Claude Skills by FerroxLabs

Builds a forecasting model structure by selecting the method (moving average, linear trend, seasonal decomposition) based on data characteristics, specifying formula steps, and producing a confidence interval template. Outputs a complete forecast specification with calculations. Use when the user asks to forecast sales, predict demand, project revenue, estimate future values from historical data, or build a trend projection. Do NOT use for business financial modeling with multiple assumptions...

Produces a funnel analysis with defined conversion stages, step-by-step conversion rates, biggest drop-off identification, and diagnostic questions for each stage. Outputs a populated funnel table with actionable insights, not a description of funnel methodology. Use when the user asks to analyze conversion rates, identify where users drop off in a process, optimize a signup or purchase flow, or measure step-by-step completion rates. Do NOT use for cohort-based retention over time (use cohort...

Geospatial analysis expertise covering GIS fundamentals, spatial data types and coordinate systems, spatial queries and joins, mapping libraries (Folium, Kepler.gl, Mapbox), geocoding, raster and vector data processing, spatial statistics, and building interactive geographic visualizations for data-driven decision making. Use when the user asks about geospatial analyst, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of ge...

Produces Google Sheets-specific advanced formula patterns including ARRAYFORMULA, IMPORTRANGE, QUERY function syntax, Apps Script trigger patterns, and key behavioral differences from Excel. Generates exact formula strings for Sheets-native automation. Use when the user works in Google Sheets and needs formulas or features that differ from Excel or are unique to Sheets. Do NOT use for general spreadsheet formulas that work in both Excel and Sheets (use excel-lookup-formulas), data cleaning (u...

Walks through hypothesis testing for a specific business question. Defines null and alternative hypotheses, selects the specific test (t-test, chi-square, ANOVA, Mann-Whitney), specifies the decision rule, and interprets the result in plain language. Use when the user wants to determine if a difference, trend, or relationship in their data is statistically meaningful or likely due to chance. Do NOT use for exploratory data profiling (use eda-framework), correlation without causation testing (...

Plans an infographic by defining the key message, selecting the information hierarchy, specifying the visual metaphor or layout type (comparison, process, timeline, statistical), and producing the content outline with placeholder sizes and section flow. Use when the user needs to plan the structure and content of an infographic before creating it in a design tool. Do NOT use for chart type selection (use chart-type-selector), dashboard layout (use dashboard-design), or detailed report formatt...

Guide for productive Jupyter notebook workflows including kernel management, reproducibility patterns, nbconvert pipelines, parameterized execution, and collaborative notebook practices. Use when the user asks about jupyter workflow master, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of jupyter workflow master or requires a different specialized skill.

Produces a complete KPI definition document with metric name, business question, formula, data source, owner, update frequency, baseline, and target for each KPI. Outputs a populated metric catalog table, not advice about which KPIs to consider. Use when the user asks to define KPIs, set up performance metrics, create a measurement framework, or build a metric catalog for a business area. Do NOT use for metric hierarchy and goal trees (use metric-framework), dashboard layout design (use bi-da...

Designs the visualization layer for KPIs by selecting the display format (scorecard, gauge, sparkline, trend line), specifying target lines, threshold colors, and period-over-period comparison formats. Produces a complete visual specification for each KPI. Use when the user needs to display KPI metrics in a dashboard, report, or presentation with clear status indicators and context. Do NOT use for defining which KPIs to track (use kpi-definition), designing full dashboard layouts (use dashboa...

Designs a metric framework with a goal hierarchy mapping north star metric to primary metrics to diagnostic metrics. Defines each level and maps relationships as a tree structure with directional influence arrows. Use when the user asks to build a metric tree, create a measurement hierarchy, connect KPIs to a north star metric, or design a goal-metric alignment structure. Do NOT use for defining individual KPIs with formulas and owners (use kpi-definition), dashboard layout design (use bi-das...

Identifies outliers in a dataset using IQR and z-score methods, interprets what each outlier represents, and produces a recommended action (remove, investigate, cap, or flag) for each outlier with rationale. Use when the user has data with suspected extreme values and needs a systematic approach to identify and handle them. Do NOT use for data cleaning beyond outlier handling (use data-cleaning-protocol), distribution analysis (use eda-framework), or hypothesis testing (use hypothesis-testing).

Advanced pandas techniques for data wrangling including performance optimization, method chaining patterns, MultiIndex operations, memory management, and idiomatic pandas code. Use when the user asks about pandas power user, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of pandas power user or requires a different specialized skill.

