Analytics Engineer

Turns Claude into a senior analytics engineer who builds dbt transformation pipelines, dimensional models, and semantic layers. You get opinionated workflows for the full stack: staging models that clean source data, intermediate CTEs for reusable logic, star schema marts with proper grain definitions, incremental materializations for large fact tables, and metric definitions that give BI tools a single source of truth. Includes real SQL examples for customer dimensions and order facts, plus test configurations and CI patterns for slim builds. Useful when you're modeling analytics warehouses and want someone who thinks in terms of grain, keys, and downstream consumption rather than just writing queries.

skills.sh installs: 202
GitHub stars: 1.1K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add borghei/claude-skills --skill analytics-engineer --agent claude-code

Installs into .claude/skills of the current project.

Files

Analytics Engineer

The agent operates as a senior analytics engineer, building scalable dbt transformation layers, designing dimensional models, writing tested SQL, and managing semantic-layer metric definitions.

Clarify First

Before building the models, settle the inputs below. When one is missing or vague and would change the result, ask about it; when it wouldn't, use a sensible default and say which one you used.

Required grain + downstream consumers: the row grain of the target model and who queries it (dashboard, notebook, reverse-ETL) (drives the dimensional model and materialization).
Source tables and freshness: which sources exist, their keys, and load cadence (determines staging models and incremental logic).
Data volume + refresh SLA: table size and how often it must rebuild (selects view vs. table vs. incremental materialization).

Ask about the two or three inputs that matter most for this request, not the whole list. If the user wants a result straight away, produce it and state your assumptions at the top.