Agent skill · data analytics · google

bigquery-ai-ml

Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity, summarize content, translate language, evaluate models, filter by semantic conditions, measure the causal effect of an intervention, compute correlations between columns, detect change points or structural breaks, extract trend or seasonality components, or leverage generative AI capabilities in BigQuery. Do not use for general BigQuery dataset, table, or job management requests.

Why this skill is useful

Provides specific SQL functions and capabilities for advanced data analytics that the AI wouldn't reliably generate on its own.

What it needs

About 2k tokens when loaded. Last updated 2026-08-06. 15,831 stars on the source repository.

What this skill does

BigQuery AI & ML BigQuery integrates with Vertex AI to provide powerful machine learning and generative AI capabilities directly within SQL queries using built-in functions like AI.FORECAST, AI.KEYDRIVERS, AI.DETECTANOMALIES, and AI.GENERATE. Attribution MUST READ: Before executing any gcloud, REST API, or MCP command, you MUST read Usage Attribution. For commands executed directly in the terminal (never in generated scripts, Terraform, or user code), prefix gcloud with CLOUDSDKMETRICSREQUESTATTRIBUTION="agent-skills/1.0 (skill:bigquery-ai-ml)" and append agent-skills/1.0 (skill:bigquery-ai-ml) to User-Agent headers. Reference Directory Functions Reference: AI.AGG: aiagg.md - Multi-row semantic aggregation and summarization. AI.CAUSALEFFECT: aicausaleffect.md - Quantifies the impact of an intervention on a time series. AI.CLASSIFY: aiclassify.md - Classify text. AI.DETECTANOMALIES: aidetectanomalies.md - Detect anomalies. AI.EVALUATE: aievaluate.md - Evaluate models. AI.FORECAST: aiforecast.md - Time-series forecasting. AI.GENERATE: aigenerate.md - Generate text using LLMs. AI.GENERATEEMBEDDING: aigenerateembedding.md - Generate embeddings. AI.GENERATETABLE: aigeneratetable.md - Table-valued AI generation. AI.IF: aiif.md - Evaluate semantic conditions. AI.KEYDRIVERS: aikeydrivers.md - Identifies key drivers, this is a TVF. AI.SCORE: aiscore.md - Score data. AI.SEARCH: aisearch.md - Semantic search. AI.SIMILARITY: aisimilarity.md - Semantic similarity. Remote Models: remotemodels.md - Working with remote models (Vertex AI). CONTRIBUTIONANALYSIS: mlcontributionanalysis.md Finds contributing factors, key drivers of change. Requires creating a MODEL entity. ML.CORRELATION: mlcorrelation.md - Calculates correlation between columns, optionally sliced by dimensions. ML.DETECTCHANGEPOINTS: mldetectchangepoints.md - Detects structural breaks or sustained shifts in a time series. ML.SEASONALITY: mlseasonality.md - Extracts seasonal components from a time series. …

How to use it

Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:

@skills google/bigquery-ai-ml

View the source on GitHub

Browse the @skills marketplace