All authors
Claude Skills by Yakoub-ai
github.com/Yakoub-ai41 skills0 installs75 views
- Mmm Api ReferenceComplete pymc-marketing API reference for writing and reviewing MMM code. Use when you need exact constructor signatures, method names, parameter lists, or code patterns for pymc-marketing v0.19.1+. Load this skill when writing new model code, debugging import errors, checking method signatures, or reviewing code that uses pymc-marketing. Also activate when you need to look up plotting methods, evaluation functions, cross-validation setup, or transformation classes.Votes: 0GitHub stars: 4
- Mmm AttributionChannel attribution, ROAS calculation, contribution decomposition, and results interpretation for Marketing Mix Models. Use when extracting channel contributions, calculating return on ad spend, generating response/saturation curves, interpreting model outputs, assessing channel effectiveness, decomposing the target variable into components, or presenting MMM results to stakeholders. Also activate when the user asks about contribution shares, waterfall charts, or which channels are over/under...Votes: 0GitHub stars: 4
- Mmm Budget OptimizationBudget allocation optimization and sensitivity analysis for Marketing Mix Models. Use when optimizing media budget allocation, setting up BudgetOptimizer with CustomModelWrapper, defining budget bounds and constraints, running sensitivity analysis, comparing current vs. optimal allocation, or advising on budget reallocation strategies. Also activate when the user asks about optimal spend, budget constraints, or allocation scenarios.Votes: 0GitHub stars: 4
- Mmm Data QualityData quality assessment and preparation for Marketing Mix Models. Use when evaluating datasets for MMM readiness, checking data requirements, validating columns, assessing collinearity, handling missing values, or preparing marketing spend data for pymc-marketing modeling. Also activate when the user asks about minimum data requirements, data granularity, or feature engineering for MMM.Votes: 0GitHub stars: 4
- Mmm DiagnosticsConvergence diagnostics, fit evaluation, and debugging for Marketing Mix Models. Use when checking rhat, ESS, divergences, evaluating model fit metrics (R-squared, MAPE, wMAPE), debugging sampling issues, assessing overfitting, running model comparison (LOO/WAIC), or validating cross-validation results. Also activate when the user encounters convergence warnings, poor model fit, or needs to understand why a model isn't working.Votes: 0GitHub stars: 4
- Mmm External Factors CatalogCatalog 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.Votes: 0GitHub stars: 4
- Mmm Greenfield Vs BrownfieldGreenfield 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.Votes: 0GitHub stars: 4
- Mmm Intake QuestionnaireIntake questionnaire for MMM projects. Use when starting a new MMM project, resuming an incomplete intake, or updating the spec.yaml. Covers company context, target unit, channel inventory, controls, seasonality, and greenfield vs brownfield classification.Votes: 0GitHub stars: 4
- Mmm Iterative ImprovementMMM 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.Votes: 0GitHub stars: 4
- Mmm Model BuildingModel construction and prior specification for Marketing Mix Models with pymc-marketing. Use when building a new MMM, choosing adstock/saturation transformations, specifying priors with moment matching, configuring the likelihood, setting up the model constructor, or designing the fitting strategy. Also activate when discussing prior calibration, spend-share sigma, channel prior tables, or model_config dictionaries.Votes: 0GitHub stars: 4
- Mmm Multi Geo PanelMulti-geo panel MMM using pymc-marketing's multidimensional API. Use when the dataset has multiple geographies, DMAs, countries, or regions that should be modeled together. Covers geo column setup, panel data validation, and the multidimensional MMM constructor.Votes: 0GitHub stars: 4
- Mmm Stakeholder ReportingStakeholder-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.Votes: 0GitHub stars: 4
- Mmm Target UnitsTarget 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 target_unit field, or when a CFO report needs to show both CPA and revenue-equivalent ROAS.Votes: 0GitHub stars: 4
- Mmm Baseline And TrendThe baseline of an MMM — intercept, trend, seasonality and controls — and how it competes with media for variance. Use when the baseline is negative, implausibly large or small, when deciding between a fixed intercept, a linear trend, changepoints, knots or a time-varying intercept, when seasonality is absorbing media's effect, when reconciling the decomposition, or when explaining "what would have happened anyway" to a stakeholder.Votes: 0GitHub stars: 4
- Mmm Causal DesignCausal identification for MMM — what to control for, what never to control for, and why. Use when deciding which variables to include, when a channel's estimate looks structurally wrong, when handling mediators (search volume, site visits, brand metrics), colliders, funnel effects or reverse causality, when building a DAG for pymc-marketing's dag/treatment_nodes/outcome_node, or when explaining why an MMM coefficient is not automatically a causal effect.Votes: 0GitHub stars: 4
- Mmm Channel SemanticsHow each type of marketing channel should be represented in an MMM — its role (paid media, reach-and-frequency, organic, non-media treatment, control), whether it is driven by spend or exposure, its carryover and saturation behaviour, and whether a ROAS is even defined for it. Use when deciding what a column means, choosing per-channel adstock/saturation, grouping or splitting channels, handling organic/owned/email/price/distribution variables, deciding what enters the budget optimiser, or di...Votes: 0GitHub stars: 4
- Mmm Data EngineeringBuilding the MMM dataset: sourcing, joining, aggregating, handling missing data, currency and inflation, fiscal calendars, taxonomy mapping, outliers and reproducible pipelines. Use when assembling data from platform exports and finance systems, deciding how to fill gaps, choosing daily vs weekly, aligning spend to delivery dates, mapping campaign names to channels, or when the audit reports impossible costs, gaps, duplicates or a non-rectangular panel.Votes: 0GitHub stars: 4
