Skills for contributing TO the SKaiNET framework — Kotlin idioms enforced by the project, the multi-module Gradle layout with version catalog, KMP source-set rules, the Java-interop facade convention, and the common in-repo test strategy. Use when editing files inside the SKaiNET repo. Consumer-side skills (using SKaiNET in your own app) live in the sibling skainet-consumer-skills plugin.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Use ONLY when editing build scripts INSIDE the SKaiNET repository — `SKaiNET/build.gradle.kts`, `SKaiNET/settings.gradle.kts`, `SKaiNET/gradle/libs.versions.toml`, anything under `SKaiNET/build-logic/`, or adding/renaming/removing a `skainet-*` module within SKaiNET. Enforces version-catalog-only references, convention-plugin reuse, BOM registration, binary-compatibility-validator, vanniktech maven-publish, kover. Do NOT fire on a CONSUMER project's build script that just depends on `sk.ainet:skainet-bom` — that's the `skainet-consumer-setup` skill.
Use ONLY when configuring KMP targets, source-set hierarchies, or `expect`/`actual` placement in a module INSIDE the SKaiNET repository. Trigger tokens include `kotlin { ... }`, `iosArm64()`, `commonMain`, `jvmMain`, `expect fun`, `actual fun`, `androidNative`, `wasmJs`, source-set dependency edits in `SKaiNET/skainet-*/build.gradle.kts`. Do NOT fire on KMP setup in a CONSUMER project (an app that depends on SKaiNET) — those concerns are simpler and live in `skainet-consumer-setup`.
Use ONLY when editing Kotlin (`.kt`) source files INSIDE the SKaiNET repository (i.e. you're contributing to SKaiNET itself, not consuming it as a library). Enforces project idioms: explicit-API mode, package layout under `sk.ainet.*`, sealed hierarchies, `value class` for type-safe wrappers, no Java-style getters in Kotlin code. Do NOT fire when the user is writing application code that depends on SKaiNET as a library — that's the consumer plugin's territory. Does not fire on DSL invocation sites, build files, or test files within SKaiNET either (those are covered by other contributor skills).
Use ONLY when designing or editing the Java-facing facade INSIDE the SKaiNET repository — files under `SKaiNET/skainet-*/src/jvmMain/kotlin/sk/ainet/java/`. Trigger tokens include `@file:JvmName`, `@JvmStatic`, `@JvmOverloads`, `package sk.ainet.java`, `object SKaiNET`, `object TensorJavaOps`. Encodes the contributor-side rules for the convention. Do NOT fire when the user is CALLING the Java facade from a Java app — that's the consumer-side `skainet-java-consumer` skill.
Use ONLY when writing or editing unit tests INSIDE the SKaiNET repository — tests under `SKaiNET/skainet-*/src/commonTest/`, `*/jvmTest/`, or `SKaiNET/skainet-test/skainet-test-java/`. Enforces the in-repo test policy: Kotest spec runner on JVM, `kotlin.test` in commonTest, `TensorAssertions.assertTensorClose` with explicit `ToleranceConfig.{STRICT/STANDARD/RELAXED/GRADIENT}`, Java JUnit 5 in `skainet-test-java`. Trigger tokens include `assertTensorClose`, `assertArrayClose`, `ToleranceConfig`, `GroundTruthTensor`. Do NOT fire on a CONSUMER project writing its own tests against SKaiNET as a dependency — those tests don't have access to `skainet-test-groundtruth` and can use any framework they like.
Official Claude Code plugin marketplace for working with SKaiNET — the Kotlin Multiplatform on-device ML/AI framework. Maintained under the SKaiNET-developers organization.
