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

Pending

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, outputs, or capabilities are mentioned. It reads as only the 'Use when...' clause with no preceding 'what it does' statement.

Suggestions

Add a clear 'what it does' statement listing concrete capabilities, e.g., 'Designs and implements ETL/ELT pipelines, configures data orchestration workflows, implements medallion architecture patterns, and troubleshoots data pipeline failures.'

Restructure to follow the pattern: capabilities first, then 'Use when...' clause, e.g., 'Designs ETL/ELT pipelines, implements medallion architecture, configures batch and streaming ingestion, and optimizes data workflows. Use when the user asks to...'

Ensure the description uses third-person declarative voice for capabilities (e.g., 'Builds data pipelines' rather than framing everything as user requests).

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.	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, it could overlap with other data-related skills (e.g., a database skill, a data analysis skill, or a cloud infrastructure skill).	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-style skill that covers ETL pipeline design broadly with good structural organization and progressive disclosure. Its main weaknesses are verbosity (explaining concepts Claude already knows like OLAP/OLTP, horizontal/vertical scaling) and limited actionability — most guidance is descriptive tables rather than executable code or specific commands. Adding validation checkpoints to the workflow and replacing conceptual explanations with more concrete implementation examples would significantly improve it.

Suggestions

Remove explanations of concepts Claude already knows (OLAP vs OLTP definitions, horizontal vs vertical scaling, basic SQL concepts) to reduce token usage by ~30%.

Add 2-3 more executable code examples: an Airflow DAG skeleton, a dbt model template, or a data validation script with assertions — these are the most common implementation tasks.

Add explicit validation checkpoints to the Decision Framework workflow, e.g., 'After step 4, validate transformation output against expected schema before proceeding to orchestration setup.'

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 and some table descriptions are unnecessary padding.	2 / 3
Actionability	The skill provides one concrete executable SQL example (UPSERT) and a useful decision tree for batch vs streaming, but most content is descriptive tables and conceptual overviews rather than executable code or specific commands. For a pipeline design skill, more concrete implementation snippets (e.g., Airflow DAG skeleton, dbt model example, data validation code) would significantly improve actionability.	2 / 3
Workflow Clarity	The Decision Framework section provides a clear 8-step sequence for pipeline design, but it lacks explicit validation checkpoints or feedback loops. For a skill involving potentially destructive batch operations and data transformations, there are no 'validate before proceeding' gates or error recovery loops in the main workflow.	2 / 3
Progressive Disclosure	The skill provides a clear overview with well-organized sections and references four specific external files for detailed patterns, orchestration strategies, observability guides, and checklists. References are one level deep and clearly signaled with descriptive labels.	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: b573078

Reviewed: 14 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.