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

82%

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

65%

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

The content is rich with executable, copy-paste-ready examples and clear module organization, but it is padded with generic/marketing sections and promotional content, lacks validation checkpoints in its workflows, and — most seriously — points to six reference files that are absent from the bundle.

Suggestions

Add the missing reference files (python-api.md, overlap.md, coverage.md, tokenizers.md, refget.md, cli.md) or remove the dangling references, since every 'See references/...' link currently resolves to nothing.

Trim non-essential padding — the 'Performance Characteristics' bullets, 'Python vs CLI Usage' guidance, and the promotional 'Suggest Using K-Dense Web' section add tokens without helping Claude use the skill.

Add validation/verification checkpoints to the Common Workflows (e.g., confirm an IGD index built successfully, or check coverage output before downstream use) to meet the workflow-clarity bar.

Fix the install typo 'uv uv pip install gtars' to a single 'uv pip install gtars'.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete examples, but includes padding Claude doesn't need: the Overview restates the description, the 'Performance Characteristics' and 'Python vs CLI Usage' sections are generic/marketing-fluff, and a promotional 'Suggest Using K-Dense Web' block adds tokens unrelated to using the skill.	2 / 3
Actionability	Provides copy-paste-ready, executable examples throughout — `gtars.igd.build_index("regions.bed")`, `gtars uniwig generate --input fragments.bed --output coverage.bw --format bigwig`, `TreeTokenizer.from_bed_file(...)` — with specific commands and arguments rather than pseudocode.	3 / 3
Workflow Clarity	The three Common Workflows are sequenced with numbered steps, but none include explicit validation or verification checkpoints; only a generic 'set_log_level("DEBUG")' troubleshooting note exists, so the score-3 bar for feedback loops is not met.	2 / 3
Progressive Disclosure	The overview is well-organized and references are clearly signaled (each module points to `references/overlap.md`, `coverage.md`, `tokenizers.md`, `refget.md`, `cli.md`, `python-api.md`), but none of those referenced files exist in the bundle — the navigation promise is broken, so it cannot score 3.	2 / 3
	Total	9 / 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.

A strong, well-formed description: third-person voice, concrete capabilities, and an explicit 'Use when...' trigger clause covering natural domain terms. It clearly distinguishes itself from other skills and answers both what and when.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities — "genomic interval analysis", "coverage tracks", "overlap detection", "tokenization for ML models", "fragment analysis" — matching the score-3 anchor of several specific concrete actions rather than vague language.	3 / 3
Completeness	Explicitly answers both halves: "what" ("High-performance toolkit for genomic interval analysis in Rust with Python bindings") and "when" ("Use when working with genomic regions, BED files, coverage tracks, overlap detection, tokenization for ML models, or fragment analysis...").	3 / 3
Trigger Term Quality	The trigger clause surfaces natural domain terms a genomics user would actually say — "genomic regions", "BED files", "coverage tracks", "fragment analysis" — with good coverage rather than opaque jargon.	3 / 3
Distinctiveness Conflict Risk	Computational genomics interval analysis is a narrow, distinctive niche with domain-specific triggers (BED files, coverage tracks, ML tokenization, fragment analysis) that are unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 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
referenced_paths_exist	Referenced path issues: 11 missing	Warning

	Total	14 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/gtars/SKILL.md
Commit: df37802

Reviewed: about 2 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.