oz-skills: Skill for Claude Code

dbt Model Index

When to Use

• Before writing any BigQuery SQL against production data
• When the task has not already explicitly stated which models/tables to query
• When resolving a vague or ambiguous data question into the right BigQuery tables

How to Set Up This Skill

This skill is a curated index of your dbt models. Each entry describes a model (a BigQuery table), what it contains, and what types of questions it is best suited to answer.

To customize this index for your project:

• Organize models into logical domain sections (e.g., Users, Activity, Revenue, Events)
• For each model, include: the table name, a 1–2 sentence description of its grain and content, and "Useful for:" bullets covering common query patterns
• Note key join keys, standard filters, and partition fields where relevant

---

[Domain: e.g., Users & Identity]

your_model_name

Brief description of what this model contains. One row per [entity]. Include what makes this model's grain unique and the most important fields.

Useful for:

• [Type of question this model answers, e.g., user counts, cohort sizes]
• [Another use case, e.g., filtering to a specific user segment]
• [Common join pattern, e.g., joining to other tables as the canonical user dimension]

---

another_model_name

Description of this model and its grain.

Useful for: [Brief use case description]

---

[Domain: e.g., Activity & Engagement]

your_activity_model

Description of the activity signal (e.g., what counts as "active"), the grain, and the time dimension.

Useful for:

• [Use case 1, e.g., daily/weekly active user metrics]
• [Use case 2, e.g., retention analysis]

---

your_engagement_model

Description.

Useful for:

• [Use case 1]
• [Use case 2]

---

[Domain: e.g., Revenue & Subscriptions]

your_revenue_model

Description of the revenue grain (e.g., one row per customer per day, or one row per subscription event).

Useful for:

• [Use case 1, e.g., MRR/ARR reporting]
• [Use case 2, e.g., churn analysis]