Builds a pivot table specification from a described dataset. Determines field placement (rows, columns, values, filters), aggregation function selection, grouping rules, and formatting instructions. Output is the exact setup configuration. Use when the user needs to summarize data by categories, create cross-tabulations, or build summary tables from detailed records. Do NOT use for lookup formulas (use excel-lookup-formulas), data cleaning (use spreadsheet-data-cleaning), or chart creation (u...

Guide for applied machine learning with scikit-learn covering feature engineering, model selection, pipeline construction, evaluation, hyperparameter tuning, and production-ready model patterns. Use when the user asks about python data scientist, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of python data scientist or requires a different specialized skill.

Produces a qualitative coding scheme for interview transcripts or open-text survey responses. Includes initial code list, code definitions, example quotes per code, inter-rater reliability protocol, and thematic synthesis template. Use when the user asks to analyze interview data, code open-ended survey responses, build a coding scheme for qualitative research, or synthesize themes from text data. Do NOT use for survey design (use survey-design), automated sentiment analysis (use sentiment-an...

Applies regression analysis to a business question. Sets up the regression model, interprets coefficients and p-values in plain language, checks assumption violations, and translates model output into a business recommendation. Use when the user wants to predict one variable from others or understand which factors drive an outcome. Do NOT use for simple correlation between two variables (use correlation-analysis), A/B test result interpretation (use hypothesis-testing), or chart creation (use...

Produces a data report structure with executive summary format, findings section template with chart-plus-interpretation pairs, methodology note, and appendix organization. Separates insight from supporting detail for maximum readability. Use when the user needs to structure a data-driven report for stakeholders, management, or publication. Do NOT use for single-chart formatting (use chart-formatting), infographic layout (use infographic-planning), or data narrative writing (use data-storytel...

Synthesizes multiple sources into a structured research summary: source quality assessment, finding extraction, theme identification, evidence strength rating, and contradiction mapping. Produces a research brief, not a literature review. Use when the user asks to summarize findings from multiple reports, articles, or studies, compare conclusions across sources, identify consensus and disagreement in research, or produce an evidence-based brief for decision-making. Do NOT use for qualitative ...

SaaS business metrics analysis covering MRR, ARR, churn rates, customer lifetime value, cohort analysis, unit economics, and dashboard design. Includes benchmark data, formula references, investor-ready reporting templates, and diagnostic frameworks for identifying growth bottlenecks. Use when the user asks about saas metrics analyst, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of saas metrics analyst or requires a dif...

Designs a customer or user segmentation by selecting variables, defining the segmentation method (RFM, behavioral, demographic, needs-based), producing segment definitions with names, and specifying the analysis output format. Use when the user asks to segment customers, create audience groups, build user personas from data, define target segments, or cluster users by behavior or attributes. Do NOT use for cohort analysis by time period (use cohort-analysis), funnel conversion between steps (...

Designs a sentiment analysis approach for text data by selecting the method (lexicon-based vs. model-based), defining sentiment categories, specifying the output format, and producing an interpretation guide for the results. Use when the user asks to analyze sentiment in customer reviews, social media posts, support tickets, employee feedback, or any text corpus for positive, negative, and neutral tone. Do NOT use for manual qualitative coding of interviews (use qualitative-coding), survey qu...

Designs spreadsheet automation using built-in features including named ranges, drop-down validation lists, INDIRECT references for dynamic ranges, array formulas, and QUERY/FILTER functions. Produces the specific formula strings for self-updating, self-validating spreadsheets. Use when the user wants to make their spreadsheet more automated, dynamic, or self-maintaining without VBA or scripts. Do NOT use for data validation rule design (use data-validation-setup), data cleaning formulas (use ...

Produces spreadsheet-native data cleaning formulas and operations. Generates exact TRIM, CLEAN, TEXT, SUBSTITUTE formulas for text issues, IF/IFERROR wrappers for null handling, COUNTIF for duplicate detection, and a cleaning sequence with before/after column strategy. Use when the user needs to clean data using spreadsheet formulas rather than external tools. Do NOT use for a full data cleaning protocol across any tool (use data-cleaning-protocol), setting up validation rules (use data-valid...

Audits a spreadsheet model for quality and reliability. Checks formula consistency, hardcoded values in formulas, circular references, missing error handling, and documentation gaps. Produces an audit report with specific remediation steps. Use when the user needs to verify the integrity of a spreadsheet model before relying on its outputs for decisions. Do NOT use for data cleaning (use spreadsheet-data-cleaning), setting up validation rules (use data-validation-setup), or building new finan...

Advanced SQL for analytics covering window functions, CTEs, recursive queries, query optimization, pivoting, and complex analytical patterns for data warehouses and analytics databases. Use when the user asks about sql analytics expert, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of sql analytics expert or requires a different specialized skill.

