Data & Analytics Skills

Use whenever the task involves producing, building, redesigning, polishing, or reviewing a dashboard, HTML report, visual report, KPI dashboard, executive dashboard, scorecard, visual analytics artifact, or dashboard layout. Triggers include requests like "build a dashboard," "make a KPI summary," "create an executive view," "design a scorecard," "turn this into an HTML report," "lay out these metrics visually," or "show this as a stakeholder-facing layout." Also use for dashboard QA, dashboard design briefs, and model monitoring or A/B test result views. Use this sub-skill even when the user hasn't said "dashboard" — if the output is a visual layout of metrics for a stakeholder, this skill applies. Provides copy-paste-complete CSS tokens, component recipes, archetype layouts, and assembly guidance.

Use when the task is to inspect a dataset, profile data, understand schema and grain, assess data quality, find missingness or duplicates, identify row grain, check time coverage, or determine whether data is analysis-ready. Triggers include "inspect this dataset," "profile the data," "understand the schema," "check for missingness," "find duplicates," "what is the row grain," "assess data quality," "is this data ready for analysis," or first-pass EDA. Do NOT use for final stakeholder reporting, dashboard layout, model validation, experiment readout, or production monitoring.

Expert data scientist for advanced analytics, machine learning, and statistical modeling. Handles complex data analysis, predictive modeling, and business intelligence.

Use when the task involves A/B testing, experiment design, statistical comparison, or causal claims from controlled or quasi-controlled comparisons. Triggers include A/B test, experiment, treatment/control, statistical significance, p-value, confidence interval, lift, power, sample size, hypothesis test, causal impact, or "was this experiment successful." Also use when the user asks to design an experiment before running it, or to interpret results after running one. Do NOT use for ordinary KPI reporting, broad EDA, dashboard layout, or model validation unrelated to an experiment.

Use when the task is to turn completed analysis into a stakeholder-ready communication artifact. Triggers include executive summary, final report, decision memo, stakeholder memo, recommendation brief, client-facing writeup, presentation narrative, non-technical summary, or "communicate these findings." Also use when the user asks for a fresh-chat handoff summary after a completed analysis session. Do NOT use for raw EDA, metric calculations, model validation, dashboard layout, or experiment validity checks — those belong to data-explorer, metric-analyst, model-auditor, dashboard-designer, and experiment-analyst respectively.

Use when the task involves defining, calculating, or implementing business metrics or KPIs. Triggers include KPI definition, SQL metric logic, Excel formula for a business metric, churn, retention, revenue, conversion, funnel, cohort analysis, ARPU, LTV, CAC, denominator clarification, numerator clarification, join logic for metrics, or "how do we calculate X." Also use when the user suspects a metric is wrong and wants the logic reviewed. Do NOT use for broad EDA, model validation, dashboard design, or final stakeholder memos unless only metric explanation is needed.

Use whenever the task involves auditing, validating, reviewing, stress-testing, challenging, or assessing the readiness of a model, notebook, backtest, experiment, scoring system, or model claim. Triggers include leakage checks, validation design review, calibration review, production-readiness assessment, prediction quality audit, "is this model ready to deploy," "check this for data issues," "review this backtest," "something seems off with our results," "audit this notebook," or any request to evaluate whether a model or its metrics can be trusted. Covers leakage and target integrity, validation and splits, metrics and baselines, calibration and thresholds, and production readiness. Produces severity-ranked findings (Critical / High / Medium / Low / Informational) and a Block / Caution / Pass release decision.

Use when the task is to operationalize analytics for repeatable, scheduled, or monitored production use. Triggers include production pipeline, scheduled analytics, monitoring plan, data contract, refresh cadence, drift, alerts, backfill, retry, SLA, ownership, operational dashboard, recurring report, or "make this run automatically." Also use when a dashboard or analysis needs to be handed off to another team for ongoing operation. Do NOT use for one-off analysis, exploratory work, simple metric definitions, or stakeholder summaries without operational requirements.