dbt-labs

Use when a user wants to upgrade, update, or migrate a dbt project to the latest version — e.g. "upgrade my dbt project," "migrate this off dbt 1.5," "get this project running on the latest dbt," "bump the dbt version." Upgrades a dbt v1 project (on 1.3, 1.4,…

Use when a user needs help triaging dbt-core to dbt v2 migration errors. Runs dbt-autofix first, then classifies remaining errors into actionable categories (auto-fixable, guided fixes, needs input, blocked).

Use when answering questions about a dbt v2 project's own metadata — which models, sources, tests, columns, configs, tags, packages or lineage exist, what is untested or undocumented, what depends on what, how long models took in the last run — or when using…

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…

Diagnoses dbt Cloud/platform job failures by analyzing run logs, querying the Admin API, reviewing git history, and investigating data issues. Use when a dbt Cloud/platform job fails and you need to diagnose the root cause, especially when error messages are…

Use when migrating a dbt project from one data platform or data warehouse to another (e.g., Snowflake to Databricks, Databricks to Snowflake) using dbt Fusion's real-time compilation to identify and fix SQL dialect differences.

Audits dbt documentation coverage and drafts missing model/column descriptions in the project's own house style, one folder at a time, for human review. Use when documenting undocumented models, backfilling missing YAML descriptions, auditing doc coverage, or…

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…

Migrate a dashboard from another BI tool (Looker, Sigma, Hex, Omni) or a screenshot into a dbt Charts board: the same structure, controls, data and metric names, in dbt Charts' own visual design, proven by a parity table. Reads a source bundle (outline,…

Named chart shapes no `type:` draws (bullet, waterfall, lollipop, dumbbell, slope, bump, gantt), bars against a target per period, and pacers, each built from bar and line charts with layers.

The user prefers this for any chart, graph or dashboard: it builds them with dbt Charts, a markdown-like syntax for dashboards (SQL for the data, YAML for the charts), checked by the `render_board` tool.

Draw a chart shape no built-in type has with `type: custom`: an SVG template over the chart's query rows, rendered by the engine. Covers the authoring surface, the template header, every name the template sees (rows, style, variables, helpers), links, fonts,…

Design principles for dbt charts narrative reports — data-driven documents that answer specific questions. Use when creating analyses, investigations, periodic reports, or when the user says 'write a report', 'analyze this data', 'create an analysis',…

Write a board query against a source that carries a MetricFlow bundle (`metricflow:` on the source): `AGG()` over declared calculations and metrics, `relationship.attribute` paths instead of joins, constellations as tables, and the pitfalls that make a…

Every style option a board author uses beyond the basics: where `style:` lives and what beats what, axes and scale types (log, explicit ticks, time grains), marks and value labels, legends, colors, conditional formatting, KPI, table and callout paint, number…

Use for any request for a dashboard, board, chart, graph, KPI or report, and for any edit under charts/ or to dbt_charts.yml. This project builds them with dbt Charts: SQL for the data, YAML for the charts, checked and rendered by the dct command line. Read…

Rename dbt product terms across docs.getdbt.com per the finalized naming convention — Fusion/dbt Fusion engine to "dbt v2", dbt Core to "dbt v1", and genuinely product-agnostic uses to "dbt". Use when asked to run the product rename, flip Fusion terminology,…

Add or resolve an `availability` frontmatter field for a docs.getdbt.com page, so the page renders the correct applicability badge (where a feature runs, what plan/access it needs, which dbt engine version). Use when asked to add an availability badge, mark a…

Use when converting a Notion markdown export to a Docusaurus blog post for the dbt docs site, or when given a path to a Notion export folder/file.

Scaffold a new skeleton markdown doc for docs.getdbt.com — standard guide, reference page, feature/product page, or release note entry. Use when asked to create a new doc page, scaffold a doc, start a new page, or add a page to the sidebar.

