Agent Skills Hub

pytorch-lightning

PyTorch Lightning skill for scalable deep learning: automates model training, multi-GPU orchestration, data pipelines, and distributed training strategies like DDP, FSDP, and DeepSpeed.

debug-distributed

Debugging guide for AReaL distributed training issues, including hangs, NCCL errors, OOM, and numerical consistency in FSDP2/TP/CP/EP.

flow-nexus-neural

Train and manage neural networks in distributed E2B sandboxes using the Flow Nexus platform, supporting custom architectures like Transformers, LSTMs, and GANs.

nvidia-resiliency-ext

Provides resiliency, health monitoring, and fault tolerance utilities for NVIDIA GPU-accelerated distributed applications, including process management and API key handling.

building-ai-agent-on-cloudflare

Build stateful AI agents on Cloudflare Workers using the Agents SDK. Features real-time WebSockets, persistent state management, scheduled background tasks, and native tool integration for production-ready deployments.

stable-baselines3

Production-ready reinforcement learning using Stable Baselines3. Train agents, design custom environments, implement training callbacks, and optimize workflows with a scikit-learn-style API.

Swarm Orchestration

Orchestrate multi-agent swarms using agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Ideal for building distributed AI systems and scaling complex development workflows.

multi-agent-patterns

Architect multi-agent systems to overcome context limits, using patterns like supervisor, swarm, and hierarchical models to manage complex workflows.

dispatching-parallel-agents

Parallelize independent debugging or development tasks by delegating to specialized subagents with isolated context.

swarm-advanced

Orchestrate complex multi-agent swarms with topologies like mesh, hierarchical, and star for research, development, and testing workflows.

parallel-agents

Orchestrate complex workflows by coordinating multiple specialized AI agents for multi-perspective code analysis, feature implementation, and system-wide reviews.

p9

P9 Tech Lead mode: Manages P8 agent teams via Task Prompts (six-element) without direct coding. Orchestrates 3+ parallel agents for project management, task decomposition, and architecture.