databricks-core-workflow-a

Execute Databricks primary workflow: Delta Lake ETL pipelines. Use when building data ingestion pipelines, implementing medallion architecture, or creating Delta Lake transformations. Trigger with phrases like "databricks ETL", "delta lake pipeline", "medallion architecture", "databricks data pipeline", "bronze silver gold".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

65%

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

The body is highly actionable with executable code throughout and a clear step sequence, but it is verbose due to duplicated flows and misses explicit validation checkpoints between batch/destructive layers. It also fails to surface the provided implementation.md reference, leaving content inline that should be split out.

Suggestions

Add explicit validation checkpoints between layers (e.g., verify row counts / merge results after Silver, confirm OPTIMIZE/VACUUM success before proceeding) to turn the reactive error table into a proactive feedback loop.

Link to references/implementation.md from the body and move the duplicated DLT pipeline and job-scheduling variants there, leaving SKILL.md as a concise overview pointing one level deep.

Remove the duplicated Auto Loader cloudFiles bronze block by referencing the single canonical version, and trim conceptual asides Claude already knows (e.g., what Auto Loader scales to).

Dimension	Reasoning	Score
Conciseness	Mostly efficient and concrete, but padded with duplication — the Auto Loader/cloudFiles bronze flow is repeated across Step 1 and the DLT Step 5, and the medallion flow is shown twice (imperative and declarative) with full scheduling boilerplate inline.	2 / 3
Actionability	Provides fully executable, copy-paste-ready PySpark, SQL (OPTIMIZE/ZORDER/VACUUM/ANALYZE), and WorkspaceClient scheduling code with specific options, not pseudocode.	3 / 3
Workflow Clarity	Steps are clearly sequenced (Bronze→Silver→Gold→Maintenance→DLT→Schedule) with an error table, but there are no explicit inter-layer validation/verification checkpoints for these batch and destructive operations (MERGE, VACUUM, partition overwrites), which caps clarity at 2.	2 / 3
Progressive Disclosure	The body is sectioned but largely monolithic, and the existing references/implementation.md bundle file is never linked from SKILL.md; content that could be split out (the DLT variant, orchestration) is kept inline.	2 / 3
	Total	9 / 12 Passed

Description

100%

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 is concise, specific, and complete — it states concrete capabilities, provides explicit 'Use when' triggers plus natural trigger phrases, and carves out a distinct Databricks ETL niche. It matches the strong reference examples across all four dimensions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'building data ingestion pipelines, implementing medallion architecture, or creating Delta Lake transformations' — matching the anchor for multiple specific concrete actions.	3 / 3
Completeness	Explicitly answers both what ('Execute Databricks primary workflow: Delta Lake ETL pipelines') and when ('Use when building data ingestion pipelines... Trigger with phrases like...'), with explicit trigger guidance.	3 / 3
Trigger Term Quality	Provides good coverage of natural terms a user would say — 'databricks ETL', 'delta lake pipeline', 'medallion architecture', 'databricks data pipeline', 'bronze silver gold' — rather than a single phrase.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (Databricks Delta Lake ETL / medallion architecture) with distinctive triggers like 'bronze silver gold' and 'delta lake pipeline', making conflict with unrelated skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 02d6341

Reviewed: 4 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.