deepmd-router

Route DeePMD-kit requests to training, inference, or MD sub-skills.

181|20|Updated Apr 29, 2026
One-click install
npx skills add https://github.com/Hello-QM/catgo-LRG --skill deepmd-router
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deepmd-router
Source: https://github.com/Hello-QM/catgo-LRG/tree/main/server/catgo/workflow/skills/deepmd
Command: npx skills add https://github.com/Hello-QM/catgo-LRG --skill deepmd-router

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Route DeePMD-kit requests to the appropriate sub-skills, enabling seamless end-to-end workflows across training, inference, and MD tasks.

Core Features & Use Cases

  • Centralized routing to train/SKILL.md, inference/SKILL.md, or ../lammps/deepmd/SKILL.md based on user intent.
  • Enforces a consistent workflow policy, common decision guide, and easy extension to new sub-skills.
  • Useful in pipelines that combine DL-based potentials with HPC scheduling and post-processing.

Quick Start

Route a training request to train/SKILL.md, an inference request to inference/SKILL.md, or a MD workflow to ../lammps/deepmd/SKILL.md.

Frequently Asked Questions about deepmd-router

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I route DeePMD-kit requests for training versus inference?

DeePMD-kit requests are routed to specific sub-skills based on user intent: training tasks go to the train skill, while inference tasks are directed to the inference skill to ensure proper execution.

Can I execute molecular dynamics workflows using DeePMD-kit and LAMMPS?

Yes, molecular dynamics workflows are routed to the LAMMPS DeePMD sub-skill, enabling seamless execution of MD tasks using deep learning potentials within the LAMMPS environment.

What is centralized routing for DeePMD-kit end-to-end workflows?

Centralized routing directs DeePMD-kit tasks to appropriate sub-skills for training, inference, or MD execution, enforcing a consistent workflow policy and common decision guide across all operations.

Do I need DeePMD-kit installed to use this workflow routing skill?

Yes, this routing skill assumes DeePMD-kit is already installed in your environment, as it acts as a centralized router directing tasks to specific sub-skills without handling installation.

Does this routing approach support pipelines combining HPC scheduling and post-processing?

Yes, this routing skill is useful in pipelines that combine deep learning based potentials with HPC scheduling and post-processing, maintaining a consistent workflow policy across combined tasks.

When should I not use this centralized DeePMD-kit routing skill?

You should not use this routing skill if DeePMD-kit is not installed, or if your workflow falls outside of training, inference, and MD execution, as it strictly enforces routing to these specific sub-skills.