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

83%

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

85%

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

The body is highly actionable and well-structured, with clear validation-gated workflows and a clean one-level-deep reference layout whose bundle files all exist. The main weakness is conciseness: dated version-snapshot detail sits in the main flow rather than a deprecated/old-patterns section.

Suggestions

Move the dated "Verified snapshot" release dates and version pins into a clearly labeled version/maintenance section (or strip release dates) so time-sensitive detail does not penalize conciseness.

Tighten the prose around the data-contract and side-effects sections, which at times restates rules already implied by the numbered steps.

Dimension	Reasoning	Score
Conciseness	Mostly efficient domain prose, but the "Verified snapshot (2026-07-23)" section with specific release dates and per-version pins is time-sensitive information outside a deprecated/old-patterns section, which the guideline penalizes; not 1 because it does not pad with concepts Claude already knows, and not 3 because it could be tightened and the dated pins relocated.	2 / 3
Actionability	Provides fully executable, copy-paste-ready bash install commands, Python import snippets, TOML dependency pins, and exact validator CLI invocations with concrete arguments, matching the anchor for copy-paste-ready examples; not 2 because nothing is left as pseudocode.	3 / 3
Workflow Clarity	The numbered "Safe local workflow" sequences validation checkpoints (step 2 validate/pilot, step 6 revalidate output) and the "Native-code trust gate" gives an ordered review sequence with explicit refusal conditions; not 2 because validation is explicit rather than implied.	3 / 3
Progressive Disclosure	The body is an overview that clearly signals one-level-deep references (e.g. "Read references/python-api.md", "See references/tokenizers.md") and lists all six bundled references with one-line descriptions; all referenced reference and script files were verified present on disk.	3 / 3
	Total	11 / 12 Passed

Description

82%

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 and distinctive with strong domain trigger terms, but omits an explicit "Use when…" trigger clause, leaving the when-to-use intent implied rather than stated. Adding trigger guidance would lift completeness from 2 to 3.

Suggestions

Append an explicit trigger clause, e.g. "Use when working with genomic intervals, BED files, region overlaps/coverage, region tokenizers, or refget/BEDbase references across Python, Rust, or the CLI."

Add a couple of natural user-phrasing variants ("BED overlaps", "region coverage", "tokenize BED regions") to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "set algebra, overlaps and counts, consensus and coverage, tokenization, fragment processing, and refget/BEDbase planning across Python, Rust, and the CLI" — matching the anchor for multiple specific actions rather than the partial domain-plus-actions anchor at 2.	3 / 3
Completeness	Clearly states what the skill does but has no "Use when…" clause or equivalent explicit trigger guidance, so per the judging guideline completeness is capped at 2; it is not 3 because the when is only implied, and not 1 because the what is well covered.	2 / 3
Trigger Term Quality	Natural domain keywords a genomics user would actually say ("overlaps and counts", "consensus and coverage", "tokenization", "fragment processing", "refget/BEDbase") give good coverage; not the jargon-only or single-keyword anchors at 1-2.	3 / 3
Distinctiveness Conflict Risk	The narrow genomic-interval and refget/BEDbase niche with distinct domain triggers is clearly distinguishable and unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/gtars/SKILL.md
Commit: 757b63b

Reviewed: about 11 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.