MCPInstall

answering-natural-language-questions-with-dbt

by dbt-labs OfficialData & Databases

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.

Installs
1K
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/dbt-labs/dbt-agent-skills --skill answering-natural-language-questions-with-dbt
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads answering-natural-language-questions-with-dbt automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Answering Natural Language Questions with dbt

Overview

Answer data questions using the best available method: semantic layer first, then SQL modification, then model discovery, then manifest analysis. Always exhaust options before saying "cannot answer."

Use for: Business questions from users that need data answers

  • "What were total sales last month?"
  • "How many active customers do we have?"
  • "Show me revenue by region"

Not for:

  • Validating model logic during development
  • Testing dbt models or semantic layer definitions
  • Building or modifying dbt models
  • dbt run, dbt test, or dbt build workflows

Decision Flow

flowchart TD
    start([Business question received])
    check_sl{Semantic layer tools available?}
    list_metrics[list_metrics]
    metric_exists{Relevant metric exists?}
    get_dims[get_dimensions]
    sl_sufficient{SL can answer directly?}
    query_metrics[query_metrics]
    answer([Return answer])
    try_compiled[get_metrics_compiled_sql<br/>Modify SQL, execute_sql]
    check_discovery{Model discovery tools available?}
    try_discovery[get_mart_models<br/>get_model_details<br/>Write SQL, execute]
    check_manifest{In dbt project?}
    try_manifest[Analyze manifest/catalog<br/>Write SQL]
    cannot([Cannot answer])
    suggest{In dbt project?}
    improvements[Suggest semantic layer changes]
    done([Done])

    start --> check_sl
    check_sl -->|yes| list_metrics
    check_sl -->|no| check_discovery
    list_metrics --> metric_exists
    metric_exists -->|yes| get_dims
    metric_exists -->|no| check_discovery
    get_dims --> sl_sufficient
    sl_sufficient -->|yes| query_metrics
    sl_sufficient -->|no| try_compiled
    query_metrics --> answer
    try_compiled -->|success| answer
    try_compiled -->|fail| check_discovery
    check_discovery -->|yes| try_discovery
    check_discovery -->|no| check_manifest
    try_discovery -->|success| answer
    try_discovery -->|fail| check_manifest
    check_manifest -->|yes| try_manifest
    check_manifest -->|no| cannot
    try_manifest -->|SQL ready| answer
    answer --> suggest
    cannot --> done
    suggest -->|yes| improvements
    suggest -->|no| done
    improvements --> done

Quick Reference

PriorityConditionApproachTools
1Semantic layer activeQuery metrics directlylist_metrics, get_dimensions, query_metrics
2SL active but minor modifications needed (missing dimension, custom filter, case when, different aggregation)Modify compiled SQLget_metrics_compiled_sql, then execute_sql
3No SL, discovery tools activeExplore models, write SQLget_mart_models, get_model_details, then show/execute_sql
4No MCP, in dbt projectAnalyze artifacts, write SQLRead target/manifest.json, target/catalog.json

Approach 1: Semantic Layer Query

When list_metrics and query_metrics are available:

  1. list_metrics - find relevant metric
  2. get_dimensions - verify required dimensions exist
  3. query_metrics - execute with appropriate filters

If semantic layer can't answer directly (missing dimension, need custom logic) → go to Approach 2.

Approach 2: Modified Compiled SQL

When semantic layer has the metric but needs minor modifications:

  • Missing dimension (join + group by)
  • Custom filter not available as a dimension
  • Case when logic for custom categorization
  • Different aggregation than what's defined
  1. get_metrics_compiled_sql - get the SQL that would run (returns raw SQL, not Jinja)
  2. Modify SQL to add what's needed
  3. execute_sql to run the raw SQL
  4. Always suggest updating the semantic model if the modification would be reusable
-- Example: Adding sales_rep dimension
WITH base AS (
    -- ... compiled metric logic (already resolved to table names) ...
)
SELECT base.*, reps.sales_rep_name
FROM base
JOIN analytics.dim_sales_reps reps ON base.rep_id = reps.id
GROUP BY ...

