Summary

A reference documentation skill for BigQuery's built-in AI and ML functions (`AI.FORECAST`, `AI.DETECT_ANOMALIES`, `AI.GENERATE`, `AI.KEY_DRIVERS`). The skill provides SQL syntax references, parameter tables, output schemas, and practical examples for performing time-series forecasting, anomaly detection, text generation, and key driver analysis directly within BigQuery queries without custom model training.

Detected Capabilities

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

Referenced Domains

External domains referenced in skill content, detected by static analysis.

Use Cases

• Forecast time-series data using pre-trained TimesFM models without custom training
• Detect anomalies in time-series data by comparing target data against historical patterns
• Generate text and structured content using Gemini models within SQL queries
• Identify key dimensional segments responsible for metric changes between interest and reference groups

Quality Notes

• Comprehensive syntax reference with clear parameter documentation for each function
• Well-structured output schema tables with descriptions for all return columns
• Practical, runnable examples for each function with realistic data sources
• Clear relationship documented between this skill and the BigQuery Basics skill for broader context
• Examples include edge cases (e.g., multivariate detection, structured output generation)
• Excellent use of markdown formatting with consistent table layouts and code blocks
• Reference directory provides quick navigation to specific function documentation
• No error handling guidance or common troubleshooting documentation provided
• Limited guidance on performance implications or cost considerations for large datasets
• No discussion of data requirements (e.g., minimum data points, data quality expectations) beyond mention of '3 data points minimum' in status fields