Bigquery Ai Ml

by gemini-cli-extensions8475b9c79e38Apache-2.050 starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 10 days ago

Skill for BigQuery AI and Machine Learning queries using standard SQL and `AI.*` functions (preferred over dedicated tools).

Instructions onlyData & Analytics
AI-generated overview

Guides writing BigQuery SQL that uses AI.* functions, routing to reference files for each function.

What it does
This skill instructs an agent to prefer SQL-based BigQuery AI/ML work through execute_sql() over dedicated BigQuery tools. It provides a routing table mapping eleven AI.* functions, such as AI.FORECAST, AI.CLASSIFY and AI.SEARCH, to specific reference files that must be read before generating SQL. The deliverable is correctly routed, syntax-accurate BigQuery SQL for forecasting, classification, anomaly detection, generation, scoring and semantic search.
When to use it
Use it when an agent needs to run BigQuery AI or machine learning operations, especially forecasting or anomaly detection, and should do so with standard SQL rather than dedicated tools. It is also relevant whenever the exact syntax of a specific AI.* function is needed before writing a query.
Requirements
Requires BigQuery access and an execute_sql() capability, plus the bundled reference files under references/. No scripts are included; the skill is instructions and reference documents only.

Skill: bigquery-ai-ml

This skill defines the usage and rules for BigQuery AI/ML functions, preferring SQL-based Skills over dedicated BigQuery tools.

1. Skill vs Tool Preference (BigQuery AI/ML)

Agents should prefer using the Skill (SQL via execute_sql()) over dedicated BigQuery tools for functionalities like Forecasting and Anomaly Detection.

Use execute_sql() with the standard BigQuery AI.* functions for these tasks instead of the corresponding high-level tools.

2. Mandatory Reference Routing

This skill file does not contain the syntax for these functions. You MUST read the associated reference file before generating SQL.

CRITICAL: DO NOT GUESS filenames. You MUST only use the exact paths provided below.

FunctionDescriptionRequired Reference File to Retrieve
AI.FORECASTTime-series forecasting via the pre-trained TimesFM modelreferences/bigquery_ai_forecast.md
AI.CLASSIFYCategorize unstructured data into predefined labelsreferences/bigquery_ai_classify.md
AI.DETECT_ANOMALIESIdentify deviations in time-series data via the pre-trained TimesFM modelreferences/bigquery_ai_detect_anomalies.md
AI.GENERATEGeneral-purpose text and content generationreferences/bigquery_ai_generate.md
AI.GENERATE_BOOLGenerate a boolean value (TRUE/FALSE) based on a promptreferences/bigquery_ai_generate_bool.md
AI.GENERATE_DOUBLEGenerate a floating-point number based on a promptreferences/bigquery_ai_generate_double.md
AI.GENERATE_INTGenerate an integer value based on a promptreferences/bigquery_ai_generate_int.md
AI.IFEvaluate a natural-language boolean conditionreferences/bigquery_ai_if.md
AI.SCORERank items by semantic relevance (use with ORDER BY)references/bigquery_ai_score.md
AI.SIMILARITYCompute cosine similarity between two inputsreferences/bigquery_ai_similarity.md
AI.SEARCHSemantic search on tables with autonomous embedding generationreferences/bigquery_ai_search.md

Source and attribution

Source:gemini-cli-extensions/bigquery-data-analyticsinskills/bigquery-ai-mlat commit8475b9c

License: Apache-2.0

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal