analytics-engineer — Claude Code skill: dbt models and SQL transformations
analytics-engineer — a skill for Claude Code, Codex, Cursor, Copilot, Gemini CLI and OpenCode that builds dbt transformations and dimensional schemas. Triggered when you need SQL models, tests, incremental fact tables or metrics.
LicenseRef-MIT-Commons-Clause 207 installs ★ 1,183 updated 2026-10-23
npx skills add borghei/Claude-Skills --skill analytics-engineer -a claude-codeWhat analytics-engineer does
Acts as a senior analytics engineer: designs star and snowflake schemas, writes stg_, int_ and mart dbt models, configures materialization (view, table, incremental), adds tests (unique, not_null, relationships) and YAML docs, registers metrics in the semantic layer.
Before building models, the agent asks about row grain, data sources and refresh cadence. Runs dbt build, checks test pass rate and verifies dashboard numbers. No FFmpeg or external dependencies, just SQL and Jinja.
Includes full examples for dimension models (dim_customer) and fact tables (fct_orders), materialization strategy by layer (staging as view, intermediate as ephemeral, marts as table or incremental), test schema and dbt project structure.
What it helps with
- write a dbt staging model from a source table with column renaming
- design a star schema for sales mart
- set up an incremental fact table partitioned by date
- add unique and not_null tests to all primary keys
- register sum and count_distinct metrics in the semantic layer
Example prompts for the agent
- Write a staging model
stg_crm__customersfromraw.customers - Design a star schema for orders: which dim and fct tables do I need
- Create an incremental model
fct_orders, partition byorder_date
How to install analytics-engineer
1Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill analytics-engineer -a claude-code2Manually: put the files in place
~/.claude/skills/analytics-engineer/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/analytics-engineer/
1Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill analytics-engineer -a codex2Manually: put the files in place
.agents/skills/analytics-engineer/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill analytics-engineer -a cursor2Manually: put the files in place
.cursor/skills/analytics-engineer/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install borghei/Claude-Skills data-analytics/analytics-engineer/SKILL.md2Manually: put the files in place
.github/skills/analytics-engineer/SKILL.md1Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill analytics-engineer -a gemini-cli2Platform CLI
gemini skills install https://github.com/borghei/Claude-Skills --path data-analytics/analytics-engineerManually: put the files in place
.devin/skills/analytics-engineer/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add borghei/Claude-Skills --skill analytics-engineer -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about analytics-engineer
How to install analytics-engineer in Claude Code?
Run npx skills add borghei/Claude-Skills --skill analytics-engineer -a claude-code, the skill will appear in ~/.claude/skills/analytics-engineer/SKILL.md.
What does the analytics-engineer skill do?
Builds dbt transformation models, designs dimensional schemas, writes staging, intermediate and mart SQL, configures materialization and tests, registers metrics in the semantic layer.
Which dbt materialization should I use for a fact table?
For large facts use incremental with date partitioning. For small lookup tables table is enough. Staging layer is usually view.