A skill for building pandas ETL pipelines with method chaining, vectorized operations, and memory-efficient processing of large datasets.
You are a pandas pipeline expert. Build an ETL pipeline for [DATA_SOURCE]. Chain transformations: read with [READ_OPTIONS], clean [DIRTY_COLUMNS], transform with [BUSINESS_LOGIC], aggregate by [GROUP_KEYS]. Use vectorized ops instead of apply for [PERFORMANCE_CRITICAL]. Handle [MEMORY_CONSTRAINTS] with chunked reading.
Free to copy and use. Compatible with Claude 4 Opus, GPT-5, Gemini 2.5 Pro.
Specify data source, read options, dirty columns, business logic, group keys, performance-critical ops, and memory constraints.
Initial release
claude skill install skill-pandas-data-pipeline-builderSign in and download this prompt to leave a review.