← Back to Skills Marketplace
76
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install mhc-layer-impl-mhc-algorithm
Description
Implement mHC (Manifold-Constrained Hyper-Connections) for stabilizing deep network training. Use when implementing residual connection improvements with dou...
Usage Guidance
This skill appears internally consistent and focused on implementing mHC in PyTorch. Before using: (1) Review the code snippets and references to ensure they fit your model and framework versions; (2) install PyTorch via the official channel appropriate for your OS/GPU (avoid arbitrary wheel URLs); (3) run the examples in an isolated environment (virtualenv/container) because mHC multiplies memory usage by num_streams; (4) confirm the referenced paper(s) if you need research provenance. If you need broader audits (license, benchmark results, or GPU/CUDA compatibility), request the author's complete implementation or test on a small toy model first.
Capability Analysis
Type: OpenClaw Skill
Name: mhc-layer-impl-mhc-algorithm
Version: 0.1.0
The skill bundle provides a legitimate implementation of the Manifold-Constrained Hyper-Connections (mHC) algorithm for PyTorch, based on DeepSeek research. The code in SKILL.md and the reference files (module-implementation.md, sinkhorn-knopp.md) focuses entirely on mathematical operations and neural network architecture, using standard libraries like torch and einops. There are no indicators of data exfiltration, malicious execution, or prompt injection.
Capability Assessment
Purpose & Capability
The name/description (mHC for stabilizing deep nets) aligns with the contents: PyTorch code snippets, Sinkhorn projection, and GPT integration patterns. The only external dependency suggested (torch, einops, numpy) is appropriate for the stated goal.
Instruction Scope
SKILL.md contains concrete implementation guidance, example code, and algorithm notes. Instructions are confined to model-code concerns (tensor shapes, Sinkhorn iterations, wrapping layers) and do not instruct reading arbitrary files, accessing environment variables, or contacting external endpoints beyond citing arXiv links.
Install Mechanism
No install spec is embedded; the doc recommends 'pip install torch einops numpy'. This is expected for a PyTorch implementation but be aware 'pip install torch' can be large and platform-specific (CUDA variants). There are no downloads from untrusted URLs or archive/extract steps.
Credentials
The skill requests no environment variables, credentials, or config paths. All required resources are typical Python packages needed to run the examples.
Persistence & Privilege
The skill is instruction-only, does not request 'always: true', and does not instruct changing agent-wide configuration or storing credentials. It does not grant persistent or elevated privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install mhc-layer-impl-mhc-algorithm - After installation, invoke the skill by name or use
/mhc-layer-impl-mhc-algorithm - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
Bulk publish from all-task-skills-dedup
Metadata
Frequently Asked Questions
What is mhc-algorithm?
Implement mHC (Manifold-Constrained Hyper-Connections) for stabilizing deep network training. Use when implementing residual connection improvements with dou... It is an AI Agent Skill for Claude Code / OpenClaw, with 76 downloads so far.
How do I install mhc-algorithm?
Run "/install mhc-layer-impl-mhc-algorithm" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is mhc-algorithm free?
Yes, mhc-algorithm is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does mhc-algorithm support?
mhc-algorithm is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created mhc-algorithm?
It is built and maintained by lnj22 (@lnj22); the current version is v0.1.0.
More Skills