The marketplace hosts two side-by-side skill bundles. They're designed to be installed together; per-skill descriptions disambiguate via path heuristics so exactly one fires per prompt.
skainet-contributor-skillsFor developers contributing to SKaiNET itself (editing files inside the SKaiNET repo).
| Skill | What it covers |
|---|---|
kotlin | Explicit-API mode, package layout, sealed hierarchies, value class. |
gradle-multimodule | Version-catalog discipline, convention plugins, BOM membership, binary-compatibility-validator. |
kmp | Full target matrix (JVM/Android/iOS/macOS/Linux/androidNative/JS/WASM), source-set hierarchy, KSP wiring. |
skainet-java-interop | The @file:JvmName / object + @JvmStatic facade convention under */jvmMain/kotlin/sk/ainet/java/. |
skainet-testing | Kotest in jvmTest, kotlin.test in commonTest, TensorAssertions + ToleranceConfig, JUnit 5 mirror in skainet-test-java. |
skainet-consumer-skillsFor developers using SKaiNET as a library in their own Kotlin / Java / Android / KMP app.
| Skill | What it covers |
|---|---|
skainet-consumer-setup | BOM (sk.ainet:skainet-bom), library coordinates (sk.ainet.core:skainet-*), artifact picker. |
skainet-data-dsl | tensor { shape(…) { … } }, transform pipelines, slice views. |
skainet-nn-dsl | sequential<T, V> { } and dag { } neural-network builders. |
skainet-model-loading | GGUF, ONNX, SafeTensors, JSON loaders. |
skainet-inference | ExecutionContext, model.forward(x, ctx), batching, threading, TurboQuant KV-cache. |
skainet-android-integration | assets/ → cacheDir, viewModelScope + Dispatchers.Default, ABI filters, onTrimMemory. |
skainet-java-consumer | Maven dependencies, SKaiNET.context(), TensorJavaOps.*, StableHloConverterFactory, TokenizerFactory. |
In any Claude Code session:
/plugin marketplace add SKaiNET-developers/skainet-coding-skills
/plugin install skainet-contributor-skills
/plugin install skainet-consumer-skills
Or clone locally and point at the working tree:
git clone https://github.com/SKaiNET-developers/skainet-coding-skills.git
# then in Claude Code:
/plugin marketplace add /path/to/skainet-coding-skills
.
├── .claude-plugin/
│ └── marketplace.json # lists both plugins
├── skainet-contributor-skills/
│ ├── .claude-plugin/plugin.json
│ └── skills/
│ ├── INDEX.md
│ ├── kotlin/
│ ├── gradle-multimodule/
│ ├── kmp/
│ ├── skainet-java-interop/
│ └── skainet-testing/
└── skainet-consumer-skills/
├── .claude-plugin/plugin.json
└── skills/
├── INDEX.md
├── skainet-consumer-setup/
├── skainet-data-dsl/
├── skainet-nn-dsl/
├── skainet-model-loading/
├── skainet-inference/
├── skainet-android-integration/
└── skainet-java-consumer/
Each skill directory contains a SKILL.md (frontmatter + workflow + canonical examples), a references/ folder with lookup tables, and an evals/evals.json with first-pass scenario tests.
// from: <path>:<line-range> so the citation check (CI on every PR) verifies it stays in sync with SKaiNET source as the framework evolves.skainet-data-dsl, skainet-nn-dsl) lead with a cheatsheet instead.See CONTRIBUTING.md for skill authoring, citation rules, and the eval scenario format.
npx claudepluginhub skainet-developers/skainet-coding-skills --plugin skainet-contributor-skillsSkills for using SKaiNET as a library in your own Kotlin Multiplatform / JVM / Android / Java app. Covers BOM-based dependency setup, the data and neural-network DSLs, model loading (GGUF / ONNX / SafeTensors), running inference, Android integration, and pure-Java consumers calling the sk.ainet.java facade. Contributor-side skills (working inside the SKaiNET repo itself) live in the sibling skainet-contributor-skills plugin.
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Develop, test, build, and deploy Godot 4.x games with Claude Code. Includes GdUnit4 testing, web/desktop exports, CI/CD pipelines, and deployment to Vercel/GitHub Pages/itch.io.
Unity Development Toolkit - Expert agents for scripting/refactoring/optimization, script templates, and Agent Skills for Unity C# development
Comprehensive .NET development skills for modern C#, ASP.NET, MAUI, Blazor, Aspire, EF Core, Native AOT, testing, security, performance optimization, CI/CD, and cloud-native applications
Modern R development skills for Claude Code - tidyverse patterns, rlang metaprogramming, Bayesian inference, performance optimization, and more
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.