Java review

Skill ducpm2303/claude-java-plugins/plugins/java-core/skills/java-review

Reviews Java code for bugs, naming issues, code smells, and version-appropriate idioms. Use when user asks to "review this code", "check my Java", "look at this class", "find issues in", "code review", "what's wrong with this", or "review this file".From its SKILL.md

Install

npx -y skills add ducpm2303/claude-java-plugins --skill java-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
17 stars17 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.5 KB, 742 tokens by cl100k_base, as published. Nobody here has run it

Review the Java code I've selected or provided. Follow these steps:

Step 1 — Detect Java version

Check the project for pom.xml (look for <java.version> or <maven.compiler.source>) or build.gradle (look for sourceCompatibility). If not found, ask: "What Java version are you targeting? (8, 11, 17, 21, or other)"

Step 2 — Review for bugs and correctness

Null safety: flag unguarded dereferences; suggest Optional<T> (Java 8+) for values that may be absent
Resource leaks: flag unclosed InputStream, Connection, PreparedStatement; suggest try-with-resources
equals/hashCode: if one is overridden without the other, flag it
Collection mutation: flag modification of a collection while iterating over it
Thread safety: flag shared mutable fields accessed from multiple threads without synchronization
Off-by-one: review loop bounds and index access

Step 3 — Review naming and style

Classes/interfaces: must be PascalCase
Methods/variables: must be camelCase
Constants (static final): must be SCREAMING_SNAKE_CASE
Flag single-letter variable names outside of loop counters (i, j, k)
Flag abbreviations that reduce clarity (e.g., usr → user, mgr → manager)

Step 4 — Review Java idioms (version-aware)

For each suggestion involving a version-gated feature, state: "Requires Java X+"

Java 8+: suggest streams/lambdas over verbose imperative loops where clarity improves
Java 8+: suggest try-with-resources for Closeable resources
Java 10+: suggest var where the type is obvious from the right-hand side
Java 16+: suggest records for classes that are pure data holders with no behaviour
Java 17+: suggest sealed classes for fixed hierarchies; pattern matching for instanceof chains

Step 5 — Review code smells

Methods longer than 20 lines: suggest extracting to named helper methods
Classes with more than one clear responsibility: suggest splitting
Magic numbers/strings: suggest named constants
Deep nesting (more than 3 levels): suggest early returns or extraction

Output format

Respond with:

Summary — 1–2 sentences overall assessment
Issues — grouped by severity:
- 🔴 Critical (bugs, resource leaks, thread safety)
- 🟡 Warning (naming, missing equals/hashCode, raw types)
- 🔵 Suggestion (idiom improvements, version-gated enhancements)
Strengths — what is done well (at least one observation)

Be concise. Each issue: one sentence description + one-line fix example.

Next Steps

After completing this review, offer these follow-up actions based on findings:

If structural issues found (long methods, god classes) → suggest running /java-refactor
If missing or inadequate tests found → suggest running /java-test
If security issues found (SQL concat, hardcoded secrets, weak crypto) → suggest delegating to the java-security-reviewer agent
If performance issues found (N+1, unbounded queries, String concatenation in loops) → suggest delegating to the java-performance-reviewer agent
If Javadoc is missing on public API → suggest running /java-docs

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most review quality skills give in 742 tokens

Counted across 1,048 of the 1,783 authors here whose files we hold, read 2026-08-07

Ask questions one at a timein 81 of 1048, across 64 files
Provide a recommended answer for each questionin 73 of 1048, across 50 files
Explore the codebase instead of asking answerable questionsin 66 of 1048, across 42 files
Resolve dependencies between decisions one-by-onein 42 of 1048, across 17 files
Interview the user relentlessly about the planin 38 of 1048, across 13 files
Order findings by severityin 31 of 1048
Resolve each branch of the decision treein 27 of 1048, across 5 files
Run a grilling sessionin 26 of 1048, across 5 files
Update CONTEXT.md immediately when a term is resolvedin 26 of 1048, across 11 files
Propose precise canonical terms for vague languagein 25 of 1048, across 7 files
Create documentation files lazilyin 24 of 1048, across 5 files
Assign severity to every findingin 24 of 1048

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.