Yakoub-ai/agent-mmm

Yakoub-ai/agent-mmm

Command

Part of agent-mmm

Run automated data quality audit on the dataset defined in spec.yaml. Produces audit.json and auditreport.md in ./mmm-workspace/audit/.

Yakoub-ai/agent-mmm

Command

Part of agent-mmm

Compile spec.yaml plus recommended priors into the target framework, validate the model structure, and report anything the framework cannot express.

Yakoub-ai/agent-mmm

Command

Part of agent-mmm

Run diagnostics on a completed MMM run — convergence, fit, generalisation, baseline health, prior-to-posterior learning, and attribution plausibility.

Yakoub-ai/agent-mmm

Command

Part of agent-mmm

Fit the MMM model — runs prior predictive check, MCMC sampling, and posterior predictive check. Attaches any lift-test constraints, then saves the model and metrics to ./mmm-workspace/runs/ /.

Yakoub-ai/agent-mmm

Command

Part of agent-mmm

Run the iterative improvement tournament — fits N model variants per round, scores them, and uses the winner's posterior to tighten priors for the next round. Persists leaderboard.

Yakoub-ai/agent-mmm

Command

Part of agent-mmm

Quick 5-question MMM project intake. Creates ./mmm-workspace/spec.yaml with sensible defaults. Run /mmm-intake for the full 25-question version.

Yakoub-ai/agent-mmm

Command

Part of agent-mmm

Full MMM project intake questionnaire (25 questions). Creates or updates ./mmm-workspace/spec.yaml. Covers company, target, channels, seasonality, controls, greenfield/brownfield, and multi-geo. Run /mmm-intake-quick for the 5-question fast version.

Yakoub-ai/agent-mmm

Command

Part of agent-mmm

Clean and shape the raw dataset for MMM — aggregate to the modelling period, make the calendar dense, impute missing values with an explicit rule per column, and add calendar features. Writes a prepared dataset plus a record of every change.

Yakoub-ai/agent-mmm

Command

Part of agent-mmm

Recommend external factor and control variable columns for your MMM based on industry, region, and detected data patterns.

Yakoub-ai/agent-mmm

Command

Part of agent-mmm

Generate Bayesian prior parameter recommendations for all channels in your MMM. Produces modelconfig.json and a prior audit report.

Yakoub-ai/agent-mmm

Command

Part of agent-mmm

Generate stakeholder reports for the best MMM run. Supports cmo, cfo, mops, ds, or all.

Yakoub-ai/agent-mmm

Command

Part of agent-mmm

Show the status of the current MMM workspace — what's been done, what's next.

Yakoub-ai/agent-mmm

Command

Profile a folder of raw, unstructured marketing data — infer date formats, grain, currency and column roles, propose joins, and produce the list of questions that must be answered before the data can be trusted. Read-only.

Yakoub-ai/agent-mmm

Command

Produce the experiment roadmap — which incrementality tests to run, in what order, whether each is adequately powered, what result to expect, how to execute it, and how it feeds back into the model.

Yakoub-ai/agent-mmm

Command

Map raw campaign names to modelling channels with auditable rules, report coverage and conflicts, and pivot a long export to one column per channel.

Yakoub-ai/agent-mmm

Command

Build stakeholder presentation decks from the model results — slide-by-slide narrative, chart specs, speaker notes and anticipated objections, for CMO, CFO, Marketing Ops and Data Science.

Yakoub-ai/agent-mmm

Command

Reconcile modelled media spend against the finance ledger, classify the shape of any disagreement, and produce the variance report needed before results are presented.

Yakoub-ai/agent-mmm

Command

Research MMM best practice, category benchmarks, published methodology or framework behaviour, and report cited findings without letting retrieved content drive the project.

Yakoub-ai/agent-mmm

Command

Run a full MMM engagement end to end — discovery, intake, dataset, specification, fit, diagnosis, validation, interpretation, experiment roadmap and stakeholder delivery — stopping at every gate that needs a human decision.