data-assistant

Engineer ETL/ELT pipelines, dbt transformations, and Airflow orchestration.

Updated Aug 23, 2026

Search Tags:#analytics #dbt #data engineering #sql #etl #airflow #data warehousing

Ready to run

npx skills add https://github.com/diegouis/provectus-marketplace --skill data-assistant

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: data-assistant
Source: https://github.com/diegouis/provectus-marketplace/tree/main/plugins/proagent-data/skills/data-assistant
Command: npx skills add https://github.com/diegouis/provectus-marketplace --skill data-assistant

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines the creation and optimization of data pipelines, transformations, and analytics, enabling efficient data processing and insightful reporting.

Core Features & Use Cases

Data Pipeline Development: Build robust ETL/ELT pipelines using tools like Airflow and dbt.
SQL Optimization: Tune SQL queries for performance across various databases.
Data Warehousing & Modeling: Design and implement effective data warehouse schemas.
Exploratory Data Analysis: Perform in-depth analysis to uncover data patterns and insights.
Use Case: You need to build a daily data pipeline to ingest sales data from a transactional database, transform it using dbt, and load it into a Snowflake data warehouse for business intelligence reporting.

Quick Start

Use the data-assistant skill to help design a star schema for customer and order data.

Frequently Asked Questions about data-assistant

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

FAQPage Schema

How do I build an ETL pipeline with dbt and Airflow?▼

Building an ETL pipeline with dbt and Airflow involves orchestrating data extraction, transforming it using dbt models, and scheduling the workflows via Airflow for automated data processing. This Skill designs and implements these robust ETL/ELT pipelines end-to-end.

How do I optimize slow SQL queries in a data warehouse?▼

Optimizing SQL queries in a data warehouse requires analyzing query execution plans and tuning them for your specific database architecture. This Skill tunes and optimizes SQL queries to improve performance across various database platforms.

What is the best way to design a star schema for business analytics?▼

Designing a star schema for business analytics involves structuring dimension and fact tables to support efficient querying and reporting. This Skill helps you design and implement effective data warehouse schemas tailored to your data modeling needs.

Can I use this to set up data quality frameworks and EDA?▼

Yes, you can use it to set up data quality frameworks and perform exploratory data analysis. It supports in-depth analysis to uncover data patterns and implements frameworks to ensure pipeline data integrity.

Does the data assistant support Spark processing and bioinformatics pipelines?▼

Yes, the data assistant supports Spark processing and bioinformatics pipelines. It covers a broad range of data engineering tasks including large-scale Spark processing and specialized bioinformatics data workflows.

What are the limitations when orchestrating ELT workflows with Airflow?▼

When orchestrating ELT workflows with Airflow, limitations typically involve managing complex task dependencies and handling external system connectivity. This Skill helps navigate these constraints by designing robust orchestration architecture upfront.