High-performance genomic interval operations and bioinformatics file I/O on Polars DataFrames. Overlap, nearest, merge, coverage, complement, subtract for BED/VCF/BAM/GFF intervals. Streaming, cloud-native, faster bioframe alternative.
SkillScore100Maintained
Automatic
◆Data Engineer pack
Last verified 8/21/2026
What it changes
Passed 22 of 22 test cases with the skill, and 8 of 22 without it.
Without skill36%
With skill100%
Checks it passed that the model alone missed
Calls pb.cluster on the interval dataset
Explains that count_overlaps returns a LazyFrame by default
Calls pb.set_option with coordinate_system as the option key
and 19 more in the full report
14 fixed8 passed either way0 still failing0 broke
Pass-rate lift
+64 pp
Tokens
+121%
Agent turns
0%
Response time
-57%
Model gemini-3.6-flashMeasured 8/21/2026v122 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 14
Prompt
When reading aligned reads from a CRAM file in Python using polars-bio streaming, what specific function should be used instead of standard BAM scanning, and what additional required reference parameter must be provided?
What was checked, without and with the skill
Checked
Without skill
With skill
Uses scan_cram or read_cram instead of standard BAM reader functions
Passed
Passed
Provides the reference_path parameter required for decoding CRAM compression
Missed
Passed
case-05 · gemini-3.6-flash · 8/21/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md366 lines7 files
polars-bio
Overview
polars-bio is a high-performance Python library for genomic interval operations and bioinformatics file I/O, built on Polars, Apache Arrow, and Apache DataFusion. It provides a familiar DataFrame-centric API for interval arithmetic (overlap, nearest, merge, coverage, complement, subtract) and reading/writing common bioinformatics formats (BED, VCF, BAM, CRAM, GFF/GTF, FASTA, FASTQ).
Key value propositions:
6-38x faster than bioframe on real-world genomic benchmarks
Streaming/out-of-core support for large genomes via DataFusion
Cloud-native file I/O (S3, GCS, Azure) with predicate pushdown
Two API styles: functional (pb.overlap(df1, df2)) and method-chaining (df1.lazy().pb.overlap(df2))
SQL interface for genomic data via DataFusion SQL engine