DATA ENGINEERING / dbt-labs
Answer Business Questions with dbt
Answer warehouse questions through existing semantic metrics before resorting to carefully scoped SQL.
“Writes and executes SQL queries against the data warehouse using dbt's Semantic Layer or ad-hoc SQL to answer business questions. Use when a user asks about analytics, metrics, KPIs, or data (e.g., "What were total sales last quarter?", "Show me top customers by revenue"). NOT for validating, testing, or building dbt models during development.”
01 / THE REASONING
Why this made the selection.
- It answers a business question from the semantic layer before it writes SQL, and it stops suggesting changes at the semantic model.
- Without a database or MCP tool it can still draft SQL, and it says it cannot execute that SQL.
- The definition distinguishes direct metric queries, modified compiled SQL, model discovery and manifest fallback, and excludes model-build workflows.
- Reuse a governed business metric with verified dimensions
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/answering-natural-language-questions-with-dbt/SKILL.md
- README.md
- LICENSE
Our findings
- The overview tries the semantic layer, then compiled SQL, then model discovery, then the manifest.
- query_metrics and execute_sql are MCP or CLI calls against the warehouse; without them the skill cannot execute SQL.
- Suggestions stay at the semantic layer and must not include schema or ETL changes.
- The skill does not validate or build dbt models.
- The definition distinguishes direct metric queries, modified compiled SQL, model discovery and manifest fallback, and excludes model-build workflows.
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/answering-natural-language-questions-with-dbt 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/answering-natural-language-questions-with-dbt - Install the pinned skill directory interactively, retaining its bundled references and scripts.
- Clarify time range, business definition and required grouping, then discover metrics/dimensions.
- Use model/artifact discovery only when needed; bound data access and report the query and interpretation used.
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/answering-natural-language-questions-with-dbt/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/answering-natural-language-questions-with-dbt/SKILL.md
Supports: upstreamDescription, review.notTested, review.reviewedAt