pyspark-transformer

Pyspark Transformer - Auto-activating skill for Data Pipelines. Triggers on: pyspark transformer, pyspark transformer Part of the Data Pipelines skill category.

1.04x

Quality

Does it follow best practices?

Impact

100%

1.04x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./planned-skills/generated/11-data-pipelines/pyspark-transformer/SKILL.md

Evaluation results

100%

11%

Custom Feature Engineering Transformer

Production-ready PySpark Transformer implementation

Criteria

Without context

With context

Transformer subclass

100%

transform() method

100%

Configurable parameter

100%

ML persistence

100%

Pipeline integration

100%

Synthetic data creation

100%

Missing value handling

70%

100%

Output schema validation

33%

100%

Three derived features

100%

Production code quality

100%

Validation report

100%

Without context: $0.8660 · 5m 39s · 35 turns · 35 in / 12,154 out tokens

With context: $1.0830 · 5m 56s · 43 turns · 74 in / 15,120 out tokens

100%

Sales Data ETL Pipeline

ETL pipeline with output validation

Criteria

Without context

With context

PySpark DataFrame API

100%

Three transformations

100%

Null handling

100%

Parquet output

100%

Partitioned by region

100%

Data quality validation

100%

Validation raises error

100%

Step-by-step structure

100%

Row count logging

100%

Production code patterns

100%

Schema awareness

100%

Without context: $0.4215 · 2m 38s · 20 turns · 20 in / 6,656 out tokens

With context: $0.7623 · 3m 54s · 37 turns · 38 in / 8,762 out tokens

100%

Real-Time IoT Sensor Stream Processor

Streaming data pipeline with step-by-step workflow

Criteria

Without context

With context

Structured Streaming API

100%

Schema definition

100%

Null machine_id filter

100%

Alert flag derivation

100%

Tumbling window

100%

Windowed aggregates

100%

WriteStream output

100%

Step-by-step workflow plan

100%

Data quality handling documented

100%

Production appName

100%

No collect() on stream

100%

Without context: $0.6340 · 3m 7s · 30 turns · 29 in / 9,792 out tokens

With context: $0.6736 · 2m 50s · 37 turns · 35 in / 8,731 out tokens

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 0c08951

Evaluated: 18 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Custom Feature Engineering Transformer Sales Data ETL Pipeline Real-Time IoT Sensor Stream Processor

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.