CtrlK
BlogDocsLog inGet started
Tessl Logo

martinfrancois/java-streams

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

100

1.00x
Quality

100%

Does it follow best practices?

Impact

100%

1.00x

Average score across 4 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 well-structured decision-oriented workflow: terse policy rules instead of concept explanations, executable snippets and a decision table, explicit checkpoints with a validate/fix/re-scan loop, and a clean reference bundle that keeps bulk detail one level deep. It aligns closely with the rubric's good examples with no notable weaknesses.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: no concept explanations (nothing teaches what a stream or collector is), just decision tables, terse rules, and short snippets. Every line encodes a project policy choice rather than general Java knowledge — e.g., 'keep sorted(...).filter(...).findFirst() when it defines the winner' and 'Carry element + result, never null sentinels' — so every token earns its place; it is not level 4, because there is no over-explanation left to trim.

5 / 5

Actionability

Guidance is concrete and executable throughout: a Goal→Preferred API decision table ('filter(...).findAny()', 'Collectors.joining', 'mapToInt/mapToLong/mapToDouble terminals', 'Collectors.teeing'), ready-to-adapt Java snippets (count() vs forEach counter, partitioningBy, reduce with BigDecimal.ZERO, toMap with merge function and LinkedHashMap, flatMap(Optional::stream), Gatherers.mapConcurrent), and a concrete verification command ('Run the marker scan ... fix hits, and re-scan'). It is not level 4: the examples cover the common cases and are copy-paste adaptable with no pseudocode.

5 / 5

Workflow Clarity

A clearly numbered 0–7 sequence with explicit checkpoints and a feedback loop: step 0 gates API choice on the Java baseline, step 1 has a checkpoint ('before writing the pipeline, confirm the chosen terminal returns the requested type ...'), and step 7 is validate→fix→re-scan ('Run the marker scan and the parallel-safety conditions ... fix hits, and re-scan'), closing with concrete review-output requirements. This matches the level-5 anchor (explicit validation steps plus error-recovery loop), not level 4's 'minor validation gaps'.

5 / 5

Progressive Disclosure

SKILL.md is a clean overview with a Reference Bundle table naming all three bundle files and their purposes, each verified to exist (references/hard-stops.md, references/stream-examples.md, references/java-stream-api.md), linked inline exactly where needed in the workflow (java-stream-api.md at step 0, hard-stops.md at step 7). Details (worked examples, compatibility tables, marker scan) are appropriately split into one-level-deep references with no inlined walls of API text — matching the level-5 anchor rather than level 4's 'minor organization gaps'.

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 exemplary: concrete action list, a specific antipattern inventory, explicit 'Use whenever ...' trigger guidance with natural user phrasing and synonyms, and a tightly scoped niche. It reads like the rubric's own good examples, with no fluff, over-claims, or missing trigger clause.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions with comprehensive coverage: 'Review Java stream performance advice', 'clean up mutation and write or refactor Java Stream and Collector code', plus a named antipattern inventory ('materializing just to inspect, sorting before min/max, counting for existence, nested stream collections, unsafe null sorting, multi-line lambdas, and careless findFirst/findAny changes'). It matches the level-5 anchor (multiple specific concrete actions, comprehensive) rather than 4, which reserves 'minor gaps in coverage' — no significant capability area of the domain is missing.

5 / 5

Completeness

Both questions are explicitly answered: the 'what' is stated up front (review performance advice, clean up mutation, write/refactor stream and collector code, avoid listed antipatterns) and the 'when' is an explicit trigger clause — 'Use whenever writing, reviewing, or refactoring Java code that uses Java streams or collectors, such as ... including review prompts asking whether a lookup should use findFirst or findAny.' This mirrors the level-5 good example's 'what + Use when ... such as' pattern; level 4 would require a less explicit or less specific 'when'.

5 / 5

Trigger Term Quality

Natural trigger phrases and their synonyms are covered comprehensively: 'Java streams or collectors', 'stream pipelines, grouping collectors, joining strings, stream first/any element lookup, sorted/limit/distinct stages, primitive stream totals, Optional values inside streams, or parallel streams', plus 'parallelStream', 'forEach/add', and 'findFirst or findAny'. These are exactly the phrases a user would naturally say; not level 4, because no common variation of the domain's vocabulary is missing.

5 / 5

Distinctiveness Conflict Risk

The description carves a clear niche — Java Stream/Collector code specifically — with distinct triggers (grouping collectors, joining, findFirst/findAny lookups, parallel streams) that no generic Java, PDF, or data skill would claim. Overlap with a hypothetical general Java skill is minimal because every trigger is scoped to streams/collectors; level 4's 'minor overlap risk with closely related skills' would apply only if the scope bled into general Java work, which it does not.

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

Table of Contents