active-inference-in-c
C++ implementation of Active Inference with belief updating, free energy minimization, and policy selection
C++ implementation of Active Inference with belief updating, free energy minimization, and policy selection
COBOL implementation of Active Inference with belief updating, free energy minimization, and policy selection
Create custom React Native native modules for iOS and Android. Use when integrating native SDKs, optimizing performance-critical code, or accessing platform-specific APIs. Trigger words include "native module", "bridge", "native code", "iOS bridge", "Android bridge", "Turbo Module".
Electron desktop development guide. Use when implementing desktop features, IPC handlers, controllers, preload scripts, window management, menu configuration, or Electron-specific functionality. Triggers on desktop app development, Electron IPC, or desktop local tools implementation.
Implement a Quick Tech Spec for small changes or features. Use when the user provides a quick tech spec and says "implement this quick spec" or "proceed with implementation of [quick tech spec]"
PyTorch implementation of TurboQuant for LLM KV cache compression using two-stage vector quantization (random rotation + Lloyd-Max + QJL residual correction).
Use token-efficient CLI patterns instead of verbose MCP output when direct shell tools are enough. Provides JSON or compact-output conventions for gh, mgrep, psql, and similar tools.
Use when porting OpenGL/DirectX to Metal - translation layer vs native rewrite decisions, migration planning, anti-patterns
Best practices for Docker-based ROS2 development including multi-stage Dockerfiles, docker-compose for multi-container robotic systems, DDS discovery across containers, GPU passthrough for perception, and dev-vs-deploy container patterns. Use this skill when containerizing ROS2 workspaces, setting up docker-compose for robot software stacks, debugging DDS communication between containers, configuring NVIDIA Container Toolkit for GPU workloads, forwarding X11/Wayland for rviz2 and GUI tools, or managing USB device passthrough for cameras and serial devices. Trigger whenever the user mentions Docker with ROS2, docker-compose for robots, Dockerfile for colcon workspaces, container networking for DDS, GPU containers for perception, devcontainer for ROS2, multi-stage builds for ROS2, or deploying ROS2 in containers. Also trigger for CI/CD with Docker-based ROS2 builds, CycloneDDS or FastDDS configuration in containers, shared memory in Docker, or X11 forwarding for rviz2. Covers Humble, Iron, Jazzy, and Rolling di
Modern R development practices emphasizing tidyverse patterns (dplyr 1.1 and later, native pipe, join_by, .by grouping), rlang metaprogramming, performance optimization, and package development. Use when Claude needs to write R code, create R packages, optimize R performance, or provide R programming guidance.
PyTorch深度学习模式与最佳实践,用于构建稳健、高效且可复现的训练流程、模型架构和数据加载。
Ordo JIT compilation and performance optimization guide. Includes Schema-aware JIT, TypedContext derive macro, Cranelift compilation, performance tuning. Use for optimizing rule execution performance, reducing latency, increasing throughput.
Create optimized multi-stage Dockerfiles for any language or framework
Fine-tune Gemma 4 and 3n models with audio, images, and text on Apple Silicon using PyTorch and Metal Performance Shaders.
Guide to develop against TMDL files or TMDL code. Use this skill when asked to change TMDL code or files (*.tmdl). Includes creating measures with DAX, setting descriptions, working with Power Query M code in partitions, creating RLS roles, and exporting semantic models to TMDL format. Use for any direct manipulation of TMDL syntax or Power BI semantic model definition files.
rebrgen のコードジェネレーターに新機能を追加する時の方法と注意点。コードジェネレーターの構造の理解、共通部分と言語固有部分の整理、EBM構造の変化への対応などを扱う。
Use when deploying custom ML models on-device, converting PyTorch models, compressing models, implementing LLM inference, or optimizing CoreML performance. Covers model conversion, compression, stateful models, KV-cache, multi-function models, MLTensor.
Deploy Cohere-powered applications to Vercel, Fly.io, and Cloud Run. Use when deploying Cohere API v2 apps to production, configuring platform-specific secrets, or setting up deployment pipelines. Trigger with phrases like "deploy cohere", "cohere Vercel", "cohere production deploy", "cohere Cloud Run", "cohere Fly.io".
Optimize Anima code generation performance with caching, parallelism, and output tuning. Use when reducing generation latency, optimizing batch component generation, or improving generated code quality for production use. Trigger: "anima performance", "anima slow", "anima optimization", "anima caching".
Functional error handling with Either/Failure. ALWAYS consult when writing repositories, handling exceptions, defining failures, or using Either in any Flutter layer — not just when setting up error handling. (triggers: lib/domain/**, lib/infrastructure/**, Either, fold, Left, Right, Failure, dartz)
Refactor given method `${input:methodName}` to reduce its cognitive complexity to `${input:complexityThreshold}` or below, by extracting helper methods.
Get best practices for C# async programming