CtrlK
BlogDocsLog inGet started
Tessl Logo

707-technologies-hexagonal-architecture

Use when you need framework-agnostic Hexagonal architecture guidance for Java projects - ports and adapters boundaries, application core independence, driving and driven adapters, dependency direction, infrastructure leakage detection, optional architecture tests, and evidence-backed remediation. This should trigger for requests such as Review Hexagonal architecture; Review ports and adapters boundaries; Enforce dependency direction; Add ArchUnit architecture tests; Detect infrastructure leakage in domain code; Improve ports and adapters boundaries. Part of Plinth Toolkit

67

Quality

84%

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

78%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, framework-agnostic instruction skill: concise constraints, concrete Maven validation commands, a clear 4-step workflow, and a verified single-level reference split. Remaining improvement is mostly tightening duplicated trigger lists and embedding the validation feedback loop inside the workflow steps.

Suggestions

Delete or compress the "When to use this skill" section — it repeats the frontmatter description's trigger phrases verbatim and adds no new information.

Fold the MANDATORY compile / VERIFY commands into the workflow steps as explicit checkpoints (e.g. after step 3, 'run `./mvnw clean verify`; if it fails, fix and re-run') to create a true feedback loop.

Consolidate the overlapping bullets in "What is covered" and "Constraints" (e.g. ARCHUNIT OPTIONAL / DEPENDENCIES / FRAMEWORK ROUTING) to cut redundancy.

DimensionReasoningScore

Conciseness

The body is efficient: it assumes Claude knows Hexagonal architecture (no concept tutorials), states a tight scope ("For Spring Boot, Quarkus, or Micronaut runtime wiring, defer to the matching framework skill"), and uses dense bullet constraints. It is not a 5 because the "When to use this skill" section duplicates the six trigger phrases already in the frontmatter description, and the Constraints bullets partially restate the "What is covered" bullets — trimming would tighten it further.

4 / 5

Actionability

Concrete, executable guidance is present: specific commands ("Run `./mvnw compile` or `mvn compile`", "Run `./mvnw clean verify`"), a real reference path to read first, precise dependency rules ("Domain packages must not depend on application, adapter, infrastructure, framework, persistence, web, messaging, or dependency-injection APIs"), and explicit routing targets ("`111-java-maven-dependencies`"). It falls short of 5 because no concrete example of a violation/finding or a sample ArchUnit rule snippet is included in the overview, leaving minor gaps.

4 / 5

Workflow Clarity

The 4-step workflow (read reference and map the codebase → identify ports/adapters/dependency direction → review violations and propose boundary-preserving changes → recommend verification and route out-of-scope work) is a clear sequence, and validation commands exist (MANDATORY compile before changes, "Run `./mvnw clean verify` or `mvn clean verify` before promoting changes") plus explicit edge-case handling ("ask a clarifying question before editing architecture-sensitive code"). It is not a 5 because the validation checkpoints live in the Constraints section rather than being embedded as feedback loops in the workflow steps themselves (no explicit 'if compile fails, fix and re-run' loop).

4 / 5

Progressive Disclosure

The body is a lean ~60-line overview with well-signaled, one-level-deep references: step 1 directs "Read `references/707-technologies-hexagonal-architecture.md`" and a dedicated Reference section links to it. The referenced file exists and is substantive (~417 lines) with no nested references inside it, matching the 5 anchor of a clear overview with appropriately split content and easy navigation.

5 / 5

Total

17

/

20

Passed

Description

83%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 names a clear Java-specific niche, enumerates concrete capabilities, and provides explicit trigger phrases covering the main use cases. Minor deductions come from second-person phrasing and a few missing natural synonyms for the architecture domain.

Suggestions

Rewrite the opening in third person (e.g. "Provides framework-agnostic Hexagonal architecture boundary review for Java projects...") to avoid the second-person specificity penalty from "Use when you need...".

Add common user synonyms to the trigger list, such as "Review clean architecture" or "Check ports and adapters dependency direction", to broaden natural trigger coverage.

Trim trigger phrases that overlap adjacent skills (e.g. "Add ArchUnit architecture tests", which is routed to 111-java-maven-dependencies) to sharpen distinctiveness.

DimensionReasoningScore

Specificity

The description lists multiple concrete capabilities ("infrastructure leakage detection", "optional architecture tests", "evidence-backed remediation", "driving and driven adapters", "dependency direction"), matching the comprehensive anchor; however the second-person phrasing "Use when you need framework-agnostic Hexagonal architecture guidance..." incurs the mandated 1-point penalty from an otherwise anchor-5 base, landing at 4. It is not a 3 because the action coverage is far broader than the '1-2 concrete actions' anchor.

4 / 5

Completeness

It explicitly answers both questions: 'what' via the capability list ("ports and adapters boundaries, application core independence, ... infrastructure leakage detection, optional architecture tests, and evidence-backed remediation") and 'when' via "This should trigger for requests such as Review Hexagonal architecture; ..." with concrete trigger phrases. This matches the 5 anchor directly; there is no missing or weakly implied component that would drop it to 4.

5 / 5

Trigger Term Quality

Concrete trigger phrases are enumerated ("Review Hexagonal architecture; Review ports and adapters boundaries; Enforce dependency direction; Add ArchUnit architecture tests; Detect infrastructure leakage in domain code"), giving good natural-keyword coverage. It falls short of the 5 anchor because common user synonyms such as "clean architecture", "onion architecture", "ports & adapters" or "architecture review" phrasing variants are not covered.

4 / 5

Distinctiveness Conflict Risk

The niche is clear ("framework-agnostic Hexagonal architecture guidance for Java projects") with explicit routing away from framework wiring, making it mostly distinct as in the 4 anchor. It is not a 5 because phrases like "Review architecture boundaries" and "Add ArchUnit architecture tests" could plausibly overlap with a generic Java architecture-review or testing skill in the same toolkit (e.g. 111-java-maven-dependencies territory for ArchUnit additions).

4 / 5

Total

17

/

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.