-- Example: Custom filter
SELECT * FROM (compiled_metric_sql) WHERE region = 'EMEA'

-- Example: Case when categorization
SELECT
    CASE WHEN amount > 1000 THEN 'large' ELSE 'small' END as deal_size,
    SUM(amount)
FROM (compiled_metric_sql)
GROUP BY 1

Note: The compiled SQL contains resolved table names, not {{ ref() }}. Work with the raw SQL as returned.

Approach 3: Model Discovery

When no semantic layer but get_all_models/get_model_details available:

  1. get_mart_models - start with marts, not staging
  2. get_model_details for relevant models - understand schema
  3. Write SQL using {{ ref('model_name') }}
  4. show --inline "..." or execute_sql

Prefer marts over staging - marts have business logic applied.

Approach 4: Manifest/Catalog Analysis

When in a dbt project but no MCP server:

  1. Check for target/manifest.json and target/catalog.json
  2. Filter before reading - these files can be large
# Find mart models in manifest
jq '.nodes | to_entries | map(select(.key | startswith("model.") and contains("mart"))) | .[].value | {name: .name, schema: .schema, columns: .columns}' target/manifest.json

# Get column info from catalog
jq '.nodes["model.project_name.model_name"].columns' target/catalog.json
  1. Write SQL based on discovered schema
  2. Explain: "This SQL should run in your warehouse. I cannot execute it without database access."

Suggesting Improvements

When in a dbt project, suggest semantic layer changes after answering (or when cannot answer):

GapSuggestion
Metric doesn't exist"Add a metric definition to your semantic model"
Dimension missing"Add dimension_name to the dimensions list in the semantic model"
No semantic layer"Consider adding a semantic layer for this data"

Stay at semantic layer level. Do NOT suggest:

  • Database schema changes
  • ETL pipeline modifications
  • "Ask your data engineering team to..."

Rationalizations to Resist

You're Thinking...Reality
"Semantic layer doesn't support this exact query"Get compiled SQL and modify it (Approach 2)
"No MCP tools, can't help"Check for manifest/catalog locally
"User needs this quickly, skip the systematic check"Systematic approach IS the fastest path
"Just write SQL, it's faster"Semantic layer exists for a reason - use it first
"The dimension doesn't exist in the data"Maybe it exists but not in semantic layer config

Red Flags - STOP

  • Writing SQL without checking if semantic layer can answer
  • Saying "cannot answer" without trying all 4 approaches
  • Suggesting database-level fixes for semantic layer gaps
  • Reading entire manifest.json without filtering
  • Using staging models when mart models exist
  • Using this to validate model correctness rather than answer business questions

Common Mistakes

MistakeFix
Giving up when SL can't answer directlyGet compiled SQL and modify it
Querying staging modelsUse get_mart_models first
Reading full manifest.jsonUse jq to filter
Suggesting ETL changesKeep suggestions at semantic layer
Not checking tool availabilityList available tools before choosing approach

FAQ

What does the answering-natural-language-questions-with-dbt skill do?

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.

How do I install answering-natural-language-questions-with-dbt?

Run npx skills add https://github.com/dbt-labs/dbt-agent-skills --skill answering-natural-language-questions-with-dbt in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/answering-natural-language-questions-with-dbt/ (personal) or .claude/skills/answering-natural-language-questions-with-dbt/ (project).

Which AI agents can use answering-natural-language-questions-with-dbt?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is answering-natural-language-questions-with-dbt safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains answering-natural-language-questions-with-dbt?

It is published by dbt-labs in dbt-labs/dbt-agent-skills, and it is an official skill from the maker of the technology it covers. It has 1,038 recorded installs.

More from dbt-labs/dbt-agent-skills

View all →

using-dbt-for-analytics-engineering

dbt-labs/dbt-agent-skills

Builds and modifies dbt models, writes SQL transformations using ref() and source(), creates tests, and validates results with dbt show. Use when doing any dbt work - building or modifying models, debugging errors, exploring unfamiliar data sources, writing tests, or evaluating impact of changes.

