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

86%

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

Quality

Content

72%

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

The body is well-structured with strong progressive disclosure and largely executable examples, but it loses points for redundancy between the Overview and per-module 'When to use' lists and for workflows that lack explicit validation checkpoints. The duplicated 'uv uv' install command is a small correctness defect worth fixing.

Suggestions

Add explicit validation/verification steps to the workflows (e.g. confirm output files exist and are non-empty after fragsplit/scoring, or re-query an index after building) to lift workflow_clarity to 3.

De-duplicate the use-case lists: keep trigger guidance in the Overview and let each module's 'When to use' add only module-specific detail rather than restating overlapping items.

Fix the install typo 'uv uv pip install gtars' to a single 'uv pip install gtars' (or 'pip install gtars') so the command is directly runnable.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete examples and no over-explanation of known concepts, but the Overview use-case list overlaps with each module's 'When to use' bullets, and minor padding ('organized into specialized modules, each focused on...') could be trimmed.	2 / 3
Actionability	Each module ships copy-paste-ready executable Python and CLI snippets (e.g. 'gtars.igd.build_index("regions.bed")', 'gtars uniwig generate --input ... --format bigwig'); one install typo ('uv uv pip install') is a minor correctness slip, not an actionability gap.	3 / 3
Workflow Clarity	The three workflows are numbered and sequenced, but none include validation/verification checkpoints, and batch/output-writing operations (fragsplit, scoring) lack feedback loops — per guidelines this caps the score at 2.	2 / 3
Progressive Disclosure	A concise overview points to clearly signaled one-level-deep references (overlap.md, coverage.md, tokenizers.md, refget.md, cli.md, python-api.md), all of which exist in ./references/, with content appropriately split and easy to navigate.	3 / 3
	Total	10 / 12 Passed

Description

100%

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 strong: concise, third-person, and clearly pairs a concrete capability statement with an explicit 'Use when' trigger clause covering natural user terminology. It is distinctive within the genomics niche and unlikely to misfire.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'genomic interval analysis', 'overlap detection', 'coverage tracks', 'tokenization for ML models', 'fragment analysis' — rather than vague language, in third person.	3 / 3
Completeness	Explicitly states what ('High-performance toolkit for genomic interval analysis in Rust with Python bindings') and when ('Use when working with...') with an explicit trigger clause.	3 / 3
Trigger Term Quality	Includes natural terms a computational-genomics user would say — 'genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, fragment analysis' — with good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	Niche is clearly scoped to genomic interval analysis in computational genomics/ML with distinct triggers (BED, coverage tracks, genomic tokenization), making conflicts with non-genomic skills unlikely.	3 / 3
	Total	12 / 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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/gtars/SKILL.md
Commit: f627ab5

Reviewed: about 7 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.