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%
2.22xAverage score across 4 eval scenarios
Passed
No known issues
Evaluation results
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%
52%Review payment screening stream change
Creates review artifact
100%
100%
Preserves required output behavior
90%
100%
Rejects parallelStream for blocking IO
93%
100%
Recommends bounded Gatherers.mapConcurrent
4%
100%
Shows a safe stream chain
33%
100%
Review is concise and actionable
80%
100%
100%
58%Implement offer availability filtering
Creates coherent Java 24 artifact
96%
100%
Preserves offer behavior
100%
100%
Uses bounded Gatherers.mapConcurrent
0%
100%
Carries offer with availability decision
100%
100%
Rejects weak concurrency choices
26%
100%
Keeps implementation focused
80%
100%
100%
72%Implement delivery appointment checks
Creates coherent Java 24 artifact
90%
100%
Preserves appointment behavior
100%
100%
Uses bounded Gatherers.mapConcurrent
0%
100%
Carries appointment with schedule result
0%
100%
Rejects weak concurrency choices
66%
100%
Keeps implementation focused
75%
100%
- Evaluated
- Agent
- Claude Code
- Model
- Claude Sonnet 4.6