python-polars
Enforces Polars over Pandas for functional pipe-style data manipulation (like dplyr in R). Use when writing Python data processing code, data transformation pipelines, ETL workflows, or analytical queries—e.g., "process this CSV", "aggregate sales data", "filter and transform DataFrame", "group by and calculate metrics".
89
86%
Does it follow best practices?
Impact
92%
7.07xAverage score across 3 eval scenarios
Passed
No known issues
Evaluation results
90%
80%Regional Sales Performance Report
Pipe-style ETL pipeline with lazy scanning
Polars import used
0%
100%
Lazy CSV scanning
0%
100%
Single continuous chain
0%
100%
Explicit column references
0%
100%
Single with_columns context
0%
0%
Polars conditional expression
0%
100%
Early filter placement
0%
100%
No row iteration
0%
100%
No apply or map_elements
100%
100%
collect() terminates pipeline
0%
100%
87%
68%Sensor Data Cleaning Pipeline
Null vs NaN handling and explicit schema
Polars not pandas
0%
100%
Explicit dtypes/schema
33%
33%
Date parsing in read
37%
100%
fill_nan for temperature
0%
100%
fill_null for humidity
0%
100%
Forward fill strategy
0%
100%
drop_nulls for sensor_id
0%
37%
No in-place mutation
0%
100%
No index operations
100%
100%
Null/NaN comments
100%
100%
100%
89%Customer Cohort Analytics
Window functions with .over() and reusable expressions
Polars not pandas
0%
100%
Anti-join for exclusion
0%
100%
cum_sum with .over()
0%
100%
rank with .over()
0%
100%
Cohort average with .over()
0%
100%
Single with_columns context
0%
100%
Reusable expression functions
0%
100%
No row iteration
100%
100%
Pipe-style chain
0%
100%
Aliases on expressions
50%
100%
- Repository
- jjjermiah/dotagents
- Commit
b74de5e
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6
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.