dive

Generate dbt marts SQL, manifest, React TSX component, and verification seed rows.

1|1|Updated Mar 26, 2026
One-click install
npx skills add https://github.com/Soria-Inc/soria-stack --skill dive-soria-inc
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dive
Source: https://github.com/Soria-Inc/soria-stack/tree/main/dive
Command: npx skills add https://github.com/Soria-Inc/soria-stack --skill dive-soria-inc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The dive skill eliminates ad-hoc dashboard work by enforcing a grain-first, repeatable workflow that produces a dbt marts model, a manifest-driven data contract, a React TSX dive component, DivesPage registration, and a set of verification seed rows so dashboards are correct, auditable, and maintainable.

Core Features & Use Cases

  • Three Questions gating: forces question, audience, and visualization clarity before any SQL is written.
  • Grain-first model design: guided grain definition, dimension listing, and filter compatibility to avoid ratio and aggregation bugs.
  • End-to-end artifact creation: produces dbt marts SQL, manifest file, TSX component wired to useDiveData/useDiveVerifications, DivesPage registration, and adds ~15–20 rows to the shared verifications seed.
  • Iterative dev loop & testing: dbt run/seed/test guidance, vite-dbt manifest sync notes, and artifact output for verification and promotion.
  • Use case: building a new corporate dashboard (e.g., MA enrollment by company) with verify checks and methodology content embedded for auditability.

Quick Start

Build a new dive for "MA enrollment by company" and guide me through the three questions, grain design, dbt marts SQL, manifest, TSX component, and verify checks.

Frequently Asked Questions about dive

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a production-ready dbt marts model with a React dashboard component?

Use the dive skill to generate a complete dashboard package: dbt marts SQL, a manifest file, a React TSX component, and DivesPage registration. It enforces grain-first design to ensure SQL aggregations and component filters align correctly.

What is grain-first design and why is it needed for dbt marts SQL?

Grain-first design defines the row level of your dbt marts model before writing SQL. It prevents ratio and aggregation bugs by ensuring manifest columns and filters match the model output exactly, creating a reliable data contract for interactive exploration.

How do I add verification checks to a dbt dashboard model?

The dive skill adds 15-20 verify rows to a shared verifications seed file. After running dbt seed and dbt run, these rows validate the marts SQL output and embed methodology content for auditability.

Can I use manifest-driven filters in a React TSX component with dbt?

Yes, the dive skill produces a manifest data contract that maps directly to React TSX component filters. The generated component uses useDiveData and useDiveVerifications hooks to sync interactive filters with the dbt marts output.

Do I need to manually register new dashboards in my React application?

No, the dive skill automatically handles DivesPage registration during artifact creation. It outputs the necessary component integration and methodology content so dashboards are discoverable without manual routing configuration.

What is the best way to structure a dbt marts model for interactive data exploration?

Structure dbt marts models using table materialization with a guided grain definition and explicit dimension listing. This approach ensures manifest-driven filters work correctly in React components and avoids aggregation bugs during interactive exploration.