CtrlK
BlogDocsLog inGet started
Tessl Logo

julia-pro

Master Julia 1.10+ with modern features, performance optimization, multiple dispatch, and production-ready practices.

43

Quality

44%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/julia-pro/SKILL.md

The canonical home for this skill is julia-pro in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

35%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 well-sectioned but padded with ecosystem knowledge Claude already possesses and provides almost no executable code or commands. Its one progressive-disclosure reference is broken (the file does not exist), and workflows lack explicit validation checkpoints.

Suggestions

Cut the "Capabilities", "Knowledge Base", and "Behavioral Traits" package lists down to a few non-obvious specifics, or move them into a real reference file, to reduce token cost for things Claude already knows.

Add copy-paste-ready examples (e.g., a Pkg.jl workflow snippet, a @code_warntype type-stability check, a BenchmarkTools.jl benchmark) to make the guidance executable.

Create the referenced `resources/implementation-playbook.md` (or fix the path) and insert explicit validation steps (e.g., 'run @code_warntype; fix type instabilities; re-check') into the Response Approach so the workflow has feedback loops.

DimensionReasoningScore

Conciseness

The body devotes 80+ lines of "Capabilities", "Knowledge Base", and "Behavioral Traits" to enumerating Julia packages and ecosystem facts Claude already knows, with padded restatement across sections — fitting 'noticeably verbose; several unnecessary explanations or padded sections' below the mostly-efficient 3 anchor.

2 / 5

Actionability

There is no executable code or concrete command anywhere; guidance like "Apply relevant best practices and validate outcomes" and "Profile and optimize using BenchmarkTools.jl and Profile.jl" are high-level hints missing the specific steps to execute, matching the 2 anchor rather than the pseudocode-bearing 3 anchor.

2 / 5

Workflow Clarity

The "Response Approach" gives a clear 8-step numbered sequence (Analyze → Design → Implement → Test → Profile → Document → Format), but checkpoints are only implicit and no validation/feedback steps are defined, fitting 'steps listed but validation gaps; checkpoints missing or implicit'.

3 / 5

Progressive Disclosure

Section headers organize the body well, but the single external reference (`resources/implementation-playbook.md`) is a dangling path to a nonexistent file and the bulk package-listing that should live in a reference file is inlined, fitting 'some structure, references present but not clearly signaled, content that should be separate is inline'.

3 / 5

Total

10

/

20

Passed

Description

53%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 clearly identifies the Julia domain and several capability areas but omits any explicit 'when to use' trigger guidance, which caps completeness. It is reasonably distinct but relies on somewhat broad, buzzword-adjacent capability labels.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers (e.g., writing or optimizing Julia 1.10+ code, designing multiple-dispatch hierarchies, profiling numerical code).

Replace generic labels like 'modern features' and 'production-ready practices' with more specific concrete actions (e.g., 'optimize type-stable Julia code with @code_warntype', 'set up Pkg.jl environments').

Include natural user-facing terms and synonyms like '.jl files', 'Julia packages', and 'Pkg' to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Quotes "modern features, performance optimization, multiple dispatch, and production-ready practices" — it names the Julia domain plus several capability areas, but they are broad topic labels rather than concrete actions and several read as buzzwords, matching the 'names domain and 1-2 concrete actions, not comprehensive' anchor rather than the 4-anchor's 'several specific actions'.

3 / 5

Completeness

Provides a clear 'what' ("Master Julia 1.10+ with modern features...") but no 'Use when...' or equivalent explicit 'when' trigger guidance, so per the missing-trigger-clause cap it lands at the 'clear what, missing when' anchor.

3 / 5

Trigger Term Quality

Natural terms present ("Julia 1.10+", "multiple dispatch", "performance optimization") but missing common variations/synonyms a user might say (.jl, Julia programming, Pkg), fitting the 'some relevant keywords but missing common variations' anchor.

3 / 5

Distinctiveness Conflict Risk

"Julia 1.10+" and "multiple dispatch" carve a clear niche with low conflict risk, but the absence of explicit triggers leaves minor overlap with general scientific-computing or other language skills, fitting 'mostly distinct; minor overlap risk'.

4 / 5

Total

13

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.