gtars

Use Gtars for local genomic interval models and set algebra, overlaps and counts, consensus and coverage, tokenization, fragment processing, and refget/BEDbase planning across Python, Rust, and the CLI.

Quality

85%

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

88%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 dense, well-structured skill with executable commands, clear sequenced workflows with validation checkpoints, and clean one-level-deep references to real bundle files. Its only weakness is token cost: provenance and version archaeology sections are thorough but could be trimmed.

Suggestions

Condense the 'Verified snapshot' and version-archaeology prose; move exhaustive provenance detail into a reference file to recover token budget.

Consider relocating the license-discrepancy caveat to the artifact-inspector reference rather than the main body.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient and assumes domain competence, but the 'Verified snapshot', 'Native-code trust gate', and license-caveat sections carry provenance detail and version archaeology that pads the token budget beyond what is strictly needed to act.	4 / 5
Actionability	Provides copy-paste-ready uv/cargo install commands, exact pinned dependencies, executable Python import examples, and concrete validator invocations covering the common local cases.	5 / 5
Workflow Clarity	The 'Safe local workflow' is a clearly sequenced six-step process with explicit validation (run the local validator first, revalidate output), and the trust gate and data contract add feedback-checkpoint guidance for batch/genomic operations.	5 / 5
Progressive Disclosure	SKILL.md is an overview with one-level-deep references to six real, well-signaled reference files (confirmed present in references/) and bundled scripts, each linked inline with a one-line description; bulk detail is offloaded appropriately.	5 / 5
	Total	19 / 20 Passed

Description

81%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 highly specific, distinctive description naming concrete genomic operations across three language surfaces. Its main gap is the absence of an explicit 'Use when...' trigger clause, which leaves the invocation conditions implicit.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g. 'Use when computing BED interval overlaps, coverage, or refget/BEDbase digests across Python, Rust, or the CLI').

Include common file extensions and synonyms (BED, BED files, .bed.gz, bigWig) to improve natural trigger term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('overlaps and counts, consensus and coverage, tokenization, fragment processing, and refget/BEDbase planning') across three surfaces (Python, Rust, CLI), giving comprehensive coverage of the domain.	5 / 5
Completeness	Clearly states what the skill does (the enumerated genomic operations and surfaces), but there is no explicit 'Use when...' clause describing when Claude should invoke it, so the 'when' is only weakly implied rather than stated.	4 / 5
Trigger Term Quality	Contains relevant domain keywords ('genomic interval', 'overlaps', 'coverage', 'tokenization', 'refget', 'BEDbase') that a user working in genomics would say, but lacks common synonyms or file extensions (e.g. BED/BED files, bigWig) that would round out coverage.	4 / 5
Distinctiveness Conflict Risk	The niche is sharply defined (genomic interval set algebra and refget/BEDbase across Python/Rust/CLI) with terminology unlikely to match any other skill, minimizing conflict risk.	5 / 5
	Total	18 / 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: K-Dense-AI/scientific-agent-skills
Path: skills/gtars/SKILL.md
Commit: b2a92ba

Reviewed: 3 days 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.