Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

dbt Model Builder

A dbt workflow skill that discovers project conventions first, then mandates `dbt build` and output verification before calling a model done.

Data & AnalyticsIntermediate★ 127⑂ 11AI score 9/10Last updated: Oct 1, 2026

What it does

  • Triggers whenever you ask to create, add, write, implement, or modify a dbt model, table, or SQL transformation.
  • Reads dbt_project.yml and 2–3 existing models to learn naming, config, and SQL patterns before writing anything.
  • Finds similar models (fct_*, *agg*) to mirror join types, aggregation patterns, and NULL handling.
  • After writing: dbt compile for syntax, then mandatory dbt build — compile alone is never treated as done.
  • Verifies real output with dbt show: exact column names, sane row counts, plausible values, no surprise NULLs; hand-checks calculations against a sample row.
  • Stops and reassesses after 3+ failed builds, and re-reads the original request before declaring completion.

Who it's for

  • Analytics engineers and data engineers working in dbt projects daily.
  • Anyone burned by an assistant declaring success after a passing compile.
  • Teams that want new models to automatically follow existing repo conventions.

Examples

  1. "Build fct_customer_monthly_revenue from orders" → learns existing fct patterns, writes SQL, builds, then verifies grain and revenue math with dbt show.
  2. "Implement the staging model per the column spec in schema.yml" → matches column names exactly and cross-checks against actual output.
  3. "Add a new join and derived column to an existing model" → previews upstream data, edits, builds, and checks the row-count impact.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/AltimateAI/data-engineering-skills/HEAD/skills/dbt/creating-dbt-models/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/dbt/creating-dbt-models folder from the GitHub repo AltimateAI/data-engineering-skills into my ~/.claude/skills/creating-dbt-models/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/AltimateAI/data-engineering-skills.git && mkdir -p ~/.claude/skills && cp -r data-engineering-skills/skills/dbt/creating-dbt-models ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal (git required).
  2. Clone the repo: git clone https://github.com/AltimateAI/data-engineering-skills.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy just this skill: cp -r data-engineering-skills/skills/dbt/creating-dbt-models ~/.claude/skills/
  5. Run Claude Code from inside your dbt project directory (the dbt CLI and a working profiles.yml connection are prerequisites).
  6. Ask something like "create a model for ..." or "modify this model" and the skill activates automatically.
  7. Point your default target at a dev environment so builds never hit production.
View source on GitHub ↗License: MIT