Skip to content
TrustedSkillsbeta
Back to all skills

Answering Natural Language Questions With Dbt

Official
dbt-labs·vlatest·data·Apache-2.0

This skill uses dbt to answer natural language questions about your data warehouse, providing instant insights and reducing query complexity.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add dbt-labs/dbt-agent-skills --skill answering-natural-language-questions-with-dbt -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

dbt-labs

Matched to the vendor's own GitHub organisation.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned dbt-labs/dbt-agent-skills at 0d094169f5.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
0d094169f5
Manifest
skills/dbt/skills/answering-natural-language-questions-with-dbt/SKILL.md
Scanned
1 file, 196 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

This skill enables AI agents to interpret and answer natural language questions directly against your data warehouse using dbt. It bridges the gap between human inquiry and raw SQL by automatically generating and executing queries based on conversational input.

When to use it

  • Ad-hoc Analysis: Quickly investigate trends or anomalies without writing complex SQL manually.
  • Stakeholder Reporting: Generate instant answers for business questions from non-technical team members.
  • Exploratory Data Science: Rapidly prototype hypotheses by querying large datasets through simple text prompts.
  • Automated Dashboards: Feed dynamic, conversational insights into reporting tools that require real-time data validation.

Key capabilities

  • Parses natural language queries into executable SQL statements.
  • Leverages dbt models and macros to ensure query accuracy and consistency.
  • Executes queries directly against the connected data warehouse.
  • Returns structured results based on the specific question asked.

Example prompts

  • "Show me the total revenue for each product category last quarter."
  • "Which customer segment has the highest churn rate in the past 30 days?"
  • "Compare average order values between the US and EU regions for January."

Tips & gotchas

Ensure your dbt models are up to date before asking questions, as the skill relies on the current state of your data definitions. While powerful for standard aggregations, complex logic may require refining your natural language prompt to be more specific about joins or filters.