AI-Toolkit

C++ Reinforcement Learning best practices using libtorch (PyTorch C++ frontend) and modern C++17/20. Use when: - Implementing RL algorithms in C++ for performance-critical applications - Building production RL systems with libtorch - Creating replay buffers and experience storage - Optimizing RL training with GPU acceleration - Deploying RL models with ONNX Runtime

Comprehensive guide for Deep Learning with Keras 3 (Multi-Backend: JAX, TensorFlow, PyTorch). Use when building neural networks, CNNs for computer vision, RNNs/Transformers for NLP, time series forecasting, or generative models (VAEs, GANs). Covers model building (Sequential/Functional/Subclassing APIs), custom training loops, data augmentation, transfer learning, and production best practices.

Set up, install, configure, and deploy OpenClaw (formerly ClawdBot/MoltBot) — a personal AI assistant that runs on your own devices and connects to messaging channels. Use when users ask to "set up OpenClaw," "install ClawdBot," "install MoltBot," "deploy a personal AI assistant," "configure OpenClaw on Mac," "deploy OpenClaw to VPS," "set up OpenClaw on Hostinger," "connect OpenClaw to Telegram," "configure iMessage with OpenClaw," or any variation involving OpenClaw installation, gateway configuration, channel setup, Anthropic auth, or security hardening. Also triggers on "openclaw onboard," "openclaw doctor," "openclaw security audit," troubleshooting OpenClaw deployments, OpenClaw security, OpenClaw cost control, or ClawHub skills safety.

Optimize prompts for Claude 4.x models using Anthropic's official best practices. Use when users want to improve, refine, or create effective prompts for Claude. Triggers include requests to optimize prompts, make prompts more effective, fix underperforming prompts, create system prompts, improve instruction following, reduce verbosity, control output formatting, or enhance agentic/tool-use behaviors. Also use when users report Claude is being too verbose, not following instructions, not using tools properly, or producing generic outputs.

Reinforcement Learning best practices for Python using modern libraries (Stable-Baselines3, RLlib, Gymnasium). Use when: - Implementing RL algorithms (PPO, SAC, DQN, TD3, A2C) - Creating custom Gymnasium environments - Training, debugging, or evaluating RL agents - Setting up hyperparameter tuning for RL - Deploying RL models to production

Build applications using the x402 protocol — Coinbase's open standard for HTTP-native stablecoin payments using the HTTP 402 status code. Use this skill when: - Creating APIs that require USDC payments per request (seller/server side) - Building clients or AI agents that pay for x402-protected resources (buyer/client side) - Implementing MCP servers with paid tools for Claude Desktop - Adding payment middleware to Express, Hono, or Next.js applications - Working with Base (EVM) or Solana (SVM) payment flows - Building machine-to-machine or agent-to-agent payment systems - Integrating micropayments, pay-per-use billing, or paid API access Triggers: x402, HTTP 402, payment required, USDC payments, micropayments, pay-per-use API, agentic payments, stablecoin payments, paid API endpoint, paywall middleware