- Home
- Skills
- Data & Databases
- Dbt Data Warehouse Modeler
Works with the AI Agents you already use
Dbt Data Warehouse Modeler
Architect and author modular dbt models with automated schema tests for Snowflake, BigQuery, and Databricks.
$15
Dbt Data Warehouse Modeler
Example session with this skill installed
Create a staging model for the 'orders' table in the 'shopify' source, including unique and not_null tests for the order_id. Target is Snowflake.
- Read your context and instructions
- Compiled the dbt data warehouse
I have generated the staging model and the corresponding schema configuration for the Shopify orders data. This includes a modular SQL file using Jinja macros and a YAML file with the requested data quality tests.
dbt Model Deliverables
File: models/staging/shopify/stg_shopify__orders.sql
with source as (
select * from {{ source('shopify', 'orders') }}
),
renamed as (
select
id as order_id,
customer_id,
order_number,
total_price,
created_at as order_timestamp,
_fivetran_synced
from source
)
select * from renamed
File: models/staging/shopify/src_shopify.yml
version: 2
sources:
- name: shopify
database: raw
schema: shopify
tables:
- name: orders
description: Raw order data from Shopify.
models:
- name: stg_shopify__orders
description: Staged Shopify orders with cleaned column names.
columns:
- name: order_id
description: The primary key for this table.
tests:
- unique
- not_null
- name: order_timestamp
description: The timestamp when the order was placed.
Next steps
- Run
dbt compileto verify the Jinja syntax is correct for your Snowflake environment. - Execute
dbt test --select stg_shopify__ordersto validate the unique and not_null constraints. - Update the
databaseandschemafields in the YAML file to match your raw data location.
Connects securely to your tools. The creator never sees your data.
About this skill
Building a modern data stack requires more than just writing SQL queries. This skill automates the creation of modular dbt architectures, ensuring your models follow industry standard staging, intermediate, and marts layering.
What it does
- Layered Modeling builds structured directory hierarchies for staging, intermediate, and marts layers to keep logic separated.
- Macro Implementation authors SQL models using Jinja
refandsourcemacros for proper dependency tracking. - Materialization Control configures table, view, and incremental strategies including merge keys for optimized performance.
- Automated Testing generates
schema.ymlfiles containing unique, not-null, accepted-values, and relationship tests. - Documentation Scaffolding creates YAML documentation blocks to ensure data lineage and column descriptions are captured.
How it works
- Analyze Source Data by identifying the raw tables and required transformations for the target warehouse.
- Scaffold Directory Structure to align with modular dbt patterns across the project workspace.
- Generate SQL Models using Jinja templating to handle dependencies and materialization logic.
- Produce Schema YAMLs to define tests and documentation for every new model created.
Frameworks & tools
This skill is built for dbt Core and dbt Cloud. It generates optimized SQL and configuration for Snowflake, BigQuery, and Databricks environments.
Why this beats prompting it yourself
Generic LLMs often mix logic layers or forget to include essential Jinja macros, leading to broken DAGs. This skill enforces a deterministic workflow that ensures every model has the correct materialization strategy and accompanying test suite from the start.
Use cases
- Scaffold a new dbt project with standard staging and marts directories.
- Convert raw SQL scripts into modular dbt models with proper
reftags. - Generate comprehensive schema tests for existing data warehouse tables.
- Implement incremental loading logic for large-scale Snowflake or BigQuery datasets.
Known limitations
This skill focuses on SQL and YAML generation within the active workspace. It does not execute dbt commands, manage warehouse infrastructure, or handle secret management beyond env placeholders.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Data & Databases.
Restricted to active project workspace. Does not execute dbt run/test commands or manage cloud infrastructure. Requires pre-existing warehouse credentials via environment variables.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 3 days ago
- Software
- Zero global installationorelevated privileges required.
File System Read/Write (strictly scoped to current project workspace `./`).
Permissions
Target Use Cases: - Write an incremental dbt model for data warehouse. - Structure dbt staging and mart models with schema tests. - Create dbt YAML documentation with unique and not_null tests.