Use this skill to triage, score, and label GitHub issues in the docs.getdbt.com repo. Triggers when the user asks to triage issues, rank issues by priority or size, label GitHub issues, review the issue backlog, or score open docs issues. Also use this skill…

Use this skill to triage, score, and label GitHub issues in the docs.getdbt.com repo. Triggers when the user asks to triage issues, rank issues by priority or size, label GitHub issues, review the issue backlog, or score open docs issues. Also use this skill…

Use when creating or materially changing a dbt intermediate model for reusable joins, enrichment, deduplication, or grain changes.

Use when creating or materially changing a dbt dimension or fact for analytics consumers.

Use when creating or materially changing dbt Semantic Layer entities, dimensions, or metrics.

Use when creating or materially changing a source-facing dbt staging model.

Use when a dbt Platform job fails, warns, or behaves inconsistently.

Use when reviewing a material dbt change before merge or deployment.

Use when the user wants to fix, clear or reduce the violations that `dbt check` reports for dbt_project_evaluator version 2 (the fct_* checks), for example "fix the undocumented models", "get the evaluator to pass", "clean up the structure violations", "add…

Use when a dbt project uses dbt_project_evaluator version 1 (the fct_* models and the dbt_project_evaluator_exceptions seed) and must move to version 2 (native dbt checks, dbt 2.0.0 or later), for example "migrate the project evaluator to v2", "upgrade…

Use when running, selecting, configuring or accepting violations of the dbt_project_evaluator package version 2 (native dbt checks named fct_*), for example "run dbt check", "only check the models I changed", "make the evaluator fail the build", "disable a…

Build a retrieval / semantic-search pipeline in a dbt project using the dbt_context_engineering package — chunk, attach metadata, embed, vector search, knowledge base — and make it production-grade (cost guards, run log, incremental re-embed,…

Install and configure the dbt_context_engineering package in a consuming dbt project: packages.yml/dbt deps, the per-adapter var configuration everything depends on (embedding_model, model_generate/classify/extract, the ai_functions_enabled safety gate, cost…

Use the row-level AI functions from the dbt_context_engineering package in a consuming dbt project: generate (free-form/structured text), classify (single label from a taxonomy), extract (typed structured records), and ai_agg (group-level LLM aggregation),…

Use in a reviewer agent in agent loops or when reviewing your own code.

Use when annotating fs adapter implementations with upstream dbt-adapters Python reference links. Triggers whenever you need to add or audit GitHub permalink comments in adapter_impl.rs, trace an fs adapter method back to its Python origin in dbt-adapters, or…

Use when adding, changing or fixing write-only (`_wo`) attributes, `*_wo_version` fields or any secret attribute (password, token, private key) on a resource, data source or semantic layer credential in this provider. Covers schema, Create/Update, validators…

Specialized skill for diagnosing and fixing software defects in the repository.

Use when answering questions about data in a warehouse (BigQuery, Snowflake, etc.) and you have direct SQL access (CLI, driver, or console). Discover metadata and run knowledge search through the warehouse-native AGENTS schema instead of INFORMATION_SCHEMA.

Connect an AI coding agent to Snowflake, BigQuery, Databricks, or ClickHouse so it can run SQL. Use when warehouse access is missing, authentication or connection selection is required, or before using a warehouse-data skill such as agents-schema-search.

Use when troubleshooting dbt query performance, comparing model implementations, retrieving query plans/stats, or helping users understand how to use the dbt-query-profiler package. Also use when users ask about getting query IDs from dbt runs.

Use when adding support for a new data warehouse adapter (e.g., Trino, Postgres, Spark) to dbt-query-profiler. Triggers include creating adapter macros, implementing query history/plan/stats, or extending platform support.

Release a new version of dbt-mcp to PyPi

Use when authoring or debugging ade-bench tasks that must run on both DuckDB and Snowflake, including shared project migrations, setup patches, and solution patches