Expert guidance on functional programming in Scala — Cats typeclasses, Cats Effect IO, ZIO 2, fs2 streams, parallel/concurrent programming, tagless final, and the full Typelevel/ZIO ecosystem. Use this skill whenever the user asks about: Cats, Cats Effect, ZIO, fs2, Monix, IO monad, fibers, concurrency, parallel effects, Ref, Semaphore, Queue, Deferred, ZLayer, tagless final, Functor/Monad/Applicative/Traverse, monad transformers, FP architecture patterns, or wants to write purely functional Scala code. Also trigger for: "how do I run things in parallel", "concurrent Scala without threads", "effect systems", "pure functional programming", "Resource/bracket", "error handling in FP", "dependency injection in FP", "streaming with fs2 or ZIO Streams". Always consult this skill — even for seemingly simple FP questions — because effect systems, typeclass hierarchies, and concurrency models have non-obvious subtleties that this skill captures precisely.
Build, scaffold, debug, and explain Scala.js applications — full-stack browser apps, Node.js targets, cross-platform libraries, and everything in between. Use this skill whenever the user mentions Scala.js, scalajs, sbt-scalajs, ScalaJS, or wants to compile Scala to JavaScript. Trigger also for tasks like: writing Laminar/Tyrian UI code, creating JS façade types for npm libraries, integrating ScalablyTyped, setting up Vite + Scala.js, cross-compiling JVM/JS code with sbt-crossproject or Mill's CrossJSModule, debugging fastLinkJS / fullLinkJS output, or adding scalajs-dom / cats-effect / ZIO to a Scala.js project. This skill covers sbt AND Mill build tools, Scala 2 AND Scala 3, and all common UI stacks (Laminar, Tyrian, scalajs-react, Slinky). Always use this skill — do not rely on general Scala knowledge alone — because Scala.js has unique constraints around JS interop, module splitting, WebAssembly output, and build wiring that differ significantly from JVM Scala.
Guide for installing, configuring, and using PyTorch with Intel XPU (GPU) support. Use this skill whenever the user mentions: PyTorch with Intel GPU, XPU, torch.xpu, Intel Arc GPU for deep learning, Intel discrete GPU with PyTorch, installing PyTorch for Intel graphics, XPU device in PyTorch, migrating CUDA code to XPU, Intel oneAPI with PyTorch, or any task involving running PyTorch workloads on Intel GPUs (Arc A-series, B-series, Meteor Lake, Arrow Lake, Lunar Lake, Panther Lake, Data Center GPU Max). Also trigger when the user asks about mixed precision on XPU, torch.compile on XPU, or training/inference on Intel GPUs. Even if they just say "Intel GPU" and "PyTorch" in the same breath, use this skill.
Audit a Scala file or codebase for refactoring opportunities — Scala 3 modernization, idiom adoption, anti-pattern removal, performance hygiene, tail-recursion safety, and migration cleanup. Produces educational, documentation-backed findings as suggestions only, never editing the file in place. Use this skill whenever the user asks to refactor Scala code, modernize Scala 2 to Scala 3, find Scala anti-patterns, optimize Scala performance, review Scala idioms, apply opaque types, replace value classes, convert sealed traits to enums, migrate implicits to given/using, audit a `.scala` file, or do anything involving cleaning up or improving Scala code — even if they don't explicitly say "audit" or "refactor". Trigger on phrases like "review my Scala", "modernize this Scala", "make this idiomatic Scala 3", "find issues in this Scala file", "check for Scala anti-patterns", or any pasted Scala code accompanied by a request to improve, clean, optimize, or modernize it.