What do I need to use dbt Model Spec?

What the model represents; Layer; Sources / upstream refs; The business logic.

Is dbt Model Spec free to use?

Yes — run it free in the browser playground (no API key needed for the sponsored trial, or bring any provider key), or install it into Claude Code, Cursor, ChatGPT and more via npx pm-claude-skills. MIT-licensed and open source.

dbt Model Spec

Q: How do I know the dbt Model Spec output is good?

The skill verifies itself against its own quality checks: The grain is stated as "one row per ___" and the key is tested unique + not_null; Sources/refs use `source()`/`ref()`, not hard-coded table names; Every column has a type and description (the schema contract); Tests cover the grain key, FKs (relationships), and enum columns.

🔵 Stable🕐 updated 2026-06-28 🔷 SkillSpec L3 pm-dataeng

Spec a dbt model — its grain, sources, transformations, tests, and materialization. Use when asked to design a dbt model, plan a data transformation, write a staging/intermediate/mart model spec, or define dbt tests for a table. Produces a model spec — purpose & grain, lineage (sources → refs), the transformation logic, column definitions, dbt tests, materialization choice, and the skeleton SQL/YAML.

▶ Run it free — no key needed 📝 Grade your existing draft View SKILL.md ↗

What to give it

▸What the model represents — and its grain (one row per ___ — the single most important decision).

▸Layer — staging, intermediate, or mart (dimension/fact). Conventions differ per layer.

▸Sources / upstream refs — the raw tables or models it builds on.

▸The business logic — joins, filters, aggregations, and any business rules.

✅ The bar it holds itself to

Every skill in this library self-verifies — these are this skill's own quality checks, straight from its definition.

✓The grain is stated as "one row per ___" and the key is tested unique + not_null

✓Sources/refs use `source()`/`ref()`, not hard-coded table names

✓Every column has a type and description (the schema contract)

✓Tests cover the grain key, FKs (relationships), and enum columns

✓Materialization is justified; incremental models declare a unique_key and is_incremental() logic

✓Fan-out joins that could break the grain are flagged

⚠️ What it refuses to do

Do not leave the grain ambiguous — an untested, unclear grain is how duplicate rows and wrong metrics happen

Do not hard-code upstream table names — use ref()/source() so lineage and environments work

Do not ship a model with no tests — untested models silently rot; the grain key at minimum must be tested

Do not default everything to a table — pick the materialization the use justifies (views for light, incremental for large append-only)

Do not bury business logic without comments — the next analyst must understand the rules

Install

npx pm-claude-skills add --agent claude   # or codex · cursor · gemini · hermes
# or one-line MCP (every skill, any client):
claude mcp add pm-skills -- npx -y pm-claude-skills-mcp

Related skills

🔌 Embed this skill

Drop this on your blog, docs, or site — it renders a "Run this skill" card:

<div data-pm-skill="dbt-model-spec"></div>
<script src="https://mohitagw15856.github.io/pm-claude-skills/embed.js" async></script>

💬 Discussion

dbt Model Spec is one of 599 open-source professional AI agent skills — all SkillSpec L3. Try them all in the browser · ⭐ Star on GitHub · Browse the full catalog