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 ./backend/cli/skills/coding/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.

Well-structured with strong progressive disclosure and actionable examples, but weighed down by padded explanatory sections and a lack of validation checkpoints in the batch-processing workflows.

Suggestions

Remove or trim the 'Data Formats' and 'Performance Characteristics' sections, which restate knowledge Claude already has, to tighten conciseness.

Add explicit verification steps to the workflows (e.g. check the generated BigWig track is non-empty and well-formed, validate token counts) since they are batch operations.

Fix the installation typo 'uv uv pip install gtars' to 'uv pip install gtars' so the primary install instruction is copy-paste correct.

Dimension	Reasoning	Score
Conciseness	Mostly efficient code examples, but padded sections restate what Claude already knows — 'Data Formats' explains BED/WIG/BigWig/FASTA, 'Performance Characteristics' is generic marketing ('Fast execution with low memory overhead'), and 'Python vs CLI Usage' and 'Integration with geniml' add little.	3 / 5
Actionability	Concrete, mostly copy-paste-ready code and CLI commands for each capability and workflow, with only minor gaps (e.g. the duplicated 'uv uv pip install gtars' typo).	4 / 5
Workflow Clarity	The three workflows are clearly sequenced with numbered steps, but batch data-processing operations (coverage generation, tokenization) lack any validation or verification checkpoints, capping this dimension at 3 per the rubric.	3 / 5
Progressive Disclosure	A clear overview structure with one-level-deep references to six real bundle files (overlap.md, coverage.md, tokenizers.md, refget.md, cli.md, python-api.md), each clearly signaled and summarized in a dedicated Reference Documentation section.	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 strong, specific description that clearly states both the toolkit's capabilities and when to invoke it, with natural trigger terms for a computational genomics audience. Only minor trigger-term breadth keeps it from a perfect score.

Dimension	Reasoning	Score
Specificity	The description names the domain ('genomic interval analysis in Rust with Python bindings') and lists multiple concrete actions — overlap detection, coverage tracks, tokenization for ML, fragment analysis, reference sequence management — giving comprehensive coverage.	5 / 5
Completeness	It explicitly answers both 'what' (toolkit for genomic interval analysis with the listed capabilities) and 'when' ('Use when working with genomic regions, BED files, coverage tracks...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural keywords a genomics user would say ('genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, fragment analysis'), but a few natural terms and extensions present in the skill (BigWig, WIG, FASTA, single-cell) are missing from the description.	4 / 5
Distinctiveness Conflict Risk	The niche is clearly specialized (Rust genomic interval toolkit with Python bindings) and the triggers are domain-specific enough that overlap with unrelated skills is minimal.	5 / 5
	Total	19 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/coding/gtars/SKILL.md
Commit: 3a6c3a9

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.