skills.rest
AubreyHan
AubreyHanCOMMUNITY
Explore all skills by this author →
GitHub

developing-with-bigquery

Optimize BigQuery SQL, BigFrames, and ML workflows with correct syntax.

Updated Jun 10, 2026
Search Tags:#embeddings#vector search#forecasting#bigquery#sql optimization#bigframes#bqml
One-click install
npx skills add https://github.com/AubreyHan/SKILL_Repo --skill developing-with-bigquery-aubreyhan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: developing-with-bigquery
Source: https://github.com/AubreyHan/SKILL_Repo/tree/main/developing-with-bigquery
Command: npx skills add https://github.com/AubreyHan/SKILL_Repo --skill developing-with-bigquery-aubreyhan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill removes the guesswork from working in BigQuery by providing a single source of guidance for SQL performance, BigFrames development, and BigQuery ML and AI workflows.

Core Features & Use Cases

  • Query optimization guidance for pruning columns, pushing filters early, reusing expressions, and choosing the right intermediate materialization strategy.
  • BigFrames coding standards for staying in the cloud, using built-in accessors, avoiding unnecessary pandas downloads, and selecting the right ML workflow.
  • BigQuery ML and AI function routing for forecasting, evaluation, embedding generation, generative table extraction, contribution analysis, and vector search.
  • Use case: a data analyst can optimize a slow warehouse query, build a scalable feature pipeline in BigFrames, and then forecast demand or generate embeddings without switching tools or violating platform-specific rules.

Quick Start

Ask for help optimizing a BigQuery query, writing BigFrames code, or using a BigQuery ML and AI function, and include your table schema, goal, and data size so the right guidance can be applied immediately.

Frequently Asked Questions about developing-with-bigquery

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I optimize slow BigQuery SQL queries?▼

To optimize slow BigQuery SQL queries, apply column pruning, predicate pushdown, expression reuse, and intermediate materialization strategies to reduce scanned data and improve execution performance.

What is the best way to write BigFrames code for warehouse-scale analytics?▼

The best way to write BigFrames code is to stay in the cloud processing environment, use built-in accessors, and avoid unnecessary pandas downloads to maintain scalability for warehouse-scale analytics.

How do I use BigQuery ML for forecasting and vector search?▼

Use BigQuery ML for forecasting and vector search by applying correct AI.FORECAST and VECTOR_SEARCH syntax, requiring remote model setup and proper AI.GENERATE_EMBEDDING configurations for warehouse-scale data.

Can I generate embeddings and evaluate models directly in BigQuery?▼

Yes, you can generate embeddings and evaluate models directly in BigQuery by using AI.GENERATE_EMBEDDING and AI.EVALUATE syntax within your SQL workflows to process warehouse-scale data.

Does BigFrames work with pandas for local data processing?▼

BigFrames avoids local pandas downloads to keep processing in the cloud, using built-in accessors instead to maintain scalable warehouse-level analytics without violating platform-specific rules.

Related Skills

Explore More Data & Analytics Skills→
Stream-claimsStream-claims

ml-data-fetch-annotate

Fetch ML datasets from Redshift and generate annotated PDFs for error analysis.

Official
Advanced
interflownexinterflownex
2

bigquery-ai-ml

Integrate Vertex AI machine learning and generative capabilities into BigQuery SQL workflows.

Community
Advanced
AubreyHanAubreyHan

notebook-guidance

Organize and validate Jupyter notebook workflows for data analysis and BigQuery investigations.

Community
Advanced
REVREBELREVREBEL

bigquery-analytics

Optimize BigQuery warehouse design with partitioning, clustering, and SQL tuning.

Official
Intermediate