polars-bio

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.

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/polars-bio/SKILL.md

Quality

Content

72%

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

A well-structured, highly actionable library-reference skill with excellent progressive disclosure and copy-paste-ready examples. Its main gaps are repeated LazyFrame explanations across sections and the absence of an explicit validation-gated workflow for batch/large operations.

Suggestions

Consolidate the LazyFrame/`.collect()` and `.pb` accessor guidance into a single 'Return types & API styles' section and remove the repetitions in Quick Start, Core Capabilities, and Common Pitfalls.

Trim or relocate the 'Key value propositions' marketing bullets ('6-38x faster') to the bioframe_migration reference, keeping the overview focused on capability.

For large/batch workflows (e.g. scan + streaming collect), add a short sequenced checklist with a validation checkpoint (verify schema/columns before collect) to lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with executable code and no basic-concept padding, but the LazyFrame/`.collect()` behavior is repeated across ~4 sections and the '6-38x faster' value-proposition bullets add marketing-style bulk, so it could be tightened.	2 / 3
Actionability	Code is fully executable throughout (real imports, concrete calls like pb.overlap, pb.scan_bam, pb.sql with copy-paste-ready arguments), matching the score-3 anchor rather than the pseudocode score-2 anchor.	3 / 3
Workflow Clarity	Content is well-organized with numbered pitfalls and best practices, but it is reference material with no sequenced multi-step workflow or explicit validation/feedback-loop checkpoints, so it sits at 2 rather than 3.	2 / 3
Progressive Disclosure	SKILL.md is a concise overview pointing to 6 clearly signaled, one-level-deep reference files (all verified to exist) listed in a Resources section, with details appropriately split out and no nested references.	3 / 3
	Total	10 / 12 Passed

Description

82%

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 specific, well-targeted description with strong natural trigger terms and a clear niche. Its only weakness is the absence of an explicit 'Use when...' clause, which leaves the trigger guidance implied rather than stated.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when performing genomic interval operations or reading/writing BED/VCF/BAM/GFF files, or when migrating from bioframe to a faster Polars-based alternative.'

Include common natural phrasings users might say (e.g. 'bedtools-style overlap', 'genomic ranges', 'interval intersection') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete operations ('Overlap, nearest, merge, coverage, complement, subtract') plus file I/O across named formats, matching the multiple-specific-actions anchor rather than the partial score-2 anchor.	3 / 3
Completeness	The 'what' is explicit and detailed, but there is no explicit 'Use when...' trigger clause; the 'when' is only implied by 'faster bioframe alternative', so per the missing-trigger-guideline it caps at 2 rather than 3.	2 / 3
Trigger Term Quality	Natural user-facing terms are well covered ('genomic interval operations', 'BED/VCF/BAM/GFF', 'overlap', 'bioframe alternative', 'Polars DataFrames'), the exact vocabulary a bioinformatics user would say.	3 / 3
Distinctiveness Conflict Risk	A narrow niche (genomic interval operations on Polars DataFrames) with distinct format/operation triggers that are unlikely to conflict with other skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/polars-bio/SKILL.md
Commit: 757b63b

Reviewed: about 10 hours ago

Table of Contents

Discovery Implementation Validation

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.