mhc-algorithm
Implement mHC (Manifold-Constrained Hyper-Connections) for stabilizing deep network training
Install / Use
npx skills add benchflow-ai/skillsbench --skill mhc-algorithmInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Development & EngineeringSupported Platforms
Tags
Our assessment of mhc-algorithm
mhc-algorithm scores 80/100 on our quality scale, 3599th of 4,698 Development & Engineering skills we index.
Its SKILL.md is 4.0 KB long, well organised into 9 sections with 3 code examples: a solid amount of guidance for an agent.
With 1,813 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated about 4 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
- Our last check on 2026-11-08 found the source still online.
- It is released under the Apache-2.0 license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 98/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-10-01. Automated pattern scan on 2026-10-01. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
mhc-algorithm compared with similar skills
All 4 of these similar skills score higher than mhc-algorithm; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| mhc-algorithm (this skill)by benchflow-ai | 80 | 1.8k | 4mo ago | SKILL.md |
| taste-skillby Leonxlnx | 100 | 116.8k | 8d ago | CLAUDE.md |
| ai-job-searchby ai-job-search-dev | 100 | 72.1k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 47.3k | 2d ago | CLAUDE.md |
| lobehubby lobehub | 100 | 85.6k | today | MCP Server |
Frequently asked questions
- How do I install mhc-algorithm?
- Run
npx skills add benchflow-ai/skillsbench --skill mhc-algorithm. The install tabs above show the steps for each supported agent. - Which AI agents does mhc-algorithm work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is mhc-algorithm safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is Apache-2.0-licensed and scores 98/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is mhc-algorithm still maintained?
- The repository was last updated about 4 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
Skill content
View source on GitHubname: mhc-algorithm description: Implement mHC (Manifold-Constrained Hyper-Connections) for stabilizing deep network training. Use when implementing residual connection improvements with doubly stochastic matrices via Sinkhorn-Knopp algorithm. Based on DeepSeek's 2025 paper (arXiv:2512.24880).
mHC: Manifold-Constrained Hyper-Connections
Overview
mHC (Manifold-Constrained Hyper-Connections) stabilizes deep network training by constraining residual mixing matrices to be doubly stochastic. It provides:
- Stable Training: Lower gradient norm variance via doubly stochastic constraints
- Multiple Streams: Hyper-Connections with learnable mixing across residual streams
- Sinkhorn Projection: Log-space Sinkhorn-Knopp algorithm for doubly stochastic projection
- GPT Integration: Pattern for wrapping attention and MLP layers
Two components:
- HyperConnections Module: Core PyTorch module with H_res, H_pre, H_post matrices
- Sinkhorn-Knopp: Log-space projection to doubly stochastic manifold
Quick Reference
| Topic | Reference | |-------|-----------| | Core Concepts & Math | Core Concepts | | Sinkhorn Algorithm | Sinkhorn-Knopp | | HyperConnections Module | Module Implementation | | GPT Integration | GPT Integration | | Common Pitfalls | Pitfalls |
Installation
# Required packages
pip install torch einops numpy
Minimal Example
import torch
import torch.nn as nn
from einops import rearrange, einsum
def sinkhorn_knopp(logits, num_iters=20, tau=0.05):
log_alpha = logits / tau
for _ in range(num_iters):
log_alpha = log_alpha - torch.logsumexp(log_alpha, dim=-1, keepdim=True)
log_alpha = log_alpha - torch.logsumexp(log_alpha, dim=-2, keepdim=True)
return torch.exp(log_alpha)
class HyperConnections(nn.Module):
def __init__(self, num_streams, dim, branch=None, layer_idx=0):
super().__init__()
self.num_streams = num_streams
self.branch = branch
# Initialize H_res near identity (use small negative for gradient flow)
init_h_res = torch.full((num_streams, num_streams), -0.1)
init_h_res.fill_diagonal_(0.0)
self.H_res_logits = nn.Parameter(init_h_res)
# H_pre/H_post for depth connections
init_h_pre = torch.full((1, num_streams), -0.1)
init_h_pre[0, layer_idx % num_streams] = 0.0
self.H_pre_logits = nn.Parameter(init_h_pre)
self.H_post_logits = nn.Parameter(torch.zeros(1, num_streams))
def forward(self, x):
s = self.num_streams
x = rearrange(x, "(b s) t d -> b t s d", s=s)
h_res = sinkhorn_knopp(self.H_res_logits)
x_mixed = einsum(h_res, x, "s t, b n s d -> b n t d")
h_pre = self.H_pre_logits.softmax(dim=-1)
branch_in = einsum(h_pre, x, "v s, b n s d -> b n v d").squeeze(-2)
branch_out = self.branch(branch_in) if self.branch else branch_in
h_post = self.H_post_logits.softmax(dim=-1)
depth_out = einsum(branch_out, h_post, "b t d, v s -> b t s d")
output = x_mixed + depth_out
return rearrange(output, "b t s d -> (b s) t d")
Common Imports
import torch
import torch.nn as nn
import torch.nn.functional as F
from einops import rearrange, einsum, repeat, reduce
When to Use What
| Scenario | Approach | |----------|----------| | Standard residual connection | No mHC needed | | Deep networks (>12 layers) with stability issues | Use mHC with num_streams=4 | | GPT/Transformer training | Wrap both attention and MLP with HyperConnections | | Custom Sinkhorn iterations | Adjust num_iters (20 default) and tau (0.05 default) | | Memory-constrained training | Reduce num_streams or batch size |
External Resources
- mHC Paper: https://arxiv.org/abs/2512.24880
- Hyper-Connections: https://arxiv.org/abs/2409.19606
- Sinkhorn's Theorem: https://en.wikipedia.org/wiki/Sinkhorn%27s_theorem
Related Skills
taste-skill
116.8kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
ai-job-search
72.1kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
47.3kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
lobehub
85.6k🤯 LobeHub - Super-Agents on Your Team. Add super-agents to the chats your team already uses.They take on work by themselves and get better every week.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