OfficialData & Databases1.2K installs

fetching-dbt-docs

dbt-labs/dbt-agent-skills

Retrieves and searches dbt documentation pages in LLM-friendly markdown format. Use when fetching dbt documentation, looking up dbt features, or answering questions about dbt Cloud, dbt Core, or the dbt Semantic Layer.

OfficialData & Databases1.1K installs

adding-dbt-unit-test

dbt-labs/dbt-agent-skills

Creates unit test YAML definitions that mock upstream model inputs and validate expected outputs. Use when adding unit tests for a dbt model or practicing test-driven development (TDD) in dbt.

OfficialTesting & QA1.1K installs

running-dbt-commands

dbt-labs/dbt-agent-skills

Formats and executes dbt CLI commands, selects the correct dbt executable, and structures command parameters. Use when running models, tests, builds, compiles, or show queries via dbt CLI. Use when unsure which dbt executable to use or how to format command parameters.

OfficialData & Databases1.1K installs

configuring-dbt-mcp-server

dbt-labs/dbt-agent-skills

Generates MCP server configuration JSON, resolves authentication setup, and validates server connectivity for dbt. Use when setting up, configuring, or troubleshooting the dbt MCP server for AI tools like Claude Desktop, Claude Code, Cursor, or VS Code.

OfficialData & Databases1K installs

building-dbt-semantic-layer

dbt-labs/dbt-agent-skills

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.

OfficialData & Databases1K installs

Popular data & databases skills

View category →

supabase-postgres-best-practices

supabase/agent-skills

Postgres best practices maintained by Supabase, for Postgres running anywhere. Load this skill BEFORE writing or changing anything that lives in a Postgres database: creating or altering tables and columns (including choosing column types), schema design, migrations and declarative schema files, RLS policies and the tests that verify them, indexes, triggers, database functions, queues and scheduled jobs (pgcron, pgmq), vector/semantic search (pgvector), and restoring dumps (pgrestore) or importing data. Also load it when diagnosing slow queries, high CPU, timeouts, EXPLAIN plans, connection exhaustion, locking, bloat, or rows visible to the wrong user or tenant. This is not just a performance guide — schema, migration, security, and SQL authoring tasks need these rules too, even for a one-column change or a single query.

OfficialData & Databases462.2K installs

prisma-client-api

prisma/skills

Prisma Client API reference covering model queries, filters, operators, and client methods. Use when writing database queries, using CRUD operations, filtering data, or configuring Prisma Client. Triggers on "prisma query", "findMany", "create", "update", "delete", "$transaction".

OfficialData & Databases393.5K installs

prisma-database-setup

prisma/skills

Deprecated compatibility name for prisma-orm-setup. Use only when a user or existing integration explicitly invokes prisma-database-setup; otherwise select prisma-orm-setup.

OfficialData & Databases392.3K installs

prisma-cli

prisma/skills

Prisma ORM 7 CLI reference for existing Prisma 7 applications or explicitly selected Prisma 7 workflows. Covers prisma init, generate, migrate, db, dev, studio, and mcp. For setup, connection repair, or Prisma 8, use prisma-orm-setup; not the Prisma Platform CLI.

OfficialData & Databases390.8K installs

prisma-postgres

prisma/skills

Deprecated compatibility name for prisma-postgres-setup. Use only when a user or existing integration explicitly invokes prisma-postgres; otherwise select prisma-postgres-setup.

OfficialData & Databases384.4K installs

prisma-driver-adapter-implementation

prisma/skills

Required reference for Prisma ORM 7 SQL driver adapter work. Use when implementing or modifying adapters, adding database drivers, or touching SqlDriverAdapter, Transaction, savepoint, result mapping, or DriverAdapterError behavior. Covers current transaction lifecycle, optional savepoint hooks, original database-error preservation, and verification.

OfficialData & Databases378.9K installs