dbt-labs/dbt-agent-skills

A curated collection of Agent Skills for working with dbt, to help AI agents understand and execute dbt workflows more effectively.

What it solves

This project provides a curated collection of "Agent Skills" designed to help AI agents perform dbt (data build tool) workflows more accurately and efficiently. It bridges the gap between a general-purpose AI agent and the specific technical requirements of analytics engineering, semantic layers, and dbt project migrations.

How it works

Instead of using manual slash commands, these skills consist of folders containing instructions, scripts, and resources. When an AI agent (such as Claude Code, Cursor, or GitHub Copilot) is installed with these skills, it automatically loads the relevant skill based on the user's natural language prompt. This allows the agent to execute dbt-specific tasks without the user needing to specify the exact command or flag.

Who it’s for

Analytics engineers and data engineers who use dbt for data modeling, testing, and governance, as well as those migrating dbt projects across platforms or upgrading dbt Core versions.

Highlights

  • Comprehensive dbt Coverage: Includes skills for building models, writing unit tests, and managing dbt Mesh governance (contracts, versions, access).
  • Semantic Layer Integration: Enables agents to create metrics and dimensions with MetricFlow and answer business questions by querying the semantic layer.
  • Migration Support: Provides specialized one-off skills for migrating dbt Core to the Fusion engine or upgrading dbt Core versions.
  • Broad Agent Compatibility: Works with agents that support the Agent Skills specification, including Claude Code, Cursor, Cline, and GitHub Copilot via the Vercel Skills CLI or Tessl.
  • Operational Tooling: Includes capabilities for troubleshooting job failures and configuring the dbt MCP server.

Related

  • Project
    kangarooking/kangarooking-skills

    A collection of structured, open-source Agent Skills and workflows for AI agents to automate tasks ranging from content creation and 3D generation to complex software engineering.

  • Project
    samber/cc-skills-golang

    A curated set of AI‑agent “skills” that encode Go best‑practice guidance (style, testing, concurrency, libraries, etc.). Installable via the universal `skills` CLI or by cloning into the discovery folder of Claude Code, Copilot, Gemini, Cursor, etc. Skills are atomic, human‑reviewed, and dramatically improve AI‑assistant accuracy on Go code reviews.

  • Project
    sanjay3290/ai-skills

    A collection of portable, standardized skills for AI coding assistants that enable them to interact with databases, productivity tools, and cloud infrastructure.

  • Project
    coreyhaines31/marketingskills

    A collection of AI agent skills that provide specialized marketing knowledge and workflows for tasks like SEO, copywriting, and conversion optimization.

  • Project
    mattpocock/skills

    A collection of composable AI agent skills that apply software engineering fundamentals like TDD and domain modeling to prevent common AI coding failures.