CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

128-java-generics

Use when you need to review, improve, or refactor Java code for generics quality — including avoiding raw types, applying the PECS (Producer Extends Consumer Super) principle for wildcards, using bounded type parameters, designing effective generic methods, leveraging the diamond operator, understanding type erasure implications, handling generic inheritance correctly, preventing heap pollution with @SafeVarargs, and integrating generics with modern Java features like Records, sealed types, and pattern matching. This should trigger for requests such as Improve the code with Generics; Apply Generics; Refactor the code with Generics; Improve generic type safety in Java APIs; Fix raw types and unchecked casts in Java code. 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 overview body with excellent progressive disclosure (a single one-level-deep, clearly signaled reference) and a sound compile-then-verify workflow with blocking failure conditions. The main weakness is redundancy: trigger phrases and build commands are each repeated across sections, which costs tokens without adding guidance.

Suggestions

Remove the 'When to use this skill' section — it duplicates the frontmatter description's trigger phrases verbatim and adds no new information to the body.

Deduplicate the build commands: keep the compile/verify commands in the Workflow steps alone (or the Constraints section alone) instead of repeating them with overlapping MANDATORY/SAFETY/VERIFY bullets in both places.

Tighten step 3 ('Apply generics refactorings') by naming which reference sections to consult for the common refactorings (raw types, wildcards, bounded types), making the pointer as actionable as the build steps.

DimensionReasoningScore

Conciseness

Mostly efficient — no over-explanation of concepts Claude already knows — but noticeably redundant: the 'When to use this skill' section duplicates the description's trigger list verbatim, and the compile/verify commands are stated twice (Constraints section plus Workflow steps 1 and 4, with overlapping MANDATORY/SAFETY/VERIFY bullets). Fits 'mostly efficient but could be tightened'; not 2 (no padding or concept tutorials), not 4 (the duplication is more than minor).

3 / 5

Actionability

Concrete executable commands ('./mvnw compile', './mvnw clean verify') and a named, existing reference file (references/128-java-generics.md) with clear pointers to detailed good/bad examples. Not 5 — step 3 ('Apply generics refactorings... while preserving behavior') is high-level and defers all specifics to the reference, leaving minor gaps.

4 / 5

Workflow Clarity

Four clearly sequenced steps with explicit validation checkpoints: compile-before with a blocking failure condition ('stop immediately if compilation fails') and verify-after ('Run ./mvnw clean verify'). Not 5 — there is no fix-and-retry feedback loop (on failure it only stops); not 3 — validation checkpoints are explicit, not missing.

4 / 5

Progressive Disclosure

The body is a lean overview that defers all detailed good/bad code patterns to a single, clearly signaled, one-level-deep reference ('## Reference' with a markdown link plus workflow step 2 naming the file), and that file exists in the bundle. Not 4 — structure, signaling, and split are all clean with no organization gaps.

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: comprehensive concrete capabilities, an explicit and natural trigger-phrase list, and a clearly distinct Java-generics niche. The only deduction is the second-person phrasing ('Use when you need to review...'), which the voice guideline penalizes on specificity.

DimensionReasoningScore

Specificity

Lists multiple concrete, comprehensive actions ('avoiding raw types, applying the PECS... principle, using bounded type parameters, designing effective generic methods, leveraging the diamond operator, understanding type erasure implications, preventing heap pollution with @SafeVarargs'), matching the 5 anchor. Reduced by 1 per the judging guideline penalizing second-person voice ('Use when you need to review...') — not 3, since coverage goes far beyond 1-2 actions.

4 / 5

Completeness

Clearly answers both 'what' (a detailed list of generics capabilities) and 'when' (an explicit trigger-phrase list). Not 4 — the 'when' is not merely present but given as concrete, user-natural trigger phrases.

5 / 5

Trigger Term Quality

Explicit natural trigger phrases users would say ('This should trigger for requests such as Improve the code with Generics; Apply Generics; Refactor the code with Generics; Fix raw types and unchecked casts in Java code') plus domain keywords (raw types, PECS, unchecked casts, @SafeVarargs). Not 4 — coverage of natural phrasings is comprehensive, not just 'good with a few missing'.

5 / 5

Distinctiveness Conflict Risk

Clearly scoped to Java generics with niche-specific triggers ('Fix raw types and unchecked casts in Java code', 'Improve generic type safety in Java APIs'); minimal conflict risk with sibling skills. Not 4 — 'minor overlap risk' understates how tightly every trigger is generics-specific.

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/128-java-generics/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.