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
100%
Does it follow best practices?
Impact
100%
2.17xAverage score across 4 eval scenarios
Passed
No known issues
Evaluation results
100%
61%Implement delivery appointment checks
Creates coherent Java 24 artifact
90%
100%
Preserves appointment behavior
95%
100%
Uses bounded Gatherers.mapConcurrent
0%
100%
Carries appointment with schedule result
37%
100%
Rejects weak concurrency choices
83%
100%
Keeps implementation focused
100%
100%
100%
35%Implement invoice bounds and temperature windows
Creates coherent Java 17 artifact
100%
100%
Uses teeing for invoice bounds
0%
100%
Handles empty invoice bounds
100%
100%
Uses takeWhile for before-overheat prefix
100%
100%
Uses dropWhile for after-safe-run remainder
100%
100%
Keeps implementation focused
100%
100%
100%
47%Review payment screening stream change
Creates review artifact
100%
100%
Preserves required output behavior
93%
100%
Rejects parallelStream for blocking IO
96%
100%
Recommends bounded Gatherers.mapConcurrent
0%
100%
Shows a safe stream chain
73%
100%
Review is concise and actionable
73%
100%
100%
73%Implement offer availability filtering
Creates coherent Java 24 artifact
88%
100%
Preserves offer behavior
90%
100%
Uses bounded Gatherers.mapConcurrent
0%
100%
Carries offer with availability decision
20%
100%
Rejects weak concurrency choices
40%
100%
Keeps implementation focused
72%
100%
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6