gtars

A high-performance Rust toolkit (with Python bindings and a CLI) for genomic interval analysis; use it when you need fast overlap queries, coverage track generation, genomic tokenization for ML, reference sequence verification, or fragment processing.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

83%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.

The body is well-structured with executable examples and good progressive disclosure via real reference files. It is slightly redundant between the feature bullets and the implementation details section, and the example-oriented content lacks explicit validation checkpoints for batch output operations.

Suggestions

Remove or condense the 'Implementation Details' section, since its content largely restates 'Key Features' and 'When to Use'; move any genuinely new detail into the corresponding references/*.md files.

For the CLI coverage-generation and overlap workflows, add an explicit verification step (e.g., checking the output track in a genome browser or confirming row counts) to strengthen workflow clarity for batch operations.

Trim redundant phrasing such as '(runnable)' labels and repeated capability descriptions to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	Largely lean with runnable code and tight bullets, but the 'Implementation Details' section re-explains capabilities already covered in 'Key Features' and 'When to Use', adding some redundant prose that could be trimmed.	4 / 5
Actionability	Provides multiple copy-paste-ready, executable examples for Python overlap, CLI coverage generation, and ML tokenization, covering the common cases with concrete imports and commands.	5 / 5
Workflow Clarity	Examples are clearly labeled and sequenced per task, but these are demonstration snippets rather than multi-step workflows with validation checkpoints; for batch/genomic output operations, no explicit verify step is given, which the rubric would expect at level 5.	4 / 5
Progressive Disclosure	SKILL.md is a concise overview with well-signaled, one-level-deep references (references/overlap.md, coverage.md, tokenizers.md, refget.md, python-api.md, cli.md), all of which exist as real bundle files, keeping detail out of the main file.	5 / 5
	Total	18 / 20 Passed

Description

88%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 specific, complete, and distinctive, clearly stating both what the toolkit does and when to use it with concrete genomics-oriented trigger phrases. Trigger term coverage is strong but slightly technical, missing a few natural synonyms and file formats a user might name.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across distinct capabilities — 'fast overlap queries', 'coverage track generation', 'genomic tokenization for ML', 'reference sequence verification', and 'fragment processing' — giving comprehensive coverage of the toolkit's functions.	5 / 5
Completeness	Explicitly answers 'what' ('A high-performance Rust toolkit ... for genomic interval analysis') and 'when' ('use it when you need fast overlap queries, coverage track generation, ...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural terms (overlap queries, coverage, tokenization, fragment processing) appear, but it leans technical and omits common synonyms or file extensions a user might mention (e.g., BED, peaks, ATAC-seq, BigWig); a few natural phrasings are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (genomic interval analysis with Rust/Python/CLI) with distinct triggers tied to genomics-specific tasks, creating minimal conflict risk with unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/gtars/SKILL.md
Commit: f5ef65b

Reviewed: ~3 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.