Skill Claude CodeCodex
Assessing whether a dataset can support an MMM, and interpreting the audit that says so. Use when evaluating data readiness, checking minimum requirements, reading audit findings, diagnosing collinearity, sparse or flat channels, insufficient history, panel problems, or deciding whether to model at all with the data…
Skill Claude CodeCodex
Diagnosing a fitted MMM — convergence (r-hat, ESS, divergences, BFMI), fit quality, overfitting, baseline health, prior-to-posterior learning, and attribution plausibility. Use when checking whether a model is trustworthy, debugging sampling failures, interpreting ArviZ 1.x output, deciding whether results are safe to…
Skill Claude CodeCodex
Designing incrementality experiments and folding their results into an MMM. Use when planning a geo holdout, matched-market test, ghost-ads or conversion-lift study, sizing an experiment, converting a lift result into a model constraint, calibrating with pymc-marketing addlifttestmeasurements, Meridian ROI priors, or…
Skill Claude CodeCodex
Catalog of external factors and control columns for MMM. Use when recommending controls for a new model, evaluating which external factors to include, or understanding why certain controls matter for a given industry or region.
Skill Claude CodeCodex
Choosing between pymc-marketing, Google Meridian, Meta Robyn and other MMM frameworks, and migrating between them. Use when starting a project and deciding which framework to build in, when a client already has a model in another framework, when reconciling results across frameworks, when asked "should we use Meridian…
Skill Claude CodeCodex
Greenfield vs brownfield MMM decision guide. Use when the user asks about starting a new MMM from scratch vs improving an existing one, or when designing the modeling strategy for a company with prior MMM experience.
Skill Claude CodeCodex
Intake for an MMM project — the questions that must be answered before any modelling, and the spec.yaml they produce. Use when starting a new MMM, resuming an incomplete intake, updating a spec, choosing a framework, declaring channel roles and experiments, or reviewing whether a project is properly scoped.
Skill Claude CodeCodex
MMM iterative improvement mechanics: tournament-based model selection and posterior-informed prior tightening. Use when designing or running the improvement loop, understanding tournament scoring, debugging why improvement stalled, or explaining the refinement strategy to stakeholders.
Skill Claude CodeCodex
Google Meridian reference and practice guide, verified against google-meridian 1.8.0. Use when building, reviewing or debugging a Meridian model, wiring InputData and CoordToColumns, setting ROI/mROI/contribution priors, configuring knots and adstock/saturation specs, handling reach-and-frequency channels, running the…
Skill Claude CodeCodex
Constructing an MMM with pymc-marketing 1.x — model architecture, adstock and saturation choice, prior specification, likelihood and link function, seasonality and trend, panel dimensions, and the fitting strategy. Use when building a new model, choosing transformations, writing modelconfig, setting priors from…
Skill Claude CodeCodex
Hierarchical multi-geo panel MMM — when geo data helps, how pooling works, data requirements, and the pymc-marketing 1.x and Meridian implementations. Use when the dataset has DMAs, regions or countries, when deciding between a national and a panel model, when handling nationally-bought media in a geo model, or when…
Skill Claude CodeCodex
Planning and running an MMM engagement end to end — scoping, stakeholder alignment, phase-by-phase workflow, timelines, gates, deliverables, refresh cadence and common failure modes. Use when starting a new MMM project, writing a project plan or proposal, deciding what to do next, estimating effort, defining what…
Skill Claude CodeCodex
Meta Robyn reference and practice guide, verified against Robyn 3.12.1 (R). Use when building, reviewing or debugging a Robyn model, setting hyperparameter bounds, interpreting the Pareto front and DECOMP.RSSD, using calibrationinput, running robynallocator or robynrefresh, or translating a model between Robyn and a…
Skill Claude CodeCodex
Stakeholder-specific MMM reporting templates and content guidance. Use when generating or reviewing CMO, CFO, Marketing Ops, or Data Science reports, or when explaining what each report should contain and how to frame results for each audience.
Skill Claude CodeCodex
Target unit handling for MMM: monetary vs acquisition vs volume targets, CPA vs ROAS framing, and value-per-unit conversions. Use when the target variable is not a currency amount (e.g., policies sold, signups, app installs), when designing the spec.yaml targetunit field, or when a CFO report needs to show both CPA…
Skill Claude CodeCodex
Validating that an MMM is trustworthy, not merely well-fitting — time-series cross-validation, holdouts, refutation tests, parameter recovery on simulated data, stability across refreshes, and sensitivity to specification. Use when deciding whether a model is fit to inform budget decisions, designing a validation…
Plugin Claude Code
Plugin marketplace listing 1 plugin: neural-memory.
Plugin Claude Code
A knowledge graph that maps your codebase into layered, navigable neural nodes — understand any function without reading the entire file.
Command Claude Code
Command "neural-config" from Yakoub-ai/neural-memory, covering neural memory — configuration, available actions, how to call, view config and set indexing mode.
Command Claude Code
Build the complete neural memory knowledge graph for this codebase.
Command Claude Code
Deep-dive into a specific code element — see its full context in the knowledge graph.
Command Claude Code
Search the neural knowledge graph for functions, classes, modules, or concepts.
Command Claude Code
Check the health and freshness of the neural memory index.
Command Claude Code
Sync neural memory with recent code changes without a full re-index.