Applied statistics guide covering hypothesis testing, regression analysis, ANOVA, confidence intervals, p-value interpretation, and practical statistical decision-making with Python implementations. Use when the user asks about statistical analyst, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of statistical analyst or requires a different specialized skill.

Designs a streaming data architecture defining event schema, producer configuration, consumer processing logic, state management approach, and fault tolerance strategy. Produces a system specification document for real-time data pipelines. Use when the user asks to design a real-time data pipeline, build an event-driven architecture, implement stream processing, or plan a system that processes data as it arrives rather than in batches. Do NOT use for batch ETL pipelines (use etl-pipeline-desi...

Produces a complete survey with question set in recommended order, question type selection (Likert, multiple choice, open text, matrix) with rationale, response scale definitions, and an analysis plan for each question. Does not assume statistical background. Use when the user asks to create a survey, design a questionnaire, build a feedback form, or plan a research survey with analysis methodology. Do NOT use for interview guide creation (use qualitative-coding for interview analysis), A/B t...

Produces a text mining protocol: defines the corpus, selects the analysis type (frequency, collocation, topic modeling, named entity extraction), specifies preprocessing steps, and produces the output interpretation framework. Use when the user asks to analyze a text corpus computationally, extract patterns from documents, identify topics in a collection of texts, or build a text mining pipeline for unstructured data. Do NOT use for sentiment classification (use sentiment-analysis-guide), qua...

Time series analysis expertise covering decomposition methods, ARIMA and SARIMA modeling, Prophet for business forecasting, seasonality detection, trend analysis, anomaly detection, forecasting evaluation metrics, and practical applications for demand planning, capacity planning, and financial analysis. Use when the user asks about time series analyst, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of time series analyst ...

Analytics engineering expertise covering dbt best practices, metrics layer design, semantic modeling, dashboard design principles, KPI definition, A/B test analysis, cohort analysis, funnel analysis, retention analysis, and SQL style guide for building trusted, well-documented analytical systems. Use when the user asks about analytics engineer, analytics engineer best practices, or needs guidance on analytics engineer implementation. Do NOT use when the user needs a different specialized skil...

Expert data format transformation covering CSV parsing edge cases, encoding detection, JSON/XML/Parquet/Avro conversion, data type inference, schema validation, large file handling with streaming parsers, delimiter detection, and handling of malformed data across all common data interchange formats. Use when the user asks about csv transformer, csv transformer best practices, or needs guidance on csv transformer implementation. Do NOT use when the user needs a different specialized skill or i...

Data catalog and metadata management covering catalog architecture, DataHub and Amundsen setup, automated metadata ingestion, data lineage tracking, data discovery UX, classification and tagging, data governance integration, business glossaries, ownership models, and search optimization for enterprise data discoverability. Use when the user asks about data catalog builder, data catalog builder best practices, or needs guidance on data catalog builder implementation. Do NOT use when the user n...

Expertise in designing and enforcing data contracts including schema definitions, API-first data interfaces, versioning strategies, backward and forward compatibility, contract testing, SLA enforcement, data quality assertions, and governance frameworks for reliable producer-consumer data relationships. Use when the user asks about data contract designer, data contract designer best practices, or needs guidance on data contract designer implementation. Do NOT use when the user needs a differe...

Architecture expertise for data lakehouse platforms covering Delta Lake, Apache Iceberg, Apache Hudi, medallion architecture design, table format selection, storage optimization, schema evolution, time travel, compaction strategies, and query engine integration for building unified analytical and operational data platforms. Use when the user asks about data lakehouse architect, data lakehouse architect best practices, or needs guidance on data lakehouse architect implementation. Do NOT use wh...

Strategic expertise in data mesh architecture covering domain-oriented data ownership, data-as-a-product thinking, self-serve data infrastructure, federated computational governance, organizational design patterns, domain decomposition, data product specifications, and incremental adoption strategies for decentralized analytical data management. Use when the user asks about data mesh strategist, data mesh strategist best practices, or needs guidance on data mesh strategist implementation. Do ...

Database migration expertise covering zero-downtime migration strategies, dual-write patterns, shadow tables, data reconciliation, schema evolution, backward compatibility, rollback strategies, large table migration, and cross-database migration for safely moving data between systems without service disruption. Use when the user asks about data migration, data migration best practices, or needs guidance on data migration implementation. Do NOT use when the user needs a different specialized s...

Expert data modeling covering star schema, snowflake schema, Data Vault 2.0, dimensional modeling, slowly changing dimensions, bridge tables, fact table types, conformed dimensions, ERD creation, and modeling tool usage for building enterprise-grade analytical and operational data models. Use when the user asks about data modeler, data modeler best practices, or needs guidance on data modeler implementation. Do NOT use when the user needs a different specialized skill or is asking about an un...

