Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.
Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.
Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging norm stats and GPU memory issues.
PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.
Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.
Extend LLM and embedding adapters in unstract/sdk1. Use when adding new adapters (LLM or embedding), removing adapters, adding/removing models to existing adapters, or editing adapter configurations. Supports OpenAI-compatible providers, cloud providers (AWS Bedrock, VertexAI, Azure), and self-hosted models (Ollama).
Performance-focused guidelines for writing React code that consumes Karton state. Use when creating or reviewing components that use useKartonState, useKartonProcedure, useComparingSelector, or any Karton React hooks. Covers selector patterns, re-render prevention, structural sharing, and edge cases.
Validate that reasoning parameters are correctly serialized and sent to provider APIs. Use when the user asks to test reasoning serialization, run reasoning tests, verify reasoning config fields, or check that ReasoningConfig maps correctly to provider-specific JSON (OpenRouter, Anthropic, GitHub Copilot, Codex).
Execute structured task plans with status tracking. Use when the user provides a plan file path in the format `plans/{current-date}-{task-name}-{version}.md` or explicitly asks you to execute a plan file.
Create a new API endpoint with Command, Handler, Validator, and Endpoint following FSH vertical slice architecture. Use when adding any new feature, API endpoint, or business operation.
Mediator library patterns and interfaces for FSH. This project uses the Mediator source generator, NOT MediatR. Reference when implementing commands, queries, and handlers.
Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, macOS-specific APIs, and iOS 26+ Liquid Glass adoption. Use when building new SwiftUI features, refactoring existing views, reviewing code quality, or adopting modern SwiftUI patterns.
Generates beautiful, consistent Preline Theme CSS files. Agent interprets user request, runs build script, delivers complete CSS.
Develops production-ready Triton kernels for Liger Kernel. Creates new kernels from PyTorch operations (local files, URLs, code snippets, or natural language) with ops, module wrappers, functional APIs, unit tests, benchmarks, and plots. Also modifies existing Liger kernels. Use when adding a new Triton kernel, converting a PyTorch operation to Triton, or updating an existing Liger kernel.
Optimizes the performance of existing Liger Kernel Triton kernels. Profiles kernels, diagnoses bottlenecks (memory-bound vs compute-bound), generates multiple optimization variants with benchmarking, and applies the best variant while maintaining correctness. Supports GPU architecture-specific optimization (Ampere, Hopper, Blackwell). Use when a user asks to optimize, speed up, tune, profile, or reduce memory of an existing Liger kernel.
Correctness invariants and architectural guidance for the adapter layer, coordinator, pgwire, peek paths, and timestamp oracle. Trigger when the user works on or asks questions about these subsystems — including "how does the coordinator work", "what are read holds", "explain the peek path", "how does timestamp selection work", "why does this query block". Also trigger when editing files in src/adapter/, src/pgwire/, or src/timestamp-oracle/.
Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling
Guide for building features, pages, tables, forms, themes, and navigation in this Next.js 16 shadcn dashboard template. Use this skill whenever the user wants to add a new page, create a feature module, build a data table, add a form, configure navigation items, add a theme, set up RBAC access control, or work with the dashboard's patterns and conventions. Also triggers when adding routes under /dashboard, working with Clerk auth/orgs/billing, creating mock APIs, or modifying the sidebar. Even if the user doesn't mention "dashboard" explicitly — if they're adding UI, pages, or features to this project, use this skill.
