run_models

Official

Orchestrate model workflows end-to-end.

AuthorCUHK-AIM-Group
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill provides a centralized orchestration layer to coordinate NeuroClaw model execution by routing high-level run requests to the appropriate modality-specific skills and model docs, ensuring safe, auditable, and reproducible runs.

Core Features & Use Cases

  • Centralized model routing: selects BrainGNN, FM-APP, NeuroStorm, GLM, ICA, DictLearning, SVM, SpaceNet, K-means, Hierarchical, Filtering, or Detrending workflows and directs preprocessing to the corresponding skill stacks.
  • Execution planning with guardrails: generates a numbered plan, requires user confirmation, and delegates preprocessing to modality skills before execution via claw-shell.
  • Experiment logging and results organization: maintains traceable run artifacts under run_models_output and supports drift monitoring and reproducibility checks.

Quick Start

Request a numbered run plan to select a model and delegate modality preprocessing via fmri-skill and smri-skill.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: run_models
Download link: https://github.com/CUHK-AIM-Group/NeuroClaw/archive/main.zip#run-models

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.