BigQuery plugins

Build production-ready data pipelines with Apache Airflow and dbt, manage scalable data warehouses, and implement vector search and RAG systems using embedding models and vector databases.

Perform business analysis workflows — KPI frameworks, predictive models, real-time dashboards, TAM/SAM/SOM calculations, and multi-year financial modeling for startups — using Python, SQL, and cloud data warehouses like Snowflake and BigQuery.

Build and manage end-to-end data analytics workflows: implement A/B testing with statistical rigor, design reliable analytics tracking, create interactive D3.js visualizations, architect scalable database schemas, and optimize SQL for cloud-native databases.

Automates finance and accounting workflows including month-end close, SOX compliance testing, financial reporting, journal entries, reconciliations, and variance analysis, with integrations to Slack and BigQuery for notifications and data querying.

Write SQL across data warehouses, profile datasets, and generate interactive dashboards and publication-quality charts. Connect to BigQuery, Amplitude, Hex, and Atlassian for integrated data analysis and reporting.

Scaffold, build, evaluate, deploy, publish, and monitor AI agents on Google Cloud using the Google ADK Python SDK.

Execute deterministic, reproducible bioinformatics analyses locally — from genome annotation and pharmacogenomics to scRNA-seq and metagenomics — with built-in privacy and AI-driven skill orchestration.

Manage AWS data lakes and analytics workflows: create and query Iceberg tables on S3 Tables, run Athena SQL across Glue and Redshift catalogs, ingest data from JDBC databases, Redshift, Snowflake, BigQuery, and DynamoDB, audit Glue Data Catalog assets, and store/query vector embeddings on S3 Vectors for semantic search and RAG.

Accelerate website creation and optimization with 103 structured skills spanning research, brand strategy, design, content, SEO, analytics, performance, security, and deployment—each providing expert-level prompts for tasks like auditing accessibility, fixing Core Web Vitals, conducting competitive analysis, running experiments, and managing incident response.

Run a full digital marketing agency from Claude Code — plan campaigns, execute paid/SEO/email/social, audit performance, manage brands, and generate client deliverables across 158 skills and 25 agents.

Guides data engineering projects through a structured Spec-Driven Development workflow with 58 specialized agents for pipeline design, schema modeling, SQL optimization, data quality, lakehouse architecture, and AI/ML infrastructure. Generates visual diagrams, HTML documentation, code reviews, and git-aware status reports.

Build and orchestrate GCP data pipelines using natural language — discover assets, profile and transform data with dbt, Dataform, Spark, and BigQuery, then deploy and monitor workflows on Cloud Composer and Dataproc.

Write geospatial SQL queries against BigQuery, Snowflake, Wherobots, and Postgres with automatic cost estimation, mandatory dry-run validation, and interactive map rendering of results via Dekart.

Create, analyze, and file USPTO, EPO, and PCT patent applications from invention disclosures — including prior art search across 100M+ patents via BigQuery, claims drafting, specification writing, compliance checking, and diagram generation — all within Claude Code without external MCP servers.

Profile, analyze, and QA data workflows across multiple SQL dialects — craft optimized queries, apply statistical methods, profile unfamiliar datasets, and catch common analysis pitfalls with a reproducible quality checklist.

Query BigQuery datasets, retrieve table metadata, and generate analytical insights including time-series forecasting and contribution analysis using standard SQL and BigQuery AI/ML functions.

Generate forecasting datasets and fine-tune models using the Lightningrod Python SDK, with seed data from BigQuery, local files, web search, or public repositories, and guided training patterns for SFT or GRPO.

Build high-quality computer vision datasets and models with FiftyOne: import/export datasets, run inference, evaluate predictions, find duplicates, visualize embeddings, and develop custom plugins — all from within Claude.

Orchestrate multi-platform marketing campaigns from Claude using the Hyper MCP — manage paid ads on Google, Meta, TikTok, Pinterest, Amazon, LinkedIn, plus organic social, SEO research, email outreach, competitor analysis, ad creative generation, and analytics integrations.

Query and model data through the Honeydew semantic layer: define entities, metrics, and dimensions from Snowflake or BigQuery sources, validate them, and explore data with structured queries or natural language.

Acquire, clean, compute, and visualize football data from multiple providers (StatsBomb, FBref, Wyscout, etc.) with built-in analytics skills, code review agents, and a searchable MCP documentation server.

Send Claude Code hook traces to BigQuery Agent Analytics for observability and monitoring of agent events across the full lifecycle.

Control SAP Datasphere via natural language to explore catalogs and schemas, design semantic models and views, build and optimize ETL flows and task chains, connect diverse data sources, migrate from BW/4HANA, govern metadata and security, activate business content, automate admin via CLI, and troubleshoot pipelines.

Generate optimized SQL queries from natural language for BigQuery, PostgreSQL, MySQL, and Snowflake; perform cohort analysis on CSV/Excel user data to compute retention rates, visualize trends, and detect anomalies; evaluate A/B tests with statistical significance, confidence intervals, and launch recommendations.

Delegate specialized development tasks to AI subagents that architect features with Mermaid diagrams and checklists, generate PRDs and specs, query SQL/BigQuery for data analysis, implement precise code from tasks.md, debug errors with root cause fixes, proactively review git diffs for quality/security, and analyze codebases for project guidance files.

Investigative journalism toolkit for OSINT ingestion, structured storage in BigQuery/PostgreSQL/SQLite, libel-defensive editorial review, multi-article series orchestration with deployment gates, and social media syndication to Facebook/X/LinkedIn/Bluesky/Threads.

Automates Dutch tax filing workflows for individuals and businesses by integrating Notion, Slack, BigQuery, and Microsoft 365 for client intake, document verification, return preparation, and objection drafting with automated reminders and quality checks.

Design AWS and GCP infrastructure using Terraform and Ansible patterns, build data pipelines with dbt and SQLMesh, generate and manage RFCs plus technical specs in Markdown, and automate local dev setups including direnv, git worktrees, and port allocations for Docker services.