databricks-performance-tuning

Optimize Databricks cluster and query performance. Use when jobs are running slowly, optimizing Spark configurations, or improving Delta Lake query performance. Trigger with phrases like "databricks performance", "spark tuning", "databricks slow", "optimize databricks", "cluster performance".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

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 highly actionable and token-efficient with strong executable examples, but it lacks validation checkpoints for its destructive maintenance operations and fails to surface the bundled reference file that duplicates some inline content.

Suggestions

Add validation/verification checkpoints around destructive and batch steps (e.g., confirm table size/retention before VACUUM, re-run the slow-query check after applying OPTIMIZE) to lift workflow_clarity.

Link the existing references/advanced-patterns.md from the body (e.g., a "## Advanced patterns" section with a markdown link) and move the duplicated CacheManager/benchmark material out of SKILL.md to fix progressive_disclosure.

Resolve the duplicated query-history SQL between SKILL.md and advanced-patterns.md so the two files stay one level deep and non-redundant.

Dimension	Reasoning	Score
Conciseness	The body is dense and lean — almost entirely executable Python/SQL and tables with only inline, load-bearing comments; no space is spent explaining concepts Claude already knows. It is at the top lean-and-efficient anchor rather than the 2-level which would carry unnecessary explanation.	3 / 3
Actionability	Provides fully executable, copy-paste-ready code and SQL throughout — a cluster-sizing function, per-workload Spark configs, OPTIMIZE/ZORDER/ANALYZE/VACUUM statements, broadcast-join patterns, and an error-handling table with concrete solutions — matching the top anchor.	3 / 3
Workflow Clarity	The seven numbered steps give a clear sequence, but destructive/batch operations (VACUUM, OPTIMIZE, cluster config changes) have no validation or verification checkpoints, capping the score at 2 per the rubric's destructive-operations guideline.	2 / 3
Progressive Disclosure	A references/advanced-patterns.md bundle exists but the body never signals or links to it, and ~250 lines of content (advanced caching, benchmarking) that overlap the bundle are kept inline; this matches the some-structure-but-refs-not-signaled anchor rather than the well-signaled top anchor.	2 / 3
	Total	10 / 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 specific, concise, and clearly answers both what the skill does and when to use it with natural trigger phrases. It is a strong example with no over-claims or fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Optimize Databricks cluster and query performance," "optimizing Spark configurations," "improving Delta Lake query performance" — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly answers both what ("Optimize Databricks cluster and query performance") and when via a clear "Use when..." clause with explicit triggers, matching the top anchor.	3 / 3
Trigger Term Quality	Provides good coverage of natural phrases users would say ("databricks performance", "spark tuning", "databricks slow", "optimize databricks", "cluster performance"), matching the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	Clear Databricks-specific niche with distinct trigger phrases unlikely to fire for unrelated skills; matches the clear-niche anchor.	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.