data-engineering

Data engineering patterns for ETL pipelines, data warehousing, Apache Spark, and data quality validation

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/data-engineering/SKILL.md

Quality

Content

80%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a strong, lean reference of executable ETL, Spark, quality, and warehouse-schema patterns with no conceptual padding. Its weaknesses are structural rather than technical: workflows show validation only implicitly inside code, and everything lives in one large file with no progressive disclosure to bundled references.

Suggestions

Add a short explicit workflow narration with validation checkpoints (e.g. 'After load, run quality checks; if a critical check fails, halt and retry the stage') to make the feedback loop visible.

Split the larger sections (Apache Spark processing, warehouse schema) into referenced files under references/ and link to them from a concise overview, enabling one-level-deep progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean executable code plus tight bullet lists (anti-patterns, checklist) with no prose explaining concepts Claude already knows; every section earns its place, matching the 'lean and efficient' anchor.	3 / 3
Actionability	Provides complete, executable Python (ETL pipeline class, Spark job, quality-check runner) and SQL DDL that are copy-paste ready, matching the 'fully executable code/commands' anchor rather than the pseudocode level.	3 / 3
Workflow Clarity	The ETL run() method sequences extract→transform→load and quality checks raise on critical failure, but these checkpoints are embedded in code rather than narrated as explicit validate→fix→retry steps, so it sits at the 'sequence present but checkpoints implicit' anchor and not level 3.	2 / 3
Progressive Disclosure	The file is well-organized into clear sections but is a monolithic 200+ line document with no one-level-deep references to separate files, fitting 'some structure but content that should be separate is inline' rather than the level-3 split-reference pattern.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 clearly identifies the data-engineering domain and its sub-areas but is entirely 'what' with no 'when to use it' trigger guidance, leaving every dimension at the mid-level anchor. Adding an explicit 'Use when...' clause and concrete action verbs would lift it across the board.

Suggestions

Append an explicit trigger clause, e.g. 'Use when building ETL pipelines, modeling a data warehouse, writing Spark jobs, or validating data quality.'

Replace the passive 'patterns for' framing with concrete verbs ('Build ETL pipelines, model warehouse star schemas, write Spark transformations, validate data quality').

Add common natural variations users would say ('data warehouse', 'pipelines', 'Airflow', 'Databricks') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names concrete sub-domains ('ETL pipelines, data warehousing, Apache Spark, and data quality validation') but frames them as 'patterns for' with no concrete verbs (build, extract, validate), so it is not a level-3 list of actions nor a level-1 vague phrase.	2 / 3
Completeness	It states what the skill covers but has no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Includes relevant natural terms ('ETL pipelines', 'data warehousing', 'Apache Spark', 'data quality validation') but misses common variations users would say such as 'data warehouse', 'pipeline', 'Airflow', or 'Databricks', so coverage is partial rather than comprehensive.	2 / 3
Distinctiveness Conflict Risk	The data-engineering niche is fairly distinct, but without explicit triggers it could still overlap with related analytics, BI, or database skills, matching the 'somewhat specific but could overlap' anchor.	2 / 3
	Total	8 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rohitg00/awesome-claude-code-toolkit
Path: skills/data-engineering/SKILL.md
Commit: ebdf1d5

Reviewed: 2 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.