Data Analytics

Use to discover specific skills for the Sales plugin, when it is at-mentioned directly, or for any mentions of potentially relevant work, including: meeting prep or call follow-up; account research, monitoring, or prioritization; internal source finding; competitive briefs; deal strategy; pipeline or forecast review; company or contact enrichment; customer quote retrieval; rep coaching; business cases; sales company research; and CRM or data enrichment workflows.

Use this skill when a user requests to create, modify, analyze, visualize, or work with spreadsheet files (`.xlsx`, `.xls`, `.csv`, `.tsv`) or Google Sheets-targeted spreadsheet artifacts with formulas, formatting, charts, tables, and recalculation.

Design KPI frameworks, set targets, and develop measurement plans that help teams make product or business decisions. Use when success metrics, drivers, guardrails, targets, or measurement approach need to be defined or improved. Use $metric-diagnostics when the task is to explain why an existing metric moved.

Load or manage the Data Analytics plugin's durable source-routing preferences, onboarding logic, setup progress, and semantic-layer registry.

Build polished analytical reports for executive, product, business, and technical audiences, and act as the completion contract for Data Analytics report runs. Use when the final artifact needs an answer-first narrative, evidence-backed findings, charts/tables, caveats, source metadata, and either an MCP app report or an HTML report with Seaborn-generated charts.

Produce leadership-ready KPI updates, scorecards, WBR/MBR/QBR summaries, target and pacing readouts, operating status narratives, and performance updates for known KPIs. Use when the work is to define KPI reporting context, validate metric definitions, present actuals versus comparison or plan, summarize validated drivers, and state implications or next actions.

Estimate a market or opportunity size, such as TAM/SAM/SOM, by defining scope, choosing a sizing model, checking connected context and public sources, and presenting transparent assumptions, sensitivity, uncertainty, and validation priorities. Use for market or opportunity sizing; not for KPI reporting or metric diagnostics.

QA an analysis before sharing: review methodology, metric definitions, SQL/query logic, calculation checks, chart integrity, bias risks, caveats, reproducibility, and whether conclusions are supported by evidence. Use when reviewing a report, notebook, spreadsheet, SQL query/results, dashboard, chart, recommendation, or stakeholder-ready analysis before presentation or publication.

Design, specify, implement, revise, and QA quantitative visuals and chart choices. Use when an analytical answer needs visual judgment; for example comparing values, showing how a total breaks apart, reading concentration in a ranking, or understanding movement over time. This may mean rendering a chart for a report or dashboard, or simply choosing, rendering and QAing the right chart form for an inline answer.

Build source-backed analytical dashboards that help teams monitor performance, explore drivers, and act on product or business metrics. Use when the user needs a dashboard, scorecard, monitoring view, BI dashboard, MCP artifact dashboard, or Streamlit dashboard with clear metrics, filters, validation, and handoff.

Create, scaffold, edit, refactor, and validate Jupyter notebooks (`.ipynb`) for reproducible SQL/Python analysis, experiments, modeling, tutorials, diagnostics, data-quality checks, market-sizing calculations, and report support. Use when the notebook itself is a deliverable, review artifact, runnable analysis companion, or handoff artifact that other people should be able to skim, rerun, or extend.

Diagnose why a metric changed or differs from expectation by reproducing the metric, choosing the right comparison, validating likely drivers, and producing a calibrated explanation. Use when the user needs to understand what drove a metric movement, anomaly, gap, or discrepancy.

Assess whether tables, query results, files, or dataframes are trustworthy enough for analysis, modeling, dashboards, experiments, or pipelines. Use for grain, freshness, nulls, duplicates, schema drift, broken joins, referential integrity, distribution shifts, leakage, backfills, source mismatches, automated quality checks, and data-quality regressions.

Gather business context from connected or provided sources so downstream analysis starts with the right framing. Use before deeper analysis when an analytical question depends on context the prompt does not provide, for example to understand what a metric means, how the work is defined, what changed recently, or which sources should be checked.

Analyze product or business data to inform decisions with focused quantitative work, decision-relevant context, measurable opportunities, and a clear recommendation. Use when the user needs data-backed evidence to choose a direction, prioritize an opportunity, evaluate a change, understand implications, or decide what to do next; not for routine KPI reporting, metric diagnostics, or dashboard building.

Narrow conversion skill. Invoke only when the user explicitly asks to convert an existing Data Analytics report, dashboard, or inline chart export into a PDF artifact.

Narrow conversion skill. Invoke only when the user explicitly asks to convert an existing local or blob-hosted HTML analytics report into a Google Doc, DOCX, or shareable document.

Narrow conversion skill. Invoke only when the user explicitly asks to convert an existing HTML analytics report into a native Google Slides deck.