spark-optimization

Optimize Apache Spark jobs with partitioning, caching, shuffle optimization, and memory tuning. Use when improving Spark performance, debugging slow jobs, or scaling data processing pipelines.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

72%

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

A rich, highly actionable reference with executable PySpark patterns, but it is a monolithic catalog lacking sequenced workflows with validation checkpoints and makes no use of progressive disclosure despite its length.

Suggestions

Add a short diagnostic-first workflow (measure skew/spills/GC, then apply the matching pattern) with explicit validation checkpoints so multi-step tuning has clear sequencing.

Extract the lengthy pattern catalog and configuration cheat sheet into reference files (e.g. patterns.md, configs.md) and link them one level deep to reduce SKILL.md's token footprint.

Tighten inline glosses (storage-level explanations, BAD/GOOD asides) that restate what Claude already knows about Spark.

Dimension	Reasoning	Score
Conciseness	The body is code-dense and largely assumes Claude's competence, but inline explanatory comments (e.g. storage-level glosses and BAD/GOOD asides) add light padding that keeps it just below the lean level-3 anchor.	2.5 / 3
Actionability	Provides fully executable PySpark snippets with concrete config keys and values (e.g. 'spark.sql.adaptive.skewJoin.skewedPartitionThresholdInBytes', '256MB') and reusable functions, matching the copy-paste-ready level-3 anchor.	3 / 3
Workflow Clarity	Content is a catalog of patterns rather than a sequenced optimization workflow, and the 'Instructions' section stays generic with no validation checkpoints or feedback loops despite batch/destructive-adjacent operations, capping it at level 2.	2 / 3
Progressive Disclosure	No bundle files exist and all detail (seven patterns, cheat sheet, best practices) lives inline in a ~420-line monolith; sections are well-organized but content that should be separate is inline, matching level 2 rather than the simple-skill level-3 case.	2 / 3
	Total	9.5 / 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.

A strong description that states concrete capabilities and an explicit 'Use when' trigger covering natural user phrasings. It is concise, distinctive, and free of fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'partitioning, caching, shuffle optimization, and memory tuning' tied to the verb 'Optimize', matching the level-3 anchor rather than the partial level-2 anchor.	3 / 3
Completeness	Explicitly answers both what ('Optimize Apache Spark jobs with...') and when via an explicit 'Use when...' clause, satisfying the level-3 anchor.	3 / 3
Trigger Term Quality	Natural trigger phrases users would say ('improving Spark performance', 'debugging slow jobs', 'scaling data processing pipelines') give good coverage; not level 2 because these read as genuine user language rather than jargon.	3 / 3
Distinctiveness Conflict Risk	Scoped to Apache Spark optimization with distinct triggers, giving it a clear niche unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: rmyndharis/antigravity-skills
Path: skills/spark-optimization/SKILL.md
Commit: e63f7dd

Reviewed: about 24 hours 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.