etl-pipeline-design

This skill should be used when the user asks to "design an ETL pipeline", "build data ingestion", "set up data orchestration", "troubleshoot pipeline issues", "optimize data workflows", or mentions ELT, medallion architecture, batch vs streaming, or data transformation patterns.

Quality

47%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./data-engineering/skills/etl-pipeline-design/SKILL.md

Quality

Discovery

37%

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

This description is essentially a trigger-term list masquerading as a skill description. While it excels at providing natural keywords users would say, it completely fails to describe what the skill actually does—no concrete actions, capabilities, or outputs are mentioned. The description needs a fundamental restructuring to lead with capabilities before listing trigger conditions.

Suggestions

Add a clear 'what it does' section listing concrete actions, e.g., 'Designs ETL/ELT pipeline architectures, generates data ingestion code, implements medallion architecture patterns, and troubleshoots pipeline performance issues.'

Restructure to lead with capabilities first, then follow with 'Use when...' clause, e.g., 'Designs and implements data pipeline architectures including ETL/ELT patterns, medallion architecture, and batch/streaming workflows. Use when the user asks to...'

Use third-person active voice to describe capabilities (e.g., 'Generates pipeline configurations' rather than 'This skill should be used when').

Dimension	Reasoning	Score
Specificity	The description lists no concrete actions or capabilities. It only describes when to use the skill (trigger scenarios) but never states what the skill actually does. Phrases like 'design an ETL pipeline' and 'build data ingestion' are trigger terms, not descriptions of the skill's capabilities.	1 / 3
Completeness	The description answers 'when' extensively but completely fails to answer 'what does this do'. There is no explanation of the skill's actual capabilities, outputs, or concrete actions it performs. The 'what' component is entirely missing.	1 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms users would say: 'ETL pipeline', 'data ingestion', 'data orchestration', 'pipeline issues', 'data workflows', 'ELT', 'medallion architecture', 'batch vs streaming', 'data transformation patterns'. These are terms users would naturally use when requesting this type of help.	3 / 3
Distinctiveness Conflict Risk	The trigger terms are fairly specific to the data engineering domain (ETL, ELT, medallion architecture), which helps distinguish it. However, without stating what the skill actually does, there could be overlap with other data-related skills. Terms like 'data workflows' and 'data transformation' are somewhat broad.	2 / 3
	Total	7 / 12 Passed

Implementation

57%

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

This is a comprehensive reference document for ETL pipeline design that excels at organization and progressive disclosure, with clear section structure and appropriate references to detailed files. However, it leans heavily toward descriptive tables cataloging concepts rather than providing actionable, executable guidance, and it includes several concepts Claude would already know (OLAP vs OLTP, horizontal vs vertical scaling). The workflow lacks validation checkpoints that would be critical for pipeline design.

Suggestions

Replace descriptive tables of well-known concepts (OLAP vs OLTP, scaling types) with actionable decision criteria or remove them entirely to improve conciseness.

Add more executable code examples for key patterns (e.g., a complete incremental ingestion script, a basic Airflow DAG skeleton, a dbt transformation example) to improve actionability.

Integrate validation checkpoints into the Decision Framework workflow, such as 'validate schema compatibility before loading' and 'test pipeline with sample data before production deployment'.

Dimension	Reasoning	Score
Conciseness	The skill is well-structured with tables that compress information efficiently, but it's quite long (~300 lines) and includes many concepts Claude already knows (what OLAP vs OLTP is, what horizontal vs vertical scaling means, basic SQL concepts). The 'Scaling Formula' section is particularly unnecessary. Some tables describe rather than instruct.	2 / 3
Actionability	The skill provides one concrete executable code example (the MERGE SQL statement) and a useful decision tree for batch vs streaming, but most content is descriptive tables listing concepts rather than executable guidance. The decision framework at the end is a good checklist but lacks concrete commands or code for most steps.	2 / 3
Workflow Clarity	The Decision Framework section provides a clear 8-step sequence for designing a pipeline, but it lacks validation checkpoints or feedback loops. For a skill involving pipeline design where errors can cascade, there are no explicit verification steps (e.g., 'validate schema before loading', 'test with sample data before full run'). The troubleshooting section lists techniques but doesn't integrate them into the workflow.	2 / 3
Progressive Disclosure	The skill has a clear overview structure with well-organized sections and ends with explicit one-level-deep references to four separate files for detailed patterns, orchestration strategies, observability guides, and checklists. Navigation is straightforward with numbered major sections.	3 / 3
	Total	9 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: back1ply/LLM-Skills
Commit: cc0ada7

Reviewed: 20 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.