Generates RALPH charts (factor-level analysis diagrams) for HAYST method test design. Use when designing combination tests, identifying test coverage gaps, or analyzing system behavior factors.
Comprehensive data quality assessment against defined business rules and constraints. Use when validating data against expected schemas, checking referential integrity across tables, or auditing data pipeline outputs before production use.
This skill should be used when working with marimo reactive notebooks for data science and analytics. Triggers include: - Creating new marimo notebooks - Converting Jupyter notebooks to marimo - Editing existing marimo notebooks - Implementing reactive patterns and UI components - Building interactive data visualizations with marimo
Fetches and processes NBA player and team statistics. Use when the user wants to analyze basketball data for the sports picker model.
MATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing. Use when writing MATLAB/Octave scripts for linear algebra, signal processing, image processing, differential equations, optimization, statistics, or creating scientific visualizations. Also use when the user needs help with MATLAB syntax, functions, or wants to convert between MATLAB and Python code. Scripts can be executed with MATLAB or the open-source GNU Octave interpreter.
Transform, clean, and reshape data using pandas and numpy for ETL and data preprocessing. WHEN: Manipulating DataFrames, cleaning datasets, reshaping data (pivot, melt), merging/joining tables, data normalization, CSV/Excel processing. WHEN NOT: Creating Excel files with formatting (use python-xlsx), building APIs (use python-backend), statistical modeling.
guidance on how to properly do data migrations in Convex
See the main Data Lineage skill for comprehensive coverage of data lineage tracking and provenance.
ALWAYS USE when configuring Polaris catalog, managing namespaces, or setting up credentials in floe-platform. Use IMMEDIATELY when integrating DuckDB via dbt-duckdb plugin, configuring PyIceberg REST catalog, or debugging access control issues. Provides research steps for REST API, OAuth2 authentication, and multi-engine coordination with DuckDB, dbt, and Dagster.
Persistent state management using AgentDB (DuckDB) for workflow analytics and checkpoints. Provides read-only analytics cache synchronized from TODO_*.md files, enabling: - Complex dependency graph queries - Historical workflow metrics - Context checkpoint storage/recovery - State transition analysis Use when: Data gathering and analysis for workflow state tracking Triggers: "analyze workflow", "query state", "checkpoint", "workflow metrics"
Diagnose ClickHouse replication health, Keeper connectivity, replica lag, and queue issues. Use for replication lag and readonly replica problems.
Comprehensive guide to dbt (data build tool) patterns, modeling best practices, testing strategies, and production workflows for modern data transformation
Data governance strategy, quality validation rules, and data dictionary management for vehicle insurance platform. Use when defining data quality standards, implementing validation rules, managing field mappings, resolving data conflicts, or establishing data governance processes. Covers data cleaning standards, quality metrics, and mapping management.
Skill for understanding, editing, analyzing, and migrating TIBCO Objectstar (Object Service Broker) code used in mainframe OTP and batch applications. Activate when user is working with Objectstar rules, asks about mainframe modernization, or legacy 4GL code involving GET, FORALL, or EXCEPTION blocks.
Executive CDO Agent. 데이터 전략, 데이터 거버넌스, AI/ML 전략을 담당합니다.
Generate real Cassandra 5.0 test data using Docker containers, export SSTables with proper directory structure, validate parsing against sstabledump, and manage test datasets. Use when working with test data generation, dataset creation, SSTable export, validation, fixture management, or sstabledump comparison.
Creates JPA entities following best practices.
Implementing comprehensive data quality checks across the data pipeline to ensure accuracy, completeness, and reliability.
Validates and fixes BOM CSV files for ECIR tool compatibility. Use when users need to check CSV files before running ECIR comparisons, fix CSV formatting issues, ensure required columns exist, or diagnose why ECIR tool fails to process a CSV file.
