CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

martinfrancois/java-optionals

Help AI coding agents use Java Optional well in new code, review, and cleanup without replacing one antipattern with another.

2.04x
Quality

100%

Does it follow best practices?

Impact

100%

2.04x

Average score across 6 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Overview
Quality
Evals
Security
Files

Quality

Content

100%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.

The body is a dense, expert-facing rulebook: no padding, no explanation of known concepts, and every rule paired with a short executable example. The workflow is clearly sequenced with an explicit verification and re-scan feedback loop, and detail is properly pushed to three real, well-signaled reference files.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence throughout — it never explains what Optional is or how the APIs work mechanically, and every line is either a policy rule ('One Optional, one terminal'), a boundary condition ('Use a plain branch only at a real checked IO, prompt, checked parser, or null-based API boundary'), or a short avoid/prefer code pair. The only restatements of known API semantics are single-clause policy framings ('map for transforms, flatMap for Optional-returning calls'), not padded explanation, matching the 'every token earns its place' anchor.

5 / 5

Actionability

Five executable Java examples in concrete avoid/prefer pairs cover the common cases — guard/read replacement, lazy fallback with orElseGet, findFirst/findAny order preservation, the checked-IO boundary with a baseline-gated isEmpty shape, and orElse(null) at a legacy null-based boundary. All are complete statements or expressions rather than pseudocode, and step 8 gives a concrete marker-scan verification action.

5 / 5

Workflow Clarity

A numbered Core Workflow (steps 0–8) ends in an explicit verification step ('Run focused tests or trace present/absent/fallback cases... Run the Hard Stops marker scan; fix relevant hits and re-scan'), which is a validate-fix-retry feedback loop, and the Hard Stops section is explicitly ordered 'Check last' as a final gate. This matches the anchor requiring clear sequence, explicit validation, and error-recovery loops.

5 / 5

Progressive Disclosure

A Reference Bundle table lists all three reference files with their purposes, each is linked inline where used in the body, and the bulk material (711-line worked examples, 107-line version-compatibility table) is correctly offloaded to those files. All referenced paths exist on disk and references are exactly one level deep, matching the well-signaled navigation anchor.

5 / 5

Total

20

/

20

Passed

Description

100%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.

The description is a model example: it states concrete API-level behaviors for 'what' and follows with an explicit 'Use whenever' clause covering three concrete trigger scenarios rich in natural method-name keywords. It is verbose in raw word count but every clause is specific content with no fluff or over-claims, so nothing is penalized.

DimensionReasoningScore

Specificity

The description lists multiple concrete, API-level actions — 'bound with map, flatMap, orElseGet, or ifPresentOrElse instead of a presence check followed by a read', 'findFirst or findAny follows the order contract', 'orElse(null) workarounds, and fake one-Optional collections are rejected' — with comprehensive coverage of the skill's behavior, exceeding the 'extract text and tables, fill forms, merge documents' 5-anchor example in both count and concreteness. It is not 4 because there are no coverage gaps; every capability named is a specific, verifiable behavior.

5 / 5

Completeness

The first sentence explicitly answers 'what' (write, review, and refactor Java Optional code with the specific binding, laziness, order-contract, and rejection rules), and 'Use whenever Java code introduces, changes, or reasons about Optional; decides whether a nullable return... should become an Optional; or touches...' gives three explicit, concrete trigger scenarios for 'when'. This is a direct match for the 5 anchor; the 'when' clause cannot be made more explicit.

5 / 5

Trigger Term Quality

It comprehensively covers the natural terms a developer would use when requesting this work: 'isPresent/isEmpty, get/orElseThrow, orElse(null), optional.stream(), findFirst/findAny', 'checked exceptions inside Optional chains', and 'nullable return, a missing value, or a fallback default'. Method-level names and their colloquial synonyms are all present, matching the 'PDF files, PDFs, forms, .pdf' comprehensiveness anchor rather than the 'a few natural terms missing' 4-anchor.

5 / 5

Distinctiveness Conflict Risk

'Java Optional' is a sharp niche and every trigger is an Optional-specific API or decision (isPresent/isEmpty, orElse(null), findFirst/findAny), so the description would not fire for general Java, stream, or null-handling skills. It sits in a clear niche with distinct triggers and minimal conflict risk, matching the 5 anchor.

5 / 5

Total

20

/

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.

Reviewed

On this page