gtars

High-performance toolkit for genomic interval analysis in Rust with Python bindings. Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis in computational genomics and machine learning applications.

Quality

78%

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 ./bundled/skills/gtars/SKILL.md

Quality

Content

65%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.

A solid, well-structured skill body with strong progressive disclosure and broadly executable examples. It is held back by padded marketing/explanation sections, an install-command typo, and workflows that omit the validation checkpoints expected for batch/file-producing operations.

Suggestions

Fix the doubled command in the Python install section ("uv uv pip install gtars" -> "uv pip install gtars") and verify the RegionSet / filter_overlapping examples against references/python-api.md so the snippets are fully executable.

Trim the 'Performance Characteristics' and 'Data Formats' sections, or fold their load-bearing points into the relevant module sections, to remove marketing padding and improve conciseness.

Add explicit validation/verification checkpoints to the batch workflows (e.g., confirm output BigWig is readable, check fragment-split output counts vs. input) to raise workflow clarity above 3.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and does not over-explain genomics basics, but the repeated 'When to use' bullet lists across six modules and the marketing-flavored 'Performance Characteristics' / 'Data Formats' sections ('Native Rust performance', 'Zero-copy operations') add padding; above 2 because code examples assume Claude's competence and there is no concept-explaining filler, but below 4 due to these unnecessary sections.	3 / 5
Actionability	Each module ships concrete, mostly copy-paste-ready Python and bash examples (e.g., 'gtars.igd.build_index("regions.bed")', 'gtars uniwig generate --input fragments.bed --output coverage.bw'); falls short of 5 because the install line 'uv uv pip install gtars' is a typo and a few API calls (e.g., gtars.RegionSet, filter_overlapping) are not verified against the bundled API reference.	4 / 5
Workflow Clarity	Workflows 1-3 present a numbered sequence but none include validation checkpoints, and several involve batch/file-producing operations (fragment splitting, coverage generation, ML preprocessing); the rubric caps batch operations without validation at 3, and the sequence lacks explicit 'verify output' or error-recovery feedback loops that the level-4/5 anchors require.	3 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled, one-level-deep references ('See references/overlap.md'), content appropriately split across the six real reference files that all exist on disk, and easy navigation; matches the top anchor exactly.	5 / 5
	Total	15 / 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.

A well-crafted description that states concrete capabilities and provides explicit, domain-specific trigger guidance in third person. Its only weakness is slightly narrower trigger-term synonym coverage (missing formats like BigWig/FASTA and terms like 'peaks' or 'single-cell').

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'genomic interval analysis', 'overlap detection', 'coverage tracks', 'tokenization for ML models', 'fragment analysis' — matching the 'comprehensive coverage' anchor; not below because the action list is specific and broad rather than partial.	5 / 5
Completeness	Explicitly answers both 'what' ('High-performance toolkit for genomic interval analysis in Rust with Python bindings') and 'when' via a concrete 'Use when working with ...' clause enumerating trigger scenarios, matching the top anchor.	5 / 5
Trigger Term Quality	Strong natural-term coverage including 'genomic regions', 'BED files', 'coverage tracks', 'fragment analysis', plus 'computational genomics and machine learning'; falls short of 5 because common synonyms and related formats users would mention (e.g., BigWig, peaks, FASTA, single-cell) are absent.	4 / 5
Distinctiveness Conflict Risk	A clear niche (genomic intervals, Rust+Python) with domain-specific triggers (BED, coverage tracks, tokenization for ML) makes overlap with other skills minimal; not below because the triggers are specific enough to avoid misfiring.	5 / 5
	Total	19 / 20 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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/gtars/SKILL.md
Commit: d5ae560

Reviewed: 1 day 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.