CtrlK
BlogDocsLog inGet started
Tessl Logo

500-frameworks-micronaut-create-project

Use when you need to create a new Maven-based Micronaut 4.x project using SDKMAN-managed Java and Micronaut CLI tooling. This should trigger for requests such as Create a Micronaut Maven project; Bootstrap Micronaut project with SDKMAN; Generate a new Micronaut service; Create Micronaut 4 Maven project; Scaffold Micronaut service with Java 25. Part of Plinth Toolkit

68

Quality

86%

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

71%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 well-structured skill body: lean constraints, a sequenced workflow with verification checkpoints, and exemplary one-level-deep progressive disclosure into a real, command-rich reference file. Its main weaknesses are redundancy (duplicated trigger list, triple reference pointer, coverage bullets restating the workflow) and the absence of any inline failure-handling guidance.

Suggestions

Remove the 'When to use this skill' section — it duplicates the frontmatter description's trigger phrases verbatim — and drop the 'BEFORE APPLYING' constraint or the '## Reference' section so the reference file is pointed to exactly once.

Replace the 'What is covered in this Skill?' bullet list with the Workflow section itself, since the bullets restate the same steps without adding information.

Add one line of failure guidance to Workflow step 4 (e.g., 'If verification fails, report the failing Maven goal and the corrective action before retrying') so the error-recovery loop exists in the body, not only in the reference.

DimensionReasoningScore

Conciseness

No concept over-explanation, but there is noticeable redundancy: the five trigger phrases from the description are repeated verbatim in 'When to use this skill', the reference file is pointed to three times ('BEFORE APPLYING' constraint, Workflow step 1, and the '## Reference' section), and the 'What is covered in this Skill?' bullets largely restate the Workflow steps. This fits anchor 3 ('could be tightened') better than 4, where only minor trimming would be needed.

3 / 5

Actionability

Concrete commands are present for the checkpoints ('sdk version', './mvnw clean verify', 'mvn clean verify') and constraints are specific (Java 25, Micronaut 4.x, Maven-only, non-empty-directory guard). The core creation command ('mn create-app ... --build=maven --jdk=25 ...') lives only in the reference file — an acceptable progressive-disclosure split since the body mandates reading the reference first, but it leaves a minor gap that keeps this below 5.

4 / 5

Workflow Clarity

The four-step workflow is clearly sequenced with validation on both ends: prerequisite check ('sdk version' before anything else) and post-creation verification ('./mvnw clean verify', with an mvnw fallback), plus a safety checkpoint on non-empty target directories. It falls short of anchor 5 because the body has no error-recovery loop if verification fails — what to do on failure is only in the reference.

4 / 5

Progressive Disclosure

The body is a genuine overview that pushes all command-level detail (SDKMAN candidate management, 'mn create-app' syntax) into exactly one reference file, which exists, is one level deep, and is clearly signaled by a dedicated '## Reference' section with a proper markdown link. This matches the anchor-5 pattern of a clear overview with well-signaled, one-level-deep references.

5 / 5

Total

16

/

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: it clearly states what the skill does and when to use it, backed by five natural, synonym-rich trigger phrases. The only minor gap is that it describes a single scaffolding action rather than enumerating several capabilities, keeping specificity just below the top anchor.

DimensionReasoningScore

Specificity

The description states a concrete action — 'create a new Maven-based Micronaut 4.x project' — with specific qualifiers ('SDKMAN-managed Java', 'Micronaut CLI tooling', 'Java 25'). It names one core action with rich domain detail rather than the multiple distinct actions of a 5 ('extract, fill forms, merge'), but is far more specific than the 1-2 generic actions of a 3 ('Processes PDF files and extracts content').

4 / 5

Completeness

It explicitly answers 'what' ('create a new Maven-based Micronaut 4.x project using SDKMAN-managed Java and Micronaut CLI tooling') and 'when' ('Use when you need to... This should trigger for requests such as...') with concrete trigger phrases, matching the 5 anchor exactly.

5 / 5

Trigger Term Quality

Five natural trigger phrases are listed with verb synonyms users would actually say: 'Create a Micronaut Maven project', 'Bootstrap Micronaut project with SDKMAN', 'Generate a new Micronaut service', 'Scaffold Micronaut service with Java 25' — covering create/bootstrap/generate/scaffold plus version variants. File extensions are not applicable to a project-scaffolding skill, so no natural term category is missing.

5 / 5

Distinctiveness Conflict Risk

The niche is narrow and unambiguous — Micronaut + Maven + SDKMAN + Java 25 project scaffolding — with trigger phrases that would not plausibly fire for other skills. The 'Part of Plinth Toolkit' tag identifies its family without blurring its own triggers.

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
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.