CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

67

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/data-engineering/skills/spark-optimization/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%Weight 40%Scale 1-5

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

Well-structured, actionable reference skill with good progressive disclosure to a real bundle file. Weakest in workflow clarity: it lacks an explicit, sequenced optimization procedure with validation checkpoints for batch output operations.

Suggestions

Add a short numbered optimization workflow (e.g., 1. inspect Spark UI for skew/spills/GC, 2. apply targeted fix, 3. re-run and verify timing) to raise workflow clarity.

Trim the opening paragraph and 'When to Use' list, which duplicate the frontmatter description, to improve token efficiency.

Inline one concrete worked example (e.g., partition-size calculation or salting) so the core techniques are actionable without opening the reference.

DimensionReasoningScore

Conciseness

Mostly lean with compact tables, a tight execution-model diagram, and clean Quick Start code, but the opening paragraph and 'When to Use' list restate the frontmatter description, which could be trimmed.

4 / 5

Actionability

Quick Start provides copy-paste-ready PySpark with specific config keys, and Best Practices give concrete do/don't bullets, but the key worked optimizations (partitioning math, salting) live in the reference rather than inline, leaving minor gaps.

4 / 5

Workflow Clarity

The body is organized as concepts + quick start + best practices rather than a sequenced optimization workflow, and there are no validation/verification checkpoints despite a batch 'write' operation; the destructive/batch cap of 3 applies.

3 / 5

Progressive Disclosure

Clear overview structure with a single, well-signaled one-level-deep reference ('references/details.md') for detailed patterns and worked examples; the referenced file exists and is appropriately split out.

5 / 5

Total

16

/

20

Passed

Description

87%Weight 40%Scale 1-5

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, well-formed description that clearly states capabilities and triggers in third-person voice with a concrete 'Use when' clause. Minor gains available from broadening trigger synonyms and naming a few more specific techniques.

DimensionReasoningScore

Specificity

Names several concrete optimization techniques ('partitioning, caching, shuffle optimization, and memory tuning') but they read as optimization sub-areas rather than fully distinct actions, leaving minor coverage gaps (e.g., broadcast joins, data skew absent from the description).

4 / 5

Completeness

Explicitly answers both what ('Optimize Apache Spark jobs with partitioning, caching, shuffle optimization, and memory tuning') and when ('Use when improving Spark performance, debugging slow jobs, or scaling data processing pipelines') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural phrases users would say appear ('improving Spark performance', 'debugging slow jobs', 'scaling data processing pipelines'), but a few common variations like 'tuning Spark' or 'Spark running slow' are missing.

4 / 5

Distinctiveness Conflict Risk

'Apache Spark jobs' is a clear niche with distinct, domain-specific triggers; minimal overlap risk with other skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
wshobson/agents
Reviewed

Table of Contents

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.