npx agentspec-cli install 939e83a9-971f-45d7-a601-0f3fbd54f157 --framework ClaudeCode→ .claude/skills/mhc/SKILL.md
# mHC Skill
Manifold-Constrained Hyper-Connections (mHC) uses Doubly Stochastic Matrices to improve Deep Learning stability.
## Contents
- [Examples](examples.md)
- Full JAX implementation of `sinkhorn_knopp` and `mhc_layer_forward`.
- [Deep Theory](reference.md)
- Motivation, stability proofs, and scalability arguments.
## Usage
Use this skill when implementing Deep Transformers (1000+ layers) where standard residual connections fail (Gradient Vanishing, Representation Collapse).
```python
# Quick Ref: Sinkhorn-Knopp (See examples.md for full context)
def sinkhorn_knopp(log_matrix, n_iters=20):
M = jnp.exp(log_matrix)
def body(i, m):
m /= m.sum(axis=1, keepdims=True)
m /= m.sum(axis=0, keepdims=True)
return m
return jax.lax.fori_loop(0, n_iters, body, M)
```
Built on the Agent Skills standard
HyperNOs: Automated and Parallel Neural Operators Research
HyperNOs is a Python framework for automated, distributed, and parallel hyperparameter optimization (HPO) of Neural Operators. It leverages **PyTorch** for model development and **Ray Tune** for scalable hyperparameter search across various physics-informed benchmarks.
by AgentHub Crawler
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. **Primary Goal for this Project:** I am learning Red Hat OpenShift AI for model training. This project implements **wilderness survival and practical skills Q&A fine-tuning** as a compelling demonstration of specialized AI capabilities. The goal is to transform a generic language model into a wilderness survival expert that can provide comprehensive, detailed guidance on essential survival and
by AgentHub Crawler
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
by AgentHub Crawler
Sign in to leave a comment.