---
title: "dak"
description: "This plugin provides a specialized suite of skills for data engineers and database practitioners working on Google Cloud. It acts as an expert assistant, allowing you to use natural language prompts in your preferred cod"
canonical: https://agentpluginsdirectory.com/plugins/dak
last-updated: 2026-09-21
---

# dak
This plugin provides a specialized suite of skills for data engineers and database practitioners working on Google Cloud. It acts as an expert assistant, allowing you to use natural language prompts in your preferred coding agent to architect complex data pipelines, transform data with dbt, write Spark and BigQuery SQL notebooks, and orchestrate end-to-end workflows across GCP's data ecosystem.
- Slug: dak
- Publisher: Google LLC
- Repository: https://github.com/gemini-cli-extensions/data-agent-kit-starter-pack
- Manifest: plugin.json
- Version: 0.11.0
- License: Apache-2.0
- Category (editorial): databases
- Skills: 33 (accidental-data-loss-prevention, bigquery-ai-ml, bigquery-bigframes, bigquery-data-transfer-service, bigquery-graph, bigquery-sql, bigtable-basics, building-data-apps, data-autocleaning, dataform-bigquery, dbt-bigquery, discovering-gcp-data-assets, enforcing-resource-attribution, federate-lakehouse-catalog, gcp-composer-troubleshooting, gcp-data-pipelines, gcp-dataflow, gcp-managed-airflow-dag-authoring, gcp-managed-airflow-migrations, gcp-managed-airflow-recommendations, gcp-pipeline-orchestration, gcp-pipeline-resource-provisioning, gcp-spark, gcs-security-assessment, google-cloud-auth-verification, google-cloud-storage-basics, google-cloud-storage-bucket-architect, google-cloud-storage-fuse, managing-python-dependencies, ml-best-practices, notebook-guidance, resolving-mcp-region-configs, schema-mapping)
- MCP servers: 10 (alloydb-postgres, bigquery, bigtable, cloud-sql-postgresql, cloud-storage, dataproc, knowledge_catalog, notebook, spanner, visualization)
- Stars: 188
- Repository created: 2026-04-02
- Repository last pushed: 2026-09-20
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/dak
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What dak does, in the publisher's words

> [!NOTE] > This extension is currently in beta (pre-v1.0), and may see breaking changes until the first stable release (v1.0).

This plugin provides a specialized suite of skills and MCP tools for data engineers and database practitioners working on Google Cloud. It acts as an expert assistant, allowing you to use natural language prompts in your preferred coding agent to architect complex data pipelines, transform data with dbt, write Spark and BigQuery SQL notebooks, create and troubleshoot Dataflow pipelines, and orchestrate end-to-end workflows across the Google Cloud data ecosystem (BigQuery, Spanner, BigLake, Dataproc, etc.).

> [!IMPORTANT] > We Want Your Feedback! > Please share your thoughts with us by opening an issue on GitHub. Your input is invaluable and helps us improve the project for everyone.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/gemini-cli-extensions/data-agent-kit-starter-pack/HEAD/README.md

