Semantic Model Builder
Turns a metric definition that only lives in someone's head into a validated YAML file your dbt Semantic Layer, or a similar framework, can actually read.
Overview
Semantic Model Builder documents a metric, dimension, or entity the moment a stakeholder asks "how is this calculated?" and no canonical definition exists yet, or when you're setting up a dbt Semantic Layer and need real YAML.
What it covers
- Identifies whether you're documenting a metric, a dimension, or an entity, and picks the matching framework.
- Gathers the calculation logic, business context, data source, grain, and known edge cases.
- Generates a starter YAML template, then validates required fields, types, and cross-references.
- Adds dbt-specific field names and constraints when the target is dbt Semantic Layer.
- Saves the final metric, dimension, and entity definitions as separate YAML files.
Part of Data Analytics Skills
This is one of 31 skills in the Data Analytics Skills library, in the Documentation & Knowledge group.
Installation
- Clone the repo once:
git clone https://github.com/nimrodfisher/data-analytics-skills.git - Copy just this skill:
cp -r data-analytics-skills/02-documentation-knowledge/semantic-model-builder ~/.claude/skills/(or~/.agents/skills/for Codex) - Ask your agent something like "define our activation rate metric as a dbt semantic model" and it activates on its own.
See the Data Analytics Skills entry for the full library.
Related assets
Frontend Design
Generates distinctive, production-grade UI that avoids generic "AI slop," with bold typography, cohesive color, and precise motion, implemented as real code.
Graphify
Turns a codebase, plus its docs, PDFs, images, and video, into a queryable knowledge graph that a coding agent can traverse instead of grepping raw files, and never guesses silently: every edge is tagged EXTRACTED, INFERRED, or AMBIGUOUS so you know what was found versus inferred.
Caveman
Makes your coding agent answer in a stripped down, high signal style that keeps every technical fact and cuts filler, saving output tokens on chat style questions.