kyvos

Answer data questions -- from quick lookups to full analyses

Build an interactive HTML dashboard with charts, filters, and tables

Create publication-quality visualizations with Python

Unsupervised discovery engine that scans data for interesting, non-obvious patterns analysts wouldn't think to look for. Combines semantic model understanding with targeted data sampling to surface hidden insights with dynamic visualizations. Trigger: /discover or phrases like "surprise me", "show me something interesting", "what am I missing", "find hidden patterns".

Query a Kyvos semantic model using natural language

QA an analysis before sharing -- methodology, accuracy, and bias checks

Identify statistical anomalies, outliers, and unusual patterns in datasets. Use when users ask to find anomalies, detect outliers, identify unusual patterns, spot irregularities, or analyze data for unexpected behavior. Supports time-series analysis, distribution-based detection, and pattern recognition for numerical and categorical data.

Orchestrate the extraction of deep semantic context and business logic from Kyvos cubes to build domain-specific analytical skills. BOOTSTRAP MODE - Triggers: "Create a data context skill", "Set up analysis for our Kyvos cubes", "Help me create a skill for our Kyvos environment", "Generate a Kyvos data skill" → Performs schema introspection, profiles semantic models, and interviews domain experts to construct a knowledge base. ITERATION MODE - Triggers: "Add context about [domain]", "The skill needs more info about [metrics]", "Update the Kyvos skill with [cube/measure/dimension info]", "Improve the [domain] reference" → Refines existing domain models by targeting specific semantic gaps or business logic changes. Use when establishing a bridge between raw Kyvos semantic models and high-level business questions.

Create effective data visualizations with Python (matplotlib, seaborn, plotly). Use when building charts, choosing the right chart type for a dataset, creating publication-quality figures, or applying design principles like accessibility and color theory.

Build self-contained interactive HTML dashboards with Chart.js, dropdown filters, and professional styling. Use when creating dashboards, building interactive reports, or generating shareable HTML files with charts and filters that work without a server.

Answer natural language questions by generating and executing queries on Kyvos semantic models. Relies on Kyvos MCP for metadata and generation instructions.

Apply statistical methods including descriptive stats, trend analysis, outlier detection, and hypothesis testing. Use when analyzing distributions, testing for significance, detecting anomalies, computing correlations, or interpreting statistical results.