dbt Analytics Project taste — ChatGPT prompt: what it does
dbt Analytics Project taste — a prompt for ChatGPT sets conventions for dbt models, tests, documentation, and CI. Use it while shaping an analytics project or revising its model structure.
CC0-1.0 ★ 178,201 updated 2026-10-24
Open on GitHubWhat dbt Analytics Project taste does
This prompt lays out conventions for organizing and building a dbt analytics project. It separates models into staging, intermediate, and marts: staging handles renames, casts, and light cleanup, while joins and business logic belong in later layers. Raw tables enter through source() in staging; other models use ref().
It calls for primary-key declarations with unique and not_null tests, plus relationships and accepted_values checks for selected fields. It also covers source freshness thresholds, YAML docs for marts, and incremental models with a unique_key and a window for late-arriving rows. CI guidance includes SQLFluff and slim CI using state:modified+ with deferral against production artifacts.
For Claude Code, the listed installation path is .claude/commands/prompts.csv.md. ChatGPT is a listed platform, but no separate installation command is provided for it.
What it helps with
- organize dbt models into staging, intermediate, and marts
- assign key and status tests to models
- document mart columns and table grain in YAML
- set up slim CI for pull requests
Example prompts for the agent
- Set conventions for a new dbt analytics project.
- Review these models and group them into staging, intermediate, and marts.
- Define tests and documentation for these dbt marts.
How to install dbt Analytics Project taste
How to use
Paste the text at the start of a chat or into project instructions
Manually: put the files in place
.claude/commands/prompts.csv.mdQuestions about dbt Analytics Project taste
How do I install dbt Analytics Project taste in ChatGPT?
Send the prompt in a ChatGPT message and ask it to apply the conventions to a dbt project. No separate ChatGPT installation command is listed.
What does dbt Analytics Project taste do?
It provides conventions for dbt model layers, SQL, tests, docs, and CI. Raw data is accessed with source() in staging models, while other models refer to data through ref().
How does the prompt handle slim CI?
For pull requests, it recommends state:modified+ and deferral against production artifacts so the build targets changed models.
Source text
prompts.csv · CC0-1.0
# dbt Analytics Project taste of a careful analytics engineer - Layer models into staging, intermediate and marts folders, with one staging model per source table. Confidence: 0.90 - Keep staging models to renaming, casting and light cleanup only; put joins and business logic in intermediate and mart models. Confidence: 0.90 - Reference raw data only through source() in staging models and use ref() everywhere else. Confidence: 0.95 - Name models with clear prefixes such as stg_, int_, fct_ and dim_ so their role is obvious in lineage graphs. Confidence: 0.85 - Declare a primary key for every model and test it with unique and not_null tests. Confidence: 0.95 - Add relationships and accepted_values tests on important foreign keys and status columns. Confidence: 0.85 - Configure source freshness checks with warn and error thresholds and run them before the main build. Confidence: 0.85 - Write SQL in lowercase with CTEs at the top, one CTE per logical step, and a final select from the last CTE. Confidence: 0.80 - Lint and format SQL with SQLFluff in CI so style debates never reach code review. Confidence: 0.80 - Use incremental models only when full refreshes are too slow, and always define unique_key and a late-arriving data window. Confidence: 0.85 - Materialize staging models as views and marts as tables or incremental models, unless profiling shows a better choice. Confidence: 0.75 - Keep business metrics defined once in the semantic layer or a single mart, not recalculated in every dashboard. Confidence: 0.85 - Document every mart model and its columns in YAML, including the grain of the table in plain words. Confidence: 0.90 - Run slim CI with state:modified+ and deferral against production artifacts so pull requests build only what changed. Confidence: 0.85 - Build each pull request into its own temporary schema and drop it after merge. Confidence: 0.80 - Pin dbt and package versions in packages.yml and the project requirements, and upgrade them deliberately. Confidence: 0.85 - Keep macros few and well tested; prefer readable SQL over clever Jinja. Confidence: 0.80 - Add unit tests for tricky transformation logic using dbt unit tests with small, explicit input fixtures. Confidence: 0.75 - Use snapshots for slowly changing dimensions only where history is genuinely needed by the business. Confidence: 0.75 - Tag models by owner and domain, and route test failures to the owning team's channel. Confidence: 0.70 - Avoid select * in marts; list columns explicitly so schema changes upstream do not silently leak through. Confidence: 0.85 - Set model contracts on public marts that other teams or tools depend on. Confidence: 0.70
© f · CC0-1.0 · f/prompts.chat