Skill UI

This skill facilitates structured, bidirectional reading and knowledge synthesis for academic texts, theories, and articles. It forces users to first capture the source material's original intent, before critically mapping its relationships, conflicts, and absorptions against the CrossFrame framework. It ensures structured output with clear source boundaries, making it ideal for deep learning and scholarly work.

This skill simulates Geoffrey Hinton, the Turing Award winner and father of deep learning. It provides expert insights on backpropagation, neural networks, deep belief networks, and capsule networks. Use this when discussing Hinton's contributions or advanced AI concepts.

This skill simulates Ilya Sutskever, co-founder of OpenAI and expert in deep learning. It provides insights on AGI safety, AI consciousness, scaling laws, and the November 2023 OpenAI episode. Ideal for discussions on safe superintelligence and advanced AI research perspectives.

This skill manages the entire lifecycle of long-running deep learning training and inference jobs deployed on remote, ephemeral computing environments (e.g., AutoDL, RunPod, bare SSH, Slurm, K8s). It provides critical capabilities like resilient checkpointing, managing spot instance preemption, debugging resource failures (OOM, NaN), and ensuring safe billing teardown, making it essential for professional ML Ops on rented resources.

This skill transforms the current workspace into a comprehensive, stateful teaching environment. It guides the user through deep, multi-session learning by structuring content into core components: a defined mission, reference materials, curated resources, structured lessons, and continuous learning records. It employs educational best practices (spaced repetition, retrieval practice) to ensure long-term knowledge retention.

Simulates Yann LeCun, Chief AI Scientist at Meta and Turing Award winner. Provides expert insights on Convolutional Neural Networks, AI safety, and deep learning research. Useful for brainstorming technical strategies and understanding AI ethics.

This technical skill covers Yann LeCun's methodologies including CNNs, LeNet, backpropagation, JEPA, AMI, Self-Supervised Learning, and Energy-Based Models. It provides complete PyTorch code implementation. Use this for specialized AI tasks requiring deep learning expertise.