code-quality

Comprehensive code review for Java - clean code principles, API contracts, null safety, exception handling, and performance. Use when user says "review code", "refactor", "check API", or before merging changes.

Quality

81%

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

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 highly actionable, example-rich review reference with clear sectioning and a sensible workflow. Its weaknesses are the absence of progressive disclosure (one large monolithic file) and minor redundancy from the repeated Quick Reference Flags table.

Suggestions

Move the detailed code-pattern catalog (HTTP verb tables, status-code tables, per-category violation/fix examples) into reference files under references/ and keep SKILL.md as a concise overview pointing to them, improving progressive_disclosure.

Drop or slim the "Quick Reference Flags" table since it duplicates the Flags already enumerated in each category section, reducing redundancy and token cost.

Add an explicit validation checkpoint to the Review Strategy (e.g. "Confirm every Critical/Important finding cites a file and line number before writing the summary") to strengthen workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is mostly code examples (violation/fix pairs) and tables with minimal concept over-explanation, but the "Quick Reference Flags" table largely repeats the flags already listed per section, a minor redundancy that could be trimmed; not 5 because of that padding.	4 / 5
Actionability	Concrete, copy-paste-ready Java examples cover the common review cases (NPE, N+1, resource leaks, broad catches, wrong HTTP verbs, missing @Transactional), with paired ❌ violation and ✅ fix snippets plus lookup tables for verbs and status codes.	5 / 5
Workflow Clarity	A clear three-step Review Strategy (scan, checklist pass, summary) backed by categorized checklists and a structured output format gives a clear sequence, but there is no explicit validation checkpoint (e.g. verifying each finding cites a line number) within the process.	4 / 5
Progressive Disclosure	Section headers organize the ~340-line body well, but everything is inlined in a single file with no references to separate files; the detailed reference tables and code-pattern catalog are content that could be split out, fitting the 3-anchor (structure present but content that should be separate is inline).	3 / 5
	Total	16 / 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 that clearly states both capability and triggering context with natural user phrases and Java-specific scoping. The main gap is that review domains are listed as topics under a single action rather than as distinct concrete actions.

Dimension	Reasoning	Score
Specificity	Lists several specific review domains ("clean code principles, API contracts, null safety, exception handling, and performance") rather than vague language, but they are categories under one verb ("review") rather than the distinct concrete actions (extract/fill/merge) the 5-anchor requires.	4 / 5
Completeness	Explicitly answers both what ("Comprehensive code review for Java - clean code principles, API contracts, null safety, exception handling, and performance") and when ("Use when user says \"review code\", \"refactor\", \"check API\", or before merging changes") with concrete trigger phrases, matching the 5-anchor structure.	5 / 5
Trigger Term Quality	Natural trigger phrases users would actually say are present ("review code", "refactor", "check API", "before merging changes"), giving good coverage, but a few common synonyms (e.g. "code review", "check this PR") appear only in the body and are missing from the description.	4 / 5
Distinctiveness Conflict Risk	The Java-specific niche plus concrete triggers make it mostly distinct with minimal overlap risk, but "code review" is a broad category that could still collide with general or other-language review skills, so it is not a fully clean niche.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: piomin/claude-ai-spring-boot
Path: .claude/skills/code-quality/SKILL.md
Commit: d87e7a3

Reviewed: ~20 hours 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.