How do I use Data & ML Engineering on Zeplik?

Sign in to Zeplik and ask in plain language, or type /data-ml-engineering in any chat to invoke it directly. The skill applies its method and returns a result you can refine in the same conversation.

Which AI model does the Data & ML Engineering skill use?

Any model you choose. Zeplik works across every model in one chat, so the Data & ML Engineering skill runs on your preferred model for the task.

Where does the Data & ML Engineering skill come from?

The Data & ML Engineering skill is adapted from the open-source wshobson/agents project (MIT) and tuned to run natively on Zeplik. The original source is linked on this page.

How much does the Data & ML Engineering skill cost?

Using the skill is free to start. You only spend Zeplik credits when the assistant runs, and new accounts begin with free credits.

Data & ML Engineering

Data and analytics skill, available on Zeplik

Data & ML Engineering is a ready-to-run data and analytics skill on Zeplik. Not for one-off dataset analysis (use analyze-dataset). Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer.

The Data & ML Engineering skill loads automatically when your request matches it, or you can invoke it directly by typing /data-ml-engineering in any chat. It works with attachments, connectors, and any model that supports the task, so you get the same expert method every time without setting anything up.

What the Data & ML Engineering skill can do

Design Airflow DAGs with operators, sensors, and backfill logic
Build dbt models with tests, docs, and incremental processing
Tune Spark jobs for partitioning, memory, and shuffle performance
Architect MLOps pipelines and recommender or ranking serving systems

Try these prompts on Zeplik

Pick a prompt to open it in the Zeplik app. If you are not signed in yet, your prompt is waiting for you the moment you do.

How the Data & ML Engineering skill works

/data-ml-engineering

Umbrella skill for production data and ML engineering: pipeline orchestration, transformation frameworks, distributed compute tuning, data quality enforcement, MLOps workflows, and recommender/ranking system architecture. The user describes their stack and the problem; deliver concrete DAGs, model code, configs, or architecture plans in the chat. For exploring or analyzing a specific dataset use analyze-dataset; for judging LLM output quality use llm-evaluation.

Dispatch table

Pick the reference file(s) that match the request, read them, then answer. Read at most 2-3 files per turn.

Topic	Read
Airflow DAG design, operators, sensors, backfills, testing	references/airflow-dag-patterns.md (+ --details.md)
dbt model organization, tests, docs, incremental processing	references/dbt-transformation-patterns.md (+ --details.md)
Spark performance: partitioning, memory, shuffle, tuning	references/spark-optimization.md (+ --details.md)
Data quality: Great Expectations, dbt tests, data contracts	references/data-quality-frameworks.md (+ --details.md)
End-to-end MLOps: data prep, training, deployment pipeline	references/ml-pipeline-workflow.md
Recommendation, ranking, and feed pipelines (top-K serving)	references/recsys-pipeline-architect.md

How to work

Identify the layer: ingestion/orchestration, transformation, compute tuning, quality, ML lifecycle, or serving. Ask one clarifying question only if the stack (Airflow vs Dagster, dbt vs raw SQL, batch vs streaming) is genuinely ambiguous.
Read the matching reference file(s) from the table above before answering.
Deliver runnable artifacts -- DAG files, dbt models, Spark configs, pipeline specs -- with a short rationale, matching the user's naming and conventions when they paste existing code.
If schema, sample rows, or job metrics are needed, ask the user to paste or upload them.

Usage

/data-ml-engineering $ARGUMENTS

How to use the Data & ML Engineering skill

Sign in to Zeplik
Create a free Zeplik account or sign in. New accounts start with free credits, so you can try the Data & ML Engineering skill right away.
Describe your data and analytics task
Ask in plain language, or type /data-ml-engineering to invoke the skill directly. Zeplik recognizes the Data & ML Engineering skill and applies its method.
Review and refine the result
Zeplik returns a clear, structured answer. Ask follow-ups in the same chat to refine it or take the next step.

Source and credit

Author: anthropic
License: MIT

Adapted from the open-source wshobson/agents project and tuned to run natively on Zeplik. View source on GitHub.

Frequently asked questions

What is the Data & ML Engineering skill?: Data & ML Engineering is a ready-to-run data and analytics skill on Zeplik. Not for one-off dataset analysis (use analyze-dataset). Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer.
How do I use Data & ML Engineering on Zeplik?: Sign in to Zeplik and ask in plain language, or type /data-ml-engineering in any chat to invoke it directly. The skill applies its method and returns a result you can refine in the same conversation.
Which AI model does the Data & ML Engineering skill use?: Any model you choose. Zeplik works across every model in one chat, so the Data & ML Engineering skill runs on your preferred model for the task.
Where does the Data & ML Engineering skill come from?: The Data & ML Engineering skill is adapted from the open-source wshobson/agents project (MIT) and tuned to run natively on Zeplik. The original source is linked on this page.
How much does the Data & ML Engineering skill cost?: Using the skill is free to start. You only spend Zeplik credits when the assistant runs, and new accounts begin with free credits.

Related data and analytics skills

More on Zeplik

Try Data & ML Engineering on Zeplik

Every model, one chat. Bring the Data & ML Engineering skill into your next conversation and let the assistant do the work.

Browse all skills