CtrlK
BlogDocsLog inGet started
Tessl Logo

polars-bio

Performs genomic interval overlap, nearest, merge, coverage, complement and subtraction on Polars DataFrames, and reads or writes BED, VCF, BCF, BAM, CRAM, GFF, GTF, FASTA and FASTQ data. Use for coordinate-aware genomic joins, read-depth analysis, lazy bioinformatics I/O, SQL queries or migration from bioframe.

75

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

92%Weight 40%Scale 1-5

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

This is a high-quality reference skill body: an overview with a validated decision workflow, executable examples with asserted expected outputs, honest 0.36.0-specific caveats (Int16 depth wraparound, unimplemented on_cols, SQL optimizer defects), and a clean one-level-deep reference bundle. The only improvement space is trimming the citation section and a few dense caveat passages for token efficiency.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence — no primer on what BED/VCF files are, no library-selection rambling — and version-specific details are justified by the 'Verify new releases against the official release notes' instruction. Minor trimming is possible: the ~15-line citation section and a few long caveat sentences (e.g., the bookended-intervals and cloud-access passages) could be tightened, matching 'efficient; minor instances of over-explanation'.

4 / 5

Actionability

Guidance is fully executable: pinned install commands, a complete runnable coordinate-contract example with assertions on expected outputs ('assert pairs.height == 4'), a copy-paste scan/overlap template, and an operation-selection table mapping questions to exact API calls including argument values. This matches 'fully executable; copy-paste ready code or commands; specific examples cover the common cases'.

5 / 5

Workflow Clarity

The 6-step Workflow sequences decisions with explicit validation checkpoints — 'Normalize all inputs to one coordinate system and validate their bounds', 'inspect a small result before scaling up', 'Validate output counts and boundaries against a hand-computable fixture' — and the body documents error conditions and recovery paths (CoordinateSystemMismatchError, strict-mode MissingCoordinateSystemError, bookend min_dist guidance). This is the 'clear sequence with explicit validation steps; feedback loops' anchor, not 4, because checkpoints are explicit rather than merely present.

5 / 5

Progressive Disclosure

The body is a well-sectioned overview whose six references ([configuration], [interval operations], [file I/O], [SQL], [pileup operations], [bioframe migration]) all exist as real files in references/, are one level deep with no further nested references, and are clearly signaled at the point of need. Detail (schemas, credentials, tested patterns) is appropriately pushed into those files, matching the 'clear overview with well-signaled one-level-deep references' anchor.

5 / 5

Total

19

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is exemplary in third-person voice, concrete, and free of fluff: it names six interval operations, ten formats, and an explicit 'Use for...' clause with domain-specific triggers. The only gap is a few natural keyword variants (literal file extensions and synonyms), which keeps trigger term quality just short of the top anchor.

DimensionReasoningScore

Specificity

The description enumerates concrete actions — 'genomic interval overlap, nearest, merge, coverage, complement and subtraction' — plus read/write support for ten named formats (BED, VCF, BCF, BAM, CRAM, GFF, GTF, FASTA, FASTQ). Coverage is comprehensive with no generic filler, matching the 'multiple specific concrete actions' anchor; nothing above 5 exists.

5 / 5

Completeness

It explicitly answers 'what' (first sentence: concrete operations and formats) and 'when' ('Use for coordinate-aware genomic joins, read-depth analysis, lazy bioinformatics I/O, SQL queries or migration from bioframe'), with both stated in concrete trigger phrases — the exact pattern of the anchor-5 example. Not 4, because the 'when' clause is explicit and specific rather than merely adequate.

5 / 5

Trigger Term Quality

Natural phrases users would say are present — 'coordinate-aware genomic joins', 'read-depth analysis', 'migration from bioframe', 'SQL queries' — alongside format names. A few natural variants are missing (literal extensions like '.bed'/'.vcf', synonyms like 'intersect' or 'genomics'), placing it at 'good keyword coverage; a few natural terms missing' rather than the fully comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

A clear niche (genomic interval arithmetic on Polars DataFrames) with distinct triggers including 'migration from bioframe' and named bioinformatics formats; overlap risk with generic data-processing skills is minimal. It clearly matches the 'clear niche with distinct triggers' anchor.

5 / 5

Total

19

/

20

Passed

Validation

100%

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
Reviewed

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.