CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

gtars

Supports 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

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

82%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 strong, highly actionable body: executable code and commands throughout, clearly sequenced workflows with explicit validation checkpoints, and a well-wired one-level-deep reference bundle. The main costs are dated version material parked outside a dedicated old-patterns section and an overview that carries some reference-grade detail inline.

DimensionReasoningScore

Conciseness

The body is dense with genuinely non-obvious, verified information (exact pins, sorting/strand traps, consensus semantics) and avoids explaining concepts Claude already knows, but time-sensitive material (release dates in "Verified snapshot", version pins throughout) sits outside a dedicated old-patterns section, and the citation section adds length. Above anchor 3 (only minor trimming needed); below anchor 5 because of the unparked dated snapshot details.

4 / 5

Actionability

Copy-paste-ready code and commands cover the common cases: complete Python import/usage blocks with expected outputs commented, install commands with version asserts, a pinned Cargo.toml, validator invocations with flags, and unittest discovery commands. Every example is executable rather than pseudocode, matching anchor 5.

5 / 5

Workflow Clarity

Sequences are clear with explicit validation: the trust gate (verify owner/checksums before install), the data contract with a mandatory validator run, and the six-step "Safe local workflow" ending in "Revalidate output sorting, bounds, row counts, checksums, and provenance". Not anchor 5 because error-recovery feedback loops (what to do when the validator or revalidation fails) are implicit rather than spelled out.

4 / 5

Progressive Disclosure

Good structure scored against the actual bundle: all six references cited in the body exist, are one level deep, and are indexed with one-line scopes under "Bundled references"; all six scripts listed are present with --help invocations. Not anchor 5 because the body itself carries detail that could live in those files (the full "Verified snapshot" version matrix and the migration-trap list partially duplicate references/cli.md), making the overview heavier than ideal.

4 / 5

Total

17

/

20

Passed

Description

70%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 specific, well-scoped description with strong natural domain keywords and near-zero conflict risk, weakened only by the absence of any "Use when..." trigger clause and a few missing common synonyms like "BED". Adding an explicit trigger sentence would raise completeness to the top band.

Suggestions

Append a trigger clause such as: "Use when working with BED files, genomic intervals or ranges, interval overlaps/set operations, or refget/BEDbase, in Python, Rust, or the CLI."

Add common synonyms and file extensions users naturally say, e.g. "BED files", ".bed", "genomic ranges", "peak/interval overlap".

Replace the abstract "interval models" with a concrete capability phrase (e.g. "build and query interval sets") so every named action is concrete.

DimensionReasoningScore

Specificity

The description lists several concrete actions ("set algebra, overlaps and counts, consensus and coverage, tokenization, fragment processing, and refget/BEDbase planning") plus the three language surfaces ("Python, Rust, and the CLI"), but "interval models" and "planning" are mildly abstract, leaving minor gaps versus the fully comprehensive anchor 5. It is above anchor 3 because far more than 1-2 concrete actions are named.

4 / 5

Completeness

The "what" is explicit and detailed, but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. It is not 2 because the "what" is concrete rather than vague, and not 4 because no "when" guidance is present even weakly.

3 / 5

Trigger Term Quality

Good natural keyword coverage a genomics user would actually say ("genomic interval", "overlaps", "coverage", "consensus", "tokenization", "refget", "BEDbase"), but common variations are missing, e.g. "BED files", ".bed", or "genomic ranges". Not anchor 5 (no synonyms/file extensions); clearly above anchor 3 (keywords are relevant and mostly complete, not partial).

4 / 5

Distinctiveness Conflict Risk

Clear niche with distinct triggers: "Gtars", "refget", and "BEDbase" are specific named technologies, and "genomic interval ... set algebra" scopes it tightly; minimal conflict risk with generic data-processing skills. Firmly matches anchor 5.

5 / 5

Total

16

/

20

Passed

Validation

100%

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

Reviewed

Table of Contents

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.