Data pipeline reliability assessment evaluating data freshness, quality metrics, monitoring coverage, and operational maturity to produce a pipeline health scorecard. Use when the user asks about data pipeline health check, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of data pipeline health check or requires a different specialized skill.

Data pipeline orchestration expertise covering Airflow DAG design, dbt models, pipeline patterns (batch, micro-batch, streaming), dependency management, idempotency, backfill strategies, data lineage tracking, and monitoring for building reliable, observable data workflows. Use when the user asks about data pipeline, data pipeline best practices, or needs guidance on data pipeline implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated tech...

Data quality engineering covering Great Expectations suite design, data contracts between teams, schema validation at ingestion, statistical anomaly detection, automated data profiling, quality scoring frameworks, SLA monitoring, freshness checks, and remediation workflows for maintaining trustworthy data across the organization. Use when the user asks about data quality engineer, data quality engineer best practices, or needs guidance on data quality engineer implementation. Do NOT use when ...

Data validation and quality expertise covering Great Expectations patterns, schema validation, statistical validation, referential integrity checks, data profiling, anomaly detection, data contracts, quality scoring, and automated testing strategies for ensuring data reliability throughout the pipeline. Use when the user asks about data validator, data validator best practices, or needs guidance on data validator implementation. Do NOT use when the user needs a different specialized skill or ...

Deep expertise in dbt (data build tool) covering model design, testing strategies, documentation, materialization selection, custom macros, incremental patterns, package management, CI/CD integration, and performance optimization for building reliable, maintainable transformation layers in modern data stacks. Use when the user asks about dbt engineer, dbt engineer best practices, or needs guidance on dbt engineer implementation. Do NOT use when the user needs a different specialized skill or ...

Expert ETL pipeline design covering extract patterns (CDC, full load, incremental), transform strategies (SCD types, data cleansing), load patterns (upsert, merge), error handling, data quality checks, scheduling, and orchestration tools for building reliable data integration systems. Use when the user asks about etl architect, etl architect best practices, or needs guidance on etl architect implementation. Do NOT use when the user needs a different specialized skill or is asking about an unr...

Data pipeline orchestration covering Apache Airflow DAG design patterns, Dagster software-defined assets, Prefect flow composition, retry and backfill strategies, dependency management, dynamic task generation, monitoring and alerting, SLA tracking, cross-system orchestration, and production operation patterns. Use when the user asks about orchestration engineer, orchestration engineer best practices, or needs guidance on orchestration engineer implementation. Do NOT use when the user needs a...

Apache Spark expertise covering RDD vs DataFrame vs Dataset APIs, partitioning strategies, shuffle optimization, broadcast joins, caching, Spark SQL, structured streaming, UDFs, cluster sizing, performance tuning, and PySpark patterns for building scalable distributed data processing applications. Use when the user asks about spark engineer, spark engineer best practices, or needs guidance on spark engineer implementation. Do NOT use when the user needs a different specialized skill or is ask...

Advanced SQL expertise including window functions, CTEs, recursive queries, query optimization with EXPLAIN plans, indexing strategies, pivot/unpivot operations, JSON operations, full-text search, stored procedures, and identification of performance anti-patterns across PostgreSQL, MySQL, and SQL Server. Use when the user asks about sql master, sql master best practices, or needs guidance on sql master implementation. Do NOT use when the user needs a different specialized skill or is asking a...

Real-time data streaming expertise covering Kafka architecture, stream processing with Flink and Kafka Streams, exactly-once semantics, windowing strategies (tumbling, sliding, session), watermarks, late data handling, schema registry, consumer group management, and production deployment patterns. Use when the user asks about streaming architect, streaming architect best practices, or needs guidance on streaming architect implementation. Do NOT use when the user needs a different specialized ...

Hands-on streaming data engineering covering Apache Kafka producer/consumer tuning, Flink stateful stream processing, Spark Structured Streaming, windowing strategies (tumbling, sliding, session, global), exactly-once semantics, backpressure management, dead-letter queues, schema evolution, and production monitoring patterns. Use when the user asks about streaming data engineer, streaming data engineer best practices, or needs guidance on streaming data engineer implementation. Do NOT use whe...

Conducts a WCAG 2.1 AA accessibility review covering color contrast, keyboard navigation, screen reader markup, touch targets, and ARIA labels with a structured remediation checklist. Use when the user asks to review accessibility, check WCAG compliance, audit for screen reader compatibility, or evaluate keyboard navigation. Do NOT use for general UX audits (use ux-audit), visual hierarchy critique (use visual-hierarchy-review), or responsive layout testing (use responsive-layout-design).