DATA ENGINEERING / dbt-labs
Build the dbt Semantic Layer
Define semantic entities, dimensions and metrics using the specification supported by the project.
“Use when creating or modifying dbt Semantic Layer components — semantic models, metrics, dimensions, entities, measures, or time spines. Covers MetricFlow configuration, metric types (simple, derived, cumulative, ratio, conversion), and validation for both latest and legacy YAML specs.”
01 / THE REASONING
Why this made the selection.
- It builds dbt semantic models and metrics, and it chooses the latest or legacy spec from the project that is already there.
- Validation with both the project parser and MetricFlow is required, and text inside SQL or YAML is not executed as instructions.
- The definition routes by both project specification and engine compatibility, and separates entity grain, metric type and time-spine requirements.
- Model business metrics at a documented entity grain
02 / THE REVIEW RECORD
What we actually inspected.
Source review has boundaries.
A clear record is more useful than a “safe” badge.
Material inspected
- skills/dbt/skills/building-dbt-semantic-layer/SKILL.md
- README.md
- LICENSE
Our findings
- The workflow detects an existing semantic layer and routes to the latest or legacy spec instead of mixing them.
- Work is not complete until both documented validations pass.
- Embedded text in SQL comments, YAML values, and column descriptions must not be executed.
- Metric filters cannot reference columns that are not declared dimensions or entities.
- The definition routes by both project specification and engine compatibility, and separates entity grain, metric type and time-spine requirements.
Not established by this review
- The resource was not executed and its tools were not called.
- No skill execution, authenticated service operation, or outcome benchmark was performed.
- Not executed: it was not installed or run.
The review applies to the material and revision named here. A newer upstream release can change its behavior.
03 / PUT IT TO WORK
Add a skill to your workflow.
DOCUMENTED COMMAND
npx skills add dbt-labs/dbt-agent-skills/skills/dbt/skills/building-dbt-semantic-layer Run in your terminal to choose your AI tools, project or global scope, and installation method. This short command follows the current upstream version; the review covers the revision shown above.
Optional: install the reviewed revision
Keeps the original source and installer version where recorded, while leaving your AI tools and installation scope for you to choose.
npx skills add https://github.com/dbt-labs/dbt-agent-skills/tree/7c7b5fa39e61694f1ae2b8ea1b8065e195c814ce/skills/dbt/skills/building-dbt-semantic-layer - Install the pinned skill directory interactively, retaining its bundled references and scripts.
- Inspect current semantic YAML and engine version, then load the matching latest/legacy reference.
- Regenerate the manifest before MetricFlow validation, add a time spine where required and query a known result.
Before you start
- A compatible dbt project and the selected CLI/MCP capabilities
- Warehouse or platform credentials only for operations that require them
04 / FOLLOW THE EVIDENCE
The source trail.
Our notes are separate from the original resource.
Check upstream before adopting a new version.
- Pinned skill definition ↗Checked
https://github.com/dbt-labs/dbt-agent-skills/blob/7c7b5fa39e61694f1ae2b8ea1b8065e195c814ce/skills/dbt/skills/building-dbt-semantic-layer/SKILL.md
Supports: summary, whySelected, bestFor, limitations, install, access, review
https://github.com/dbt-labs/dbt-agent-skills/blob/7c7b5fa39e61694f1ae2b8ea1b8065e195c814ce/README.md
Supports: install
- Apache-2.0 licence ↗Checked
https://github.com/dbt-labs/dbt-agent-skills/blob/7c7b5fa39e61694f1ae2b8ea1b8065e195c814ce/LICENSE
Supports: license
https://raw.githubusercontent.com/dbt-labs/dbt-agent-skills/7c7b5fa39e61694f1ae2b8ea1b8065e195c814ce/skills/dbt/skills/building-dbt-semantic-layer/SKILL.md
Supports: upstreamDescription, review.notTested, review.reviewedAt