## Skills

- accidental-data-loss-prevention: **STOP AND VERIFY**: Before running any command or tool that results in irreversible data loss, you MUST obtain explicit user consent. When in doubt, ask. It is better to wait for confirmation than to accidentally delete production data or critical project assets. Use this for: SQL: DROP TABLE/VI…
- 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, detect outliers, find key drivers, or leverage generative AI capabilities in BigQuery.
- bigquery-bigframes: Generates Python code using BigQuery DataFrames (BigFrames), the pandas/scikit-learn-style API over BigQuery. Use when writing BigFrames code or doing pandas-style dataframe/ML work against BigQuery (e.g. in a notebook). Don't use for SQL-first workflows or the google-cloud-bigquery client library…
- bigquery-data-transfer-service: Discovers and inspects BigQuery Data Transfer Service (DTS) configurations.
- bigquery-graph: Provides guidelines and best practices for querying and defining property graphs and semantic graphs in BigQuery using GQL (Graph Query Language). Use when creating property graphs or querying graph topologies in BigQuery.
- bigquery-sql: Provides BigQuery SQL query optimization techniques, execution best practices, and performance tuning rules for high-efficiency querying. Use when optimizing BigQuery SQL queries, reducing query costs, or designing performant SQL transformations.
- bigtable-basics: Assists in provisioning instances/tables, designing performant schemas, and querying data in Bigtable. Use when designing Bigtable row keys, configuring column families, writing SQL queries or client library code (Java, Go, Python) for Bigtable, or diagnosing performance/hotspotting issues. Also us…
- building-data-apps: Build modern data apps, dashboards, and interactive reports using either React + Vite or Streamlit. Includes optional Gemini Data Analytics chat integration for an AI powered "chat with your data" experience. Relevant when any of the following conditions are true: 1. User explicitly requests to bui…
- data-autocleaning: Automated data quality and transformation capabilities for Dataform/dbt/BigQuery
- dataform-bigquery: Expertise in generating clean, correct, and efficient Dataform pipeline
- dbt-bigquery: Expert guidance for creating, modifying, and optimizing dbt pipelines
- discovering-gcp-data-assets: Finds and inspects data assets within Google Cloud. Relevant when any of the following conditions are true: 1. The user request involves finding, exploring, or inspecting data assets in Google Cloud, such as: BigQuery datasets, tables, or views, BigLake catalog or tables, Spanner instances, dat…
- enforcing-resource-attribution
- federate-lakehouse-catalog
- gcp-composer-troubleshooting
- gcp-data-pipelines
- gcp-dataflow
- gcp-managed-airflow-dag-authoring
- gcp-managed-airflow-migrations
- gcp-managed-airflow-recommendations
- gcp-pipeline-orchestration
- gcp-pipeline-resource-provisioning
- gcp-spark
- gcs-security-assessment
- google-cloud-auth-verification
- google-cloud-storage-basics
- google-cloud-storage-bucket-architect
- google-cloud-storage-fuse
- managing-python-dependencies
- ml-best-practices
- notebook-guidance
- resolving-mcp-region-configs
- schema-mapping

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

## MCP servers

- alloydb-postgres: transport: stdio; command: node ${PLUGIN_ROOT}/mcp/bin/mcp_proxy_bundle.cjs https://alloydb.googleapis.com/mcp; env: X_GOOG_PROXY_HEADERS
- bigquery: transport: stdio; command: node ${PLUGIN_ROOT}/mcp/bin/mcp_proxy_bundle.cjs https://bigquery.googleapis.com/mcp; env: X_GOOG_PROXY_HEADERS
- bigtable: transport: stdio; command: node ${PLUGIN_ROOT}/mcp/bin/mcp_proxy_bundle.cjs https://bigtableadmin.googleapis.com/mcp; env: X_GOOG_PROXY_HEADERS
- cloud-sql-postgresql: transport: stdio; command: node ${PLUGIN_ROOT}/mcp/bin/mcp_proxy_bundle.cjs https://sqladmin.googleapis.com/mcp; env: X_GOOG_PROXY_HEADERS
- cloud-storage: transport: stdio; command: node ${PLUGIN_ROOT}/mcp/bin/mcp_proxy_bundle.cjs https://storage.googleapis.com/storage/mcp; env: X_GOOG_PROXY_HEADERS
- dataproc: transport: stdio; command: node ${PLUGIN_ROOT}/mcp/bin/mcp_proxy_bundle.cjs https://dataproc-$GCP_REGION.googleapis.com/mcp; env: X_GOOG_PROXY_HEADERS
- knowledge_catalog: transport: stdio; command: node ${PLUGIN_ROOT}/mcp/bin/mcp_proxy_bundle.cjs https://dataplex.googleapis.com/mcp; env: X_GOOG_PROXY_HEADERS
- notebook: transport: stdio; command: npx -y -p git+https://github.com/gemini-cli-extensions/data-agent-kit-starter-pack.git notebook-tools --mode=notebook
- spanner: transport: stdio; command: node ${PLUGIN_ROOT}/mcp/bin/mcp_proxy_bundle.cjs https://spanner.googleapis.com/mcp; env: X_GOOG_PROXY_HEADERS
- visualization: transport: stdio; command: npx -y -p git+https://github.com/gemini-cli-extensions/data-agent-kit-starter-pack.git notebook-tools --mode=visualization

Read from the plugin's own mcp.json. Environment variable names only, never values.