Teaches AI agents to write idiomatic Kotlin (data classes, val, scope fns, Kotest) AND to make the right stack choices on JVM: Kotlin 2.3 + JDK 21 + Gradle Kotlin DSL, Ktor for HTTP, kotlinx-coroutines, DJL for ML inference, JavaCV for vision, Koog for AI agent orchestration.
95
95%
Does it follow best practices?
Impact
95%
1.23xAverage score across 10 eval scenarios
Passed
No known issues
data classdata classclass with manually-written equals, hashCode, and toString is a data class that hasn't realised it yetequals / hashCode / toStringtoString — in which case override only toString, not all threecopy() Is the Mutation Patterndata class instance via instance.copy(field = newValue) — preserves all other fields, gives you a new immutable instanceval (the previous rule) — together they make immutable update painlessval (id, name) = user) and componentN() come for free; lean on them when iterating collections of value objectsdata class is the exception — its generated constructor / copy() / componentN() signatures break binary compatibility when properties change, so prefer a regular class there. Use the kotlin-api-review skill before converting library surface