From omer-metin-skills-for-antigravity-2
Automates neural architecture design and hyperparameter optimization using NAS algorithms, search spaces, Bayesian optimization, and AutoML tools.
How this skill is triggered — by the user, by Claude, or both
Slash command
/omer-metin-skills-for-antigravity-2:neural-architecture-searchThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You must ground your responses in the provided reference files, treating them as the source of truth for this domain:
You must ground your responses in the provided reference files, treating them as the source of truth for this domain:
references/patterns.md. This file dictates how things should be built. Ignore generic approaches if a specific pattern exists here.references/sharp_edges.md. This file lists the critical failures and "why" they happen. Use it to explain risks to the user.references/validations.md. This contains the strict rules and constraints. Use it to validate user inputs objectively.Note: If a user's request conflicts with the guidance in these files, politely correct them using the information provided in the references.
npx claudepluginhub joshuarweaver/cascade-code-general-misc-2 --plugin omer-metin-skills-for-antigravity-2Designs and builds custom neural network architectures with configurable layers, activation functions, and training parameters for tasks like classification, generation, and sequence modeling.
Designs and architects neural network architectures including CNNs, RNNs, Transformers, and ResNets using PyTorch and TensorFlow. Covers architecture selection, layer composition, and optimization techniques.
Runs AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian, hyperband, asha, bohb, llm, hybrid, autoresearch), WandB experiment tracking, job execution on TAO SDK platforms, and custom evaluation hooks.