nyc_data

Create standardized metadata for data assets. Use when documenting new datasets, building data catalogs, improving data discoverability, or creating data dictionaries for teams.

Structure analysis approach before starting work. Use when receiving new analysis requests, breaking down complex questions into steps, or planning iterative analysis workflows.

Comprehensive data quality assessment against business rules, schema constraints, and freshness expectations. Activate when validating production pipelines, onboarding new data sources, or when stakeholders report data quality concerns.

Identify distinct customer or user segments based on behavior, attributes, or value. Activate when you need to answer "who are our best customers?" or "what distinct groups exist in our user base?" and need data-driven profiles to inform strategy.

Create effective, publication-ready data visualizations. Use when choosing chart types, designing presentation visuals, building dashboard charts, or applying visual design best practices to data output.

Create a clear, transparent explanation of analytical methodology for any audience level. Activate when you deliver findings that require the audience to trust the method — A/B tests, attribution models, forecasts, statistical analyses, or anything where "how did you get that?" is a likely question.

Analyse temporal patterns in data including trends, seasonality, anomalies, and forecasting. Activate when you need to understand trends over time, detect seasonality, identify anomalies in time series, or build simple forecasting models for planning.

Translate a SQL query into a plain-language explanation of what the business logic does. Use when documenting queries, onboarding analysts, preparing code reviews, or explaining logic to non-technical stakeholders.

Systematically diagnose why a metric changed unexpectedly. Activate when a KPI moves significantly, a stakeholder asks "why did X drop/spike?", or a post-incident review requires evidence-based root cause documentation.

Transform raw analysis findings into prioritised, actionable business insights. Activate when an analysis has produced many statistics but no clear "so what", or when you need to prioritise findings before a stakeholder briefing.

Estimate and communicate the business impact of analytical findings. Activate after an analysis surfaces an opportunity, risk, or inefficiency that needs a dollar, user, or time value attached before stakeholders can prioritise it.

Structure and clarify analysis requests before work begins. Activate when a request is vague, has multiple stakeholders with potentially different needs, or when the analysis is non-trivial and rework would be costly.

Reframe technical analysis findings in business language. Activate when findings need to reach a non-technical audience, when jargon is obscuring the message, or when a stakeholder needs to understand and act on statistical results without a technical background.

Investigate and resolve metric discrepancies across data sources, systems, or time periods. Activate when metrics from different sources don't match, after a data migration, or when a dashboard figure doesn't match a report.

Systematic exploratory data analysis. Activate when a dataset needs profiling — structure check, nulls, outliers, distributions, correlations — before deeper analysis begins.

Review SQL queries for correctness, performance, and best practices before they reach production. Activate when promoting queries to dashboards, investigating unexpected results, or when a query is slow and needs optimisation.

Discover, document, and visualize database schemas including tables, columns, relationships, and join paths. Use when working with an unfamiliar database, creating ERD documentation, or understanding how tables connect before writing queries.

Track and document analytical assumptions and decisions. Use when making analytical choices, documenting trade-offs, ensuring transparency, or creating audit trails for analytical work.

Create a structured semantic layer definition for a metric, dimension, or entity. Use when you need a canonical, shareable definition that can feed dbt Semantic Layer, a data catalog, or a BI tool's metric store.

Rigorous statistical analysis of A/B test results. Activate when experiment results need validation, significance is unclear, test duration decisions need justification, or disputed results require documented statistical analysis.

Standard business metric calculation with industry benchmarks. Use when calculating SaaS metrics (MRR, churn, LTV, CAC), e-commerce KPIs, or product analytics metrics with proper definitions.

Time-based cohort analysis with retention and behaviour tracking. Activate when you need to measure how groups of users/customers behave over time — retention rates, revenue by cohort, or feature adoption curves.

Analyse conversion through a multi-step process, identify where users drop off, and diagnose why. Activate when conversion is low, when comparing conversion across segments, or when optimising a user journey.

Define complete requirements for a data dashboard before development begins. Use when a new dashboard is requested, when an existing dashboard needs redesign, or when stakeholder alignment is needed before building.

Transform analytical findings into a compelling, story-driven presentation or document. Activate when data exists but the story is unclear, when a presentation feels like a "data dump", or when you need to make findings memorable and actionable for a specific audience.

Distil complex analysis into a concise, decision-ready executive summary. Activate when findings need to reach a senior audience who won't read the full analysis, when a 1-page briefing is required, or when stakeholders need a clear recommendation, not a data dump.

Pre-delivery quality gate for analytical work. Activate before sharing any analysis, dashboard, or query result with stakeholders. Catches logic errors, presentation issues, and assumption gaps before they reach the audience.

Run a structured retrospective after completing an analysis project to capture learnings and improve future work. Use within one week of project completion while memory is fresh, or immediately after a project that had significant problems.

Package and compress the context needed for an AI-assisted analysis session. Use when starting a complex analysis with Claude to minimise token usage, reduce repetition, and establish shared understanding upfront.

Structure a peer review of analytical work before stakeholder delivery. Use when reviewing a colleague's analysis, dashboard, or query for quality, correctness, and clarity.

Rigorous A/B test statistical analysis. Use when analyzing experiment results, calculating statistical significance, checking for sample ratio mismatch, or validating test design before launch.

Track and document analytical assumptions and decisions. Use when making analytical choices, documenting trade-offs, ensuring transparency, or creating audit trails for analytical work.

Structured, reproducible analysis documentation. Use when documenting analysis findings, creating analysis notebooks, ensuring reproducibility, or building analysis archives for future reference.

Structure analysis approach before starting work. Use when receiving new analysis requests, breaking down complex questions into steps, or planning iterative analysis workflows.

Pre-delivery quality assurance for analysis work. Use when reviewing analysis before sharing with stakeholders, checking for completeness, validating assumptions, or ensuring clarity of recommendations.

Post-analysis learning and process improvement. Use when completing major analysis projects, documenting lessons learned, or improving team analytical practices.

Standard business metric calculation with industry benchmarks. Use when calculating SaaS metrics (MRR, churn, LTV, CAC), e-commerce KPIs, or product analytics metrics with proper definitions.

Time-based cohort analysis with retention and behaviour tracking. Activate when you need to measure how groups of users/customers behave over time — retention rates, revenue by cohort, or feature adoption curves.

Efficiently package context for AI-assisted analysis. Use when preparing to work with Claude on analysis, organizing context documents, or structuring prompts for complex analytical tasks.

Design specifications for effective dashboards. Use when planning new dashboards, improving existing ones, or documenting dashboard requirements before development starts.