Agent skill · data analytics · github
snowflake-semanticview
Create, alter, and validate Snowflake semantic views using Snowflake CLI (snow). Use when asked to build or troubleshoot semantic views/semantic layer definitions with CREATE/ALTER SEMANTIC VIEW, to validate semantic-view DDL against Snowflake via CLI, or to guide Snowflake CLI installation and connection setup.
Why this skill is useful
Provides specific commands and workflows for creating and validating Snowflake semantic views that the AI wouldn't reliably generate on its own.
What it needs
Requires snowflake-cli installed locally. About 2k tokens when loaded. Last updated 2026-08-07. 37,534 stars on the source repository.
What this skill does
Snowflake Semantic Views One-Time Setup Verify Snowflake CLI installation by opening a new terminal and running snow --help. If Snowflake CLI is missing or the user cannot install it, direct them to https://docs.snowflake.com/en/developer-guide/snowflake-cli/installation/installation. Configure a Snowflake connection with snow connection add per https://docs.snowflake.com/en/developer-guide/snowflake-cli/connecting/configure-connections#add-a-connection. Use the configured connection for all validation and execution steps. Workflow For Each Semantic View Request 1. Confirm the target database, schema, role, warehouse, and final semantic view name. 2. Confirm the model follows a star schema (facts with conformed dimensions). 3. Draft the semantic view DDL using the official syntax: https://docs.snowflake.com/en/sql-reference/sql/create-semantic-view 4. Populate synonyms and comments for each dimension, fact, and metric: Read Snowflake table/view/column comments first (preferred source): https://docs.snowflake.com/en/sql-reference/sql/comment If comments or synonyms are missing, ask whether you can create them, whether the user wants to provide text, or whether you should draft suggestions for approval. 5. Use SELECT statements with DISTINCT and LIMIT (maximum 1000 rows) to discover relationships between fact and dimension tables, identify column data types, and create more meaningful comments and synonyms for columns. 6. Create a temporary validation name (for example, append tmpvalidate) while keeping the same database and schema. 7. Always validate by sending the DDL to Snowflake via Snowflake CLI before finalizing: Use snow sql to execute the statement with the configured connection. If flags differ by version, check snow sql --help and use the connection option shown there. 8. If validation fails, iterate on the DDL and re-run the validation step until it succeeds. 9. Apply the final DDL (create or alter) using the real semantic view name. 10. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills github/snowflake-semanticview