How does it handle data quality and validation?

The skill integrates patterns for Great Expectations and dbt tests to monitor data freshness, volume anomalies, and schema validation.

Can this skill help with data transformation modeling?

Yes, it is highly proficient in dbt (data build tool) best practices, including staging, intermediate, and mart layer design.

Does it support bioinformatics or specialized analytics?

Yes, it includes specific domain knowledge for bioinformatics pipelines using Nextflow and Allotrope, as well as KPI dashboard design.

Which databases does the Data Assistant skill support?

It provides specialized patterns and optimization techniques for PostgreSQL, Snowflake, BigQuery, and general SQL-based systems.

Data Engineering & Analytics Assistant

Name: Data Engineering & Analytics Assistant
Author: diegouis

bydiegouis

•

データベース管理

Architects, optimizes, and manages end-to-end data pipelines, warehouse schemas, and analytics workflows using industry-standard frameworks.

The Data Assistant skill transforms Claude into a specialized data engineer and analyst capable of handling the entire data lifecycle. It provides expert guidance on designing robust ETL/ELT pipelines with Airflow and Spark, implementing dbt transformation layers, and architecting scalable data warehouses using star or snowflake schemas. Beyond infrastructure, the skill excels at SQL performance tuning, exploratory data analysis, and implementing rigorous data quality frameworks like Great Expectations. It also supports niche domains such as bioinformatics pipelines and automated spreadsheet operations, making it an essential companion for building production-grade data platforms.

主な機能

01Advanced dbt modeling including staging, marts, and incremental materialization

022 GitHub stars

03Visual pipeline and schema diagramming via Excalidraw integration

04Comprehensive data quality frameworks and anomaly detection implementation

05SQL performance optimization with EXPLAIN ANALYZE and advanced window functions

06ETL/ELT pipeline orchestration using Airflow DAGs and Spark processing patterns

ユースケース

01Orchestrating complex bioinformatics or financial analytics pipelines with custom infrastructure

02Designing and optimizing a Snowflake or BigQuery data warehouse for business intelligence

03Building a production transformation layer with dbt and automated data quality testing

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add diegouis/provectus-marketplace data-assistant

For use in Claude.ai and ChatGPT

Download Skill