dbt-ce-setup
Install and configure the dbt_context_engineering package in a consuming dbt project: packages.yml/dbt deps, the per-adapter var configuration everything depends on (embedding_model, model_generate/classify/extract, the ai_functions_enabled safety gate, cost ceilings, output caps), and per-engine prerequisites for Snowflake (Cortex), Databricks (serverless/DBR), BigQuery (Vertex connection, Gemini thinking budget), and Redshift (Amazon Bedrock inference UDFs provisioned via CREATE EXTERNAL MODEL). Use whenever a user is setting up or configuring the package: 'how do I install dbt_context_engineering', 'which vars for Snowflake/Databricks/BigQuery/Redshift', 'how do I create the Bedrock functions for Redshift', "my AI model raises 'AI functions are disabled'", 'why is my BigQuery bill full of thinking tokens', "Redshift says permission denied for language mlfunc", or 'the package cannot find my connection'. Trigger even when the user mentions only one var or one error, since the config surface is interdependen
Source facts
- Repository
- dbt-labs/dbt-context-engineering
- Last source activity
- October 28, 2026 at 18:16
- Detected SKILL.md language
- English
- Stars
- 49
- Forks
- 3
Install options
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Review the source files
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Showing SKILL.md
| name | dbt-ce-setup |
|---|---|
| description | Install and configure the dbt_context_engineering package in a consuming dbt project: packages.yml/dbt deps, the per-adapter var configuration everything depends on (embedding_model, model_generate/classify/extract, the ai_functions_enabled safety gate, cost ceilings, output caps), and per-engine prerequisites for Snowflake (Cortex), Databricks (serverless/DBR), BigQuery (Vertex connection, Gemini thinking budget), and Redshift (Amazon Bedrock inference UDFs provisioned via CREATE EXTERNAL MODEL). Use whenever a user is setting up or configuring the package: 'how do I install dbt_context_engineering', 'which vars for Snowflake/Databricks/BigQuery/Redshift', 'how do I create the Bedrock functions for Redshift', "my AI model raises 'AI functions are disabled'", 'why is my BigQuery bill full of thinking tokens', "Redshift says permission denied for language mlfunc", or 'the package cannot find my connection'. Trigger even when the user mentions only one var or one error, since the config surface is interdependen |