Skills
.Work. You
Rest

run-experiment

Community

Deploy and run ML experiments.

Software Engineering#automation#mlops#remote execution#gpu management#experiment deployment#training jobs
AuthorMACJONSW
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill streamlines the deployment and execution of machine learning experiments, whether on local hardware or remote GPU servers, simplifying the MLOps workflow.

Core Features & Use Cases

  • Environment Detection: Automatically identifies the target environment (local GPU or remote server) by reading CLAUDE.md.
  • Pre-flight Checks: Verifies GPU availability before allocating resources.
  • Code Synchronization: Efficiently syncs only necessary code files to remote servers.
  • Deployment: Launches experiments in isolated screen sessions (remote) or background processes (local) with GPU binding.
  • Verification & Notification: Confirms experiment launch and optionally sends notifications.
  • Use Case: Launch a PyTorch training job on a remote A100 GPU server, ensuring sufficient memory is available and the code is up-to-date, then receive a confirmation once it's running.

Quick Start

Use the run-experiment skill to deploy the attached script 'train.py' with arguments '--epochs 10 --lr 0.001' to the remote server defined in CLAUDE.md.

Dependency Matrix

Required Modules

None required

Components

references

💻 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-experiment
Download link: https://github.com/MACJONSW/AutoResearchIDEA/archive/main.zip#run-experiment

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 223,000+ vetted skills library on demand.