CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

110-java-maven-best-practices

Use when you need to review, improve, or troubleshoot a Maven pom.xml file — including dependency management with BOMs, plugin configuration, version centralization, multi-module project structure, build profiles, or any situation where you want to align your Maven setup with industry best practices. This should trigger for requests such as Review pom.xml to improve it; Apply Maven best practices to pom.xml; Improve Maven POM configuration; Review Maven dependency management and plugin configuration; Modernize Maven build conventions for a Java project. Part of Plinth Toolkit

65

Quality

82%

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

60%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 has a clear, well-validated workflow and good single-level reference structure, but it is noticeably padded: the same multi-module, untrusted-input, and allowlist rules are stated two to three times, and the 'When to use this skill' section duplicates the frontmatter description verbatim. Trimming the redundancy and adding a post-change validation step would lift it substantially.

Suggestions

Remove the 'When to use this skill' section entirely — it repeats the frontmatter description's trigger phrases verbatim and adds nothing Claude cannot already see in the description.

State each rule once: keep the operational bullets (untrusted-POM input, allowlisted extraction, multi-module discovery, cross-module scope) in the Constraints section only, and drop their duplicates from the 'What is covered in this Skill?' list.

Add a final verification step to the workflow, e.g., 'After applying recommendations, re-run ./mvnw validate and confirm the build still passes before reporting changes.'

DimensionReasoningScore

Conciseness

Noticeably verbose through duplication: the untrusted-POM/allowlist rules appear in both the 'What is covered' bullets and the Constraints list, multi-module scope is stated three times ('What is covered', Constraints, and Workflow step 3), and the 'When to use this skill' section repeats the five trigger phrases already in the frontmatter description verbatim. Several of these padded sections could be cut with no loss of guidance.

2 / 5

Actionability

Concrete commands are present ('./mvnw validate' or 'mvn validate') alongside specific tooling guidance (DOM/SAX/StAX, xmllint, Maven model APIs) and an explicit allowlist of fields to extract. Minor gap: no copy-paste example of an XML query invocation, so guidance is mostly but not fully executable.

4 / 5

Workflow Clarity

The 4-step workflow has a clear sequence with an explicit upfront validation checkpoint and stop condition ('Run ./mvnw validate... stop if validation fails'; 'If validation fails, do not continue'). Minor gap: no post-modification verification step (e.g., re-running validate after applying recommendations), so it sits at anchor 4 rather than 5.

4 / 5

Progressive Disclosure

The bundle structure is sound: one real reference file (references/110-java-maven-best-practices.md, verified to exist), one level deep, clearly signaled in both Workflow step 2 and a dedicated 'Reference' section, and the body stays an overview. Minor gap: constraint/allowlist detail repeated inline (in 'What is covered' and Constraints) could live once in the reference, keeping the organization from fully matching the anchor-5 split.

4 / 5

Total

14

/

20

Passed

Description

95%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 strong description: explicit what-and-when structure with verbatim trigger phrases, comprehensive domain coverage, and clear niche distinctiveness. The only deduction is the second-person 'Use when you need to' phrasing, which costs one point on specificity per the judging guidelines.

DimensionReasoningScore

Specificity

Concrete actions ("review, improve, or troubleshoot a Maven pom.xml file") with comprehensive coverage of sub-domains ("dependency management with BOMs, plugin configuration, version centralization, multi-module project structure, build profiles") would rate 5, but the phrasing "Use when you need to" is second-person voice, which the guidelines penalize by reducing the specificity score by 1.

4 / 5

Completeness

Both 'what' (review/improve/troubleshoot pom.xml including the listed sub-domains) and 'when' ("Use when you need to..." plus an explicit "This should trigger for requests such as..." list of concrete trigger phrases) are clearly and explicitly stated.

5 / 5

Trigger Term Quality

Explicit natural trigger phrases are enumerated verbatim ("Review pom.xml to improve it; Apply Maven best practices to pom.xml; Improve Maven POM configuration; Review Maven dependency management and plugin configuration; Modernize Maven build conventions for a Java project") plus synonyms and the file name (pom.xml, POM, Maven, Java project).

5 / 5

Distinctiveness Conflict Risk

A clear niche (Maven pom.xml best practices) with distinct triggers (pom.xml, Maven best practices, POM configuration, Maven build conventions); minimal overlap risk with other skills.

5 / 5

Total

19

/

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

jabrena/plinth

Path

skills/110-java-maven-best-practices/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.