Equips your coding agent with a data engineer, pipeline commands and skills for Airflow, dbt, Spark and data quality.
by wshobson· Data & analyticsUnclaimed · Yours? Claim it
4 images
About
Data Engineering is a plugin from Seth Hobson's agents collection (wshobson/agents), a community project. It adds two subagents, two commands and four skills for building data pipelines: a data engineer for pipelines, warehouses and streaming, a backend architect for the services around them, a pipeline-design command, a step-by-step data-driven feature workflow, and skills for Airflow, dbt, Spark and data quality. What's inside - data-engineer: designs batch and streaming pipelines, warehouses and lakehouses across Spark, dbt, Airflow, Kafka and the cloud data services, with data quality checks, monitoring and cost in mind. - backend-architect: designs the APIs, services and event-driven architecture around your data. - /data-pipeline: designs and implements a batch or streaming pipeline, from ingestion and orchestration to dbt transformations, data quality checks and monitoring. - /data-driven-feature: takes a feature from exploratory analysis and an A/B test design through instrumentation, build and gradual rollout to statistical analysis, stopping for your approval between phases. - airflow-dag-patterns (skill): DAG design, operators, sensors, testing and deployment for Apache Airflow. - dbt-transformation-patterns (skill): model layers, naming, tests, documentation and incremental models in dbt. - spark-optimization (skill): partitioning, caching, shuffles and memory tuning for slow Spark jobs. - data-quality-frameworks (skill): validation with Great Expectations, dbt tests and data contracts. How to install In Claude Code, run /plugin marketplace add wshobson/agents, then /plugin install data-engineering@claude-code-workflows. Codex CLI uses codex plugin marketplace add wshobson/agents. The repository also has install routes for Cursor, OpenCode, Antigravity CLI, GitHub Copilot and Pi. Good to know - It's a community plugin, not a data vendor's. - It doesn't connect to your warehouse or pipelines; it guides your agent's design and code. - /data-driven-feature keeps its working files in a .data-driven-feature folder in your project.
Once it’s added
“Design a real-time streaming pipeline from Kafka to BigQuery.”
“Build a modern data stack with dbt, Snowflake and Fivetran for dimensional modeling.”
“Create a data quality framework that monitors and alerts on data anomalies.”
“Build a change data capture pipeline to keep two databases in sync.”
“This Spark job is slow. Tune its partitioning, shuffles and memory.”
“Write an Airflow DAG for our nightly batch load, with tests.”
Before you add it
Reads only
Your pipeline requirements, schemas and code · Your Airflow DAGs, dbt models and Spark jobs
Makes changes · your agent can ask first
Pipeline designs, Airflow DAGs and dbt models · Data quality checks and monitoring · Feature plans and A/B test designs
Each with its own page
From people who use it
Step by step
Nothing new reaches your agent until a person has looked at it.
No reviews yet. Used Data Engineering? Say how it went.
Write a reviewRuns on your machine.
Runs on your machine.
/plugin marketplace add wshobson/agents /plugin install data-engineering@claude-code-workflows
Scanned and passed · checked 4 h ago
Plugins people install alongside Data Engineering.
Scanned on every change, and again when our rules improve.
Claude CodeSupported
OpenClawSupportedTell us and a person on the trust team will look at it. Or email [email protected].
Nobody has shared how they use Data Engineering yet.
Security scan
Passed
Safe to install in every agent it supports. Claude plugins.
Plugins people install alongside Data Engineering.
Lets your agent search, query and chart the data in your own Metabase, and build questions and dashboards with your permissions.
Lets your agent query your PostHog analytics, triage errors, and create feature flags and experiments from plain-language asks.
Data analytics skills for product managers: SQL from plain English, cohort retention analysis and A/B test reads with a ship-or-stop call.
