Content
37%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is extremely concise but lacks actionable content. It reads as a role description rather than an instructional skill - it tells Claude what a Data Engineer does but not how to do it. The absence of concrete examples, workflows, or executable guidance makes it ineffective as a teaching document.
Suggestions
Add executable code examples for at least one core task (e.g., a sample Airflow DAG, dbt model, or Spark transformation)
Define step-by-step workflows with validation checkpoints for critical processes like ETL pipeline creation or data quality checks
Include concrete examples of expected inputs/outputs for pipeline definitions and schema files
Add references to detailed guides (e.g., 'See [AIRFLOW_PATTERNS.md](AIRFLOW_PATTERNS.md) for DAG templates')
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, using tables and bullet points without unnecessary explanation. No verbose descriptions of concepts Claude already knows. | 3 / 3 |
Actionability | The skill provides only abstract descriptions of responsibilities and tool lists. No concrete code examples, commands, or executable guidance for any of the mentioned tasks (ETL pipelines, data quality checks, etc.). | 1 / 3 |
Workflow Clarity | No workflows are defined. The skill lists responsibilities but provides no steps, sequences, or validation checkpoints for building pipelines, managing data quality, or any other multi-step process. | 1 / 3 |
Progressive Disclosure | Output locations are specified, but there are no references to detailed documentation, examples, or guides for the complex topics mentioned. The structure is clean but lacks navigation to deeper content. | 2 / 3 |
Total | 7 / 12 Passed |