databricks-reference-architecture

Implement Databricks reference architecture with best-practice project layout. Use when designing new Databricks projects, reviewing architecture, or establishing standards for Databricks applications. Trigger with phrases like "databricks architecture", "databricks best practices", "databricks project structure", "how to organize databricks", "databricks layout".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

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

A highly actionable reference architecture with executable code throughout, but it is a long monolithic document lacking validation checkpoints in its workflow and any progressive disclosure into separate reference files. Its own deprecation notice acknowledges it is really an architecture doc that should live in references/.

Suggestions

Add explicit validation checkpoints between steps (e.g., 'databricks bundle validate' after Step 2, a data-flow row-count check after Step 4) before proceeding to deployment or destructive maintenance.

Split the inline SQL DDL, bundle YAML, and code templates into reference files under references/ and keep SKILL.md as a concise overview pointing to them.

Trim the Prerequisites section and Overview of concepts Claude already knows (e.g., the medallion bronze/silver/gold gloss) to reduce token overhead.

Dimension	Reasoning	Score
Conciseness	Largely concrete reference material (SQL, YAML, Python) rather than padded explanation, but it is a ~290-line monolith that restates known concepts in Prerequisites and inlines content that could be trimmed or split.	2 / 3
Actionability	Provides fully executable SQL DDL, Asset Bundle YAML, Auto Loader Python, and maintenance scripts that are specific and copy-paste ready.	3 / 3
Workflow Clarity	Steps 1-5 are sequenced, but there are no explicit validation checkpoints for batch/destructive operations such as VACUUM and ETL jobs, which caps workflow clarity at 2 per the rubric.	2 / 3
Progressive Disclosure	Well-sectioned with clear headers, but it is a single-file monolith with no bundle references; content that should be split (the architecture doc) is inline, and the deprecation note itself states it belongs in shared references/.	2 / 3
	Total	9 / 12 Passed

Description

90%

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

A well-structured description with explicit what/when guidance and natural trigger phrases; its only weakness is that the named actions are somewhat abstract rather than concrete capabilities. Voice is correctly third person.

Dimension	Reasoning	Score
Specificity	Names the Databricks domain and several actions ('Implement', 'designing', 'reviewing', 'establishing standards') but the actions are abstract rather than the multiple concrete actions the score-3 anchor requires.	2 / 3
Completeness	Explicitly answers what ('Implement Databricks reference architecture with best-practice project layout') and when ('Use when designing new Databricks projects, reviewing architecture...') with explicit trigger guidance.	3 / 3
Trigger Term Quality	Provides natural trigger phrases users would actually say ('databricks architecture', 'databricks best practices', 'how to organize databricks'), giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Targets a clear Databricks-specific niche with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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: 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.