- HTML: https://affpapa.org/en/nevibecode/skills/pymc-marketing-mmm-clv

## What it does

The skill wires the PyMC-Marketing library into your agent and guides it through building a media mix model. It covers adstock transformations — geometric, delayed and Weibull — plus saturation functions: logistic, Michaelis-Menten and tanh. Time-varying effects are there too, for baseline sales and media contribution.

For CLV you get Beta-Geometric/NBD, Pareto/NBD and Gamma-Gamma. Customer choice analysis ships alongside. Models can be calibrated with lift test results, then used to allocate budget across channels with bounds and a planning horizon.

What you need first: PyMC-Marketing installed via conda or pip, with Docker support for Jupyter workflows. Your data has to be a table with a date column, channel columns and controls such as holidays or promotions. No dated channel history means no media mix model — worth fixing your data collection before anything else.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/marketing-skills --skill pymc-marketing-mmm-clv -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/pymc-marketing-mmm-clv/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/pymc-marketing-mmm-clv/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/marketing-skills --skill pymc-marketing-mmm-clv -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/pymc-marketing-mmm-clv/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/marketing-skills --skill pymc-marketing-mmm-clv -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/pymc-marketing-mmm-clv/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install reason-machines/marketing-skills pymc-marketing-mmm-clv
```

2. **Manually: put the files in place**
- File: `.github/skills/pymc-marketing-mmm-clv/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add reason-machines/marketing-skills --skill pymc-marketing-mmm-clv -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/reason-machines/marketing-skills --path skills/pymc-marketing-mmm-clv
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/pymc-marketing-mmm-clv/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add reason-machines/marketing-skills --skill pymc-marketing-mmm-clv -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/reason-machines/marketing-skills/tree/HEAD/skills/pymc-marketing-mmm-clv/SKILL.md

## When to use it
- build a media mix model with adstock and saturation
- compute ROAS and per-channel contributions
- allocate budget across channels under bounds
- model customer lifetime value for non-contractual buyers
- calibrate a model with lift test results

## Example prompts
- create a media mix model for tv, radio and digital with geometric adstock
- calculate ROAS and channel contributions from this model
- build a customer lifetime value model for non-contractual customers

## Similar
- [statistical-analysis](https://affpapa.org/en/nevibecode/skills/k-dense-ai-statistical-analysis.md) — skill · 2300 installs
- [ad-conversion-tracking](https://affpapa.org/en/nevibecode/skills/ad-conversion-tracking.md) — skill · 19800 installs
- [influencer-measurement-framework](https://affpapa.org/en/nevibecode/skills/influencer-measurement-framework.md) — skill · 12600 installs
- [instagram-marketing](https://affpapa.org/en/nevibecode/skills/instagram-marketing.md) — skill · 826 installs
- [marketing-org-and-stack](https://affpapa.org/en/nevibecode/skills/marketing-org-and-stack.md) — skill · 316 installs
- [marketing](https://affpapa.org/en/nevibecode/skills/marketing.md) — skill · 339 installs

From the same set: [reason-machines/marketing-skills](https://affpapa.org/en/nevibecode/by/reason-machines/marketing-skills.md) — 19 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md