julia-pro

Master Julia 1.10+ with modern features, performance optimization, multiple dispatch, and production-ready practices. Expert in the Julia ecosystem including package management, scientific computing, and high-performance numerical code. Use PROACTIVELY for Julia development, optimization, or advanced Julia patterns.

Quality

53%

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/julia-pro/SKILL.md

Quality

Content

31%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 content is an exhaustive capability inventory rather than actionable skill guidance: it lists packages and traits Claude already knows, provides no executable code or validation steps, and inlines everything in one large file. It needs concrete examples, a real workflow with checkpoints, and split-out reference files.

Suggestions

Replace the package-ecosystem enumeration with a few concrete, executable examples (e.g. a Pkg.jl workflow snippet, a @code_warntype type-stability check) and keep only skill-specific guidance Claude would not already know.

Tighten the 'Response Approach' into a real workflow with explicit validation checkpoints (e.g. 'run @code_warntype; if type-unstable, refactor and re-check') instead of abstract verb phrases.

Move the long capability lists into separate reference files under references/ and link to them from a concise SKILL.md overview, so the body is a lean entry point rather than a monolithic catalog.

Dimension	Reasoning	Score
Conciseness	The body is a long padded enumeration of the entire Julia package ecosystem (Flux.jl, Genie.jl, CUDA.jl, etc.) and capabilities Claude largely already knows, repeating domain knowledge rather than adding skill-specific guidance.	2 / 5
Actionability	It offers only high-level hints and abstract capability lists ('Implement with type annotations', 'Profile and optimize using BenchmarkTools.jl') with no executable code, concrete commands, or copy-paste examples.	2 / 5
Workflow Clarity	The 'Response Approach' provides a rough 8-step sequence, but the steps are abstract verb phrases with no validation checkpoints or concrete commands, and the generic 'Instructions' section adds little.	3 / 5
Progressive Disclosure	All content lives in one monolithic file with no bundle files or references; the large package-listing sections clearly belong in separate reference files but are fully inlined with no navigation.	2 / 5
	Total	9 / 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.

A solid, mostly third-person description that names a distinct domain and includes an explicit 'Use when' clause. It is specific and complete enough to trigger correctly, with minor room for more natural synonyms and concrete trigger phrases.

Dimension	Reasoning	Score
Specificity	The description lists several concrete capability areas ('multiple dispatch', 'performance optimization', 'package management', 'scientific computing', 'high-performance numerical code') rather than a single vague domain, with only minor gaps in coverage.	4 / 5
Completeness	It clearly answers 'what' (Julia expertise across modern features and ecosystem) and 'when' ('Use PROACTIVELY for Julia development, optimization, or advanced Julia patterns'), but the 'when' could be more explicit with concrete trigger situations.	4 / 5
Trigger Term Quality	It includes natural trigger phrases ('Julia development', 'optimization', 'advanced Julia patterns') users would say, but lacks synonyms or file extensions and relies on a narrow set of terms.	4 / 5
Distinctiveness Conflict Risk	It is a clearly Julia-specific niche with distinct triggers ('Julia 1.10+', 'multiple dispatch'), giving minimal conflict risk with only minor overlap against general programming skills.	4 / 5
	Total	16 / 20 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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: rmyndharis/antigravity-skills
Path: skills/julia-pro/SKILL.md
Commit: 3eff4af

Reviewed: 1 day 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.