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

80%

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 ./skills/gtars/SKILL.md

Quality

Content

85%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 highly actionable with clear, validated workflows and exemplary progressive disclosure to six real reference files. The main weakness is conciseness: time-sensitive version/release dates are inlined rather than isolated in a deprecated section, adding tokens that age quickly.

Suggestions

Move exact release dates and the 2026-07-23 version snapshot into a dedicated, clearly labeled version/deprecated section so the core guidance stays evergreen.

Consider trimming the 'Verified snapshot' provenance detail (per-archive .sha256 sidecars, changelog-stops-at-0.5.1) into references/cli.md to reduce body length.

Tighten the 'Network and cache gate' bullet list, which repeats side-effect disclosures already implied by the gate's approval requirement.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and information-dense with non-obvious domain gotchas (u32 coordinate limits, lexicographic sort, strand vector init to '*'), but the body is long and embeds time-sensitive version/release dates ("released 2026-06-17", "snapshot 2026-07-23") outside a deprecated/old-patterns section, which the rubric penalizes.	3 / 5
Actionability	Provides copy-paste-ready, executable bash, Python, and TOML snippets covering the common cases (RegionSet construction, overlap/count/coverage calls, tokenizer usage, refget stores, install/validate commands), matching the score-5 anchor.	5 / 5
Workflow Clarity	The 'Safe local workflow' and 'Native-code trust gate' give clearly sequenced numbered steps with explicit validation checkpoints and feedback loops (validate -> pilot -> revalidate output sorting/bounds/checksums), appropriate for batch/destructive genomic operations.	5 / 5
Progressive Disclosure	The body is a concise overview pointing to exactly six one-level-deep references, all clearly signaled in the 'Bundled references' section and verified present in references/ (python-api, overlap, coverage, tokenizers, refget, cli), with no nested reference chains.	5 / 5
	Total	18 / 20 Passed

Description

75%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 and distinctive with strong domain trigger terms, but it lacks an explicit "Use when..." trigger clause, capping completeness. Adding concrete trigger guidance (e.g., "Use when working with BED files or genomic intervals...") would raise it.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when working with BED files, genomic intervals, overlaps, or refget/BEDbase'.

Include file-extension/synonym triggers such as '.bed', 'BED files', or 'intervals' to broaden natural keyword coverage.

Rephrase to third-person declarative voice ('Processes genomic intervals...') to avoid the imperative 'Use Gtars' framing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "set algebra, overlaps and counts, consensus and coverage, tokenization, fragment processing, and refget/BEDbase planning" — with comprehensive coverage across Python, Rust, and the CLI, matching the score-5 anchor that enumerates several specific concrete actions.	5 / 5
Completeness	The "what" is clear and detailed, but there is no explicit "Use when..." clause or equivalent trigger guidance — the "when" is only weakly implied by "Use Gtars for...", which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Strong natural domain terms a genomics user would say ("genomic interval", "overlaps", "coverage", "tokenization", "refget/BEDbase") plus language triggers (Python, Rust, CLI), but missing common synonyms/file extensions like "BED files" or ".bed" that would push it to a 5.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (local genomic interval models / refget / BEDbase) with distinct triggers and minimal overlap risk with other skills, matching the score-5 anchor.	5 / 5
	Total	17 / 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: 49c6e97

Reviewed: 9 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.