data-engineer

Data Engineer Agent. ETL 파이프라인, 데이터 웨어하우스, 데이터 레이크 구축을 담당합니다.

Quality

35%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/data-engineer/SKILL.md

Quality

Discovery

32%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description identifies the data engineering domain and lists high-level responsibilities but lacks the explicit trigger guidance ('Use when...') that is critical for skill selection. It uses appropriate third-person voice but needs more specific concrete actions and natural user keywords to be effective in a multi-skill environment.

Suggestions

Add an explicit 'Use when...' clause with trigger scenarios like 'Use when the user asks about building data pipelines, ETL workflows, data warehouse design, or data lake architecture'

Include more natural trigger terms users might say: 'data pipeline', 'batch jobs', 'data ingestion', 'Spark', 'Airflow', 'dbt', 'schema design'

Expand specific actions beyond high-level concepts: 'design data models', 'write transformation logic', 'configure scheduling', 'optimize query performance'

Dimension	Reasoning	Score
Specificity	Names the domain (data engineering) and mentions some actions (ETL pipelines, data warehouse, data lake construction), but lacks specific concrete actions like 'design schemas', 'optimize queries', or 'configure ingestion jobs'.	2 / 3
Completeness	Describes what it does (ETL, data warehouse, data lake construction) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	Includes relevant technical terms like 'ETL', 'data warehouse', 'data lake' that users might say, but misses common variations like 'data pipeline', 'ELT', 'batch processing', 'Spark', 'Airflow', or simpler terms users might use.	2 / 3
Distinctiveness Conflict Risk	The data engineering focus provides some distinction, but 'ETL pipelines' and 'data' terms could overlap with general database skills, analytics skills, or other data-related agents without clearer boundaries.	2 / 3
	Total	7 / 12 Passed

Implementation

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

Validation

90%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	10 / 11 Passed

Repository: shaul1991/shaul-agents-plugin
Commit: 9242c58

Reviewed: 29 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.