- Mmm Experiment RoadmapProducing the experiment roadmap deliverable — which incrementality tests to run, in what order, what result each is expected to produce, how to execute it, and how it feeds back into the model. Use when asked what experiments to run, how to prioritise testing, whether a proposed test is adequately powered, how many geos or weeks are needed, or how much revenue a test puts at risk.Votes: 0GitHub stars: 4
- Mmm Experimentation CalibrationDesigning 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 add_lift_test_measurements, Meridian ROI priors, or Robyn calibration_input, or when reconciling an MMM with platform-reported or experimental numbers.Votes: 0GitHub stars: 4
- Mmm Framework SelectionChoosing 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 or Robyn", or when a spec feature cannot be expressed in the chosen framework.Votes: 0GitHub stars: 4
- Mmm MeridianGoogle 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 Analyzer or BudgetOptimizer, or translating a model between Meridian and pymc-marketing.Votes: 0GitHub stars: 4
- Mmm OrchestrationRunning a full MMM engagement end to end — the phases, the gates between them, which specialist sub-agent handles which stage, and what must be true before each stage begins. Use when running a complete project, when asked "what do we do next", when a stage has finished and the next one has to start, or when deciding whether to delegate work to a sub-agent or handle it directly.Votes: 0GitHub stars: 4
- Mmm PresentationsBuilding stakeholder presentations from MMM results — deck structure per audience, headline writing, chart selection, speaker notes, and preparing for the questions a room will actually ask. Use when preparing to present MMM results to a CMO, CFO, marketing ops, an agency or a technical reviewer, when asked for a deck or a readout, or when a set of results needs to become a decision.Votes: 0GitHub stars: 4
- Mmm Project PlanPlanning 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 "done" means for a phase, or setting up a recurring measurement practice.Votes: 0GitHub stars: 4
- Mmm ResearchResearching MMM best practice, category benchmarks, published methodology and framework documentation, and folding findings into a project safely. Use when a modelling decision would benefit from outside evidence — typical adstock or ROAS ranges in an industry, how comparable businesses handle a hard channel, what a framework version actually does, or what the published work says about a technique. Includes the untrusted-content rules that govern anything fetched from the web.Votes: 0GitHub stars: 4
- Mmm RobynMeta 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 calibration_input, running robyn_allocator or robyn_refresh, or translating a model between Robyn and a Bayesian framework.Votes: 0GitHub stars: 4
- Mmm Unstructured DataMaking sense of raw, messy, unstructured marketing data before it becomes a modelling dataset. Use when handed a folder of exports, a shared drive, or files nobody can fully explain — platform exports at different grains, finance workbooks, CRM extracts, hand-maintained promo calendars. Covers profiling unknown files, inferring date formats and grain, classifying columns, mapping campaign names to channels, reconciling against finance, and the question bank that has to be answered before any ...Votes: 0GitHub stars: 4
- Mmm ValidationValidating 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 plan, running placebo or subset refutation tests, checking whether conclusions survive reasonable alternative specifications, or explaining why R-squared is not validation.Votes: 0GitHub stars: 4
- Neural Add BugManually log a bug into the neural memory knowledge graph when not using context log files. Links the bug node to the affected code by file path.Votes: 0GitHub stars: 2
- Neural Add TaskManually log a task or phase into the neural memory knowledge graph. Links the task to related code files so it appears in semantic search results.Votes: 0GitHub stars: 2
- Neural ConfigView and modify neural memory settings — indexing mode, exclusions, redaction patterns, and staleness thresholds.Votes: 0GitHub stars: 2
- Neural ContextGet a compact, token-budgeted context snapshot AND save a rich persistent session snapshot — project overview, active bugs/tasks with code connections, and recent git commits. Use this to orient quickly and persist context for the next session.Votes: 0GitHub stars: 2
- Neural IndexBuild the complete neural memory knowledge graph for this codebase by parsing AST, resolving relationships, and scoring importance.Votes: 0GitHub stars: 2
- Neural InsightGenerate comprehensive technical documentation by synthesizing all accumulated insights from the neural memory knowledge graph. Also use to save a new insight with neural_add_insight.Votes: 0GitHub stars: 2
- Neural InspectDeep-dive into a specific code element — see its full context, callers, callees, siblings, and call chains in the knowledge graph.Votes: 0GitHub stars: 2
- Neural QuerySearch the neural knowledge graph for functions, classes, modules, or concepts and get layered results with summaries.Votes: 0GitHub stars: 2
- Neural StatusCheck the health and freshness of the neural memory index — initialization state, staleness, and graph statistics.Votes: 0GitHub stars: 2
- Neural StopStop the running neural memory dashboard server.Votes: 0GitHub stars: 2
- Neural TasksManage the full task lifecycle in the neural knowledge graph — list, create, update status and priority. Tasks connect to code nodes and appear in every prompt via the context hook.Votes: 0GitHub stars: 2
- Neural UpdateSync neural memory with recent code changes incrementally without a full re-index.Votes: 0GitHub stars: 2
- Neural VisualizeGenerate and open the interactive knowledge graph dashboard in your browser — hierarchy treemap, semantic radial tree, and force-directed graph.Votes: 0GitHub stars: 2