skills.rest
loujc
loujcCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

monitor-experiment

Monitor SSH sessions and collect experiment outputs and metrics.

Updated Mar 17, 2026
Search Tags:#automation#ssh#experiments#monitor#results#wandb
One-click install
npx skills add https://github.com/loujc/Auto-claude-code-research-in-sleep-manual --skill monitor-experiment-loujc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: monitor-experiment
Source: https://github.com/loujc/Auto-claude-code-research-in-sleep-manual/tree/main/skills/monitor-experiment
Command: npx skills add https://github.com/loujc/Auto-claude-code-research-in-sleep-manual --skill monitor-experiment-loujc

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Monitor running experiments, check progress, collect results across remote servers to keep you informed without constant manual polling.

Core Features & Use Cases

  • SSH-based session discovery to enumerate active experiment tasks on target machines.
  • Centralized collection of outputs from each screen/session and identification of latest results.
  • Optional integration with Weights & Biases to fetch training metrics when enabled.
  • Automated summaries and optional notifications to keep the team updated.

Quick Start

Check the status of all running experiments on the target server and retrieve the latest outputs.

Frequently Asked Questions about monitor-experiment

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

FAQPage Schema
How do I monitor running experiments on remote servers via SSH?▼

You can monitor running experiments via SSH by discovering active sessions and collecting progress updates. This skill automates periodic progress checks on SSH-accessible servers to aggregate outputs and metrics without manual polling.

Can I pull training metrics from W&B while checking experiment progress?▼

Yes, you can pull training metrics from W&B. The skill supports optional Weights & Biases integration to fetch and aggregate training metrics alongside remote output capture when enabled.

How do I aggregate JSON results from multiple remote training sessions?▼

You can aggregate JSON results by capturing remote outputs from each active screen or session. The skill identifies and collects the latest JSON results across target machines into centralized summaries.

What is the best way to automate progress checks for long-running experiments?▼

Automating progress checks for long-running experiments involves periodic polling of remote servers. This skill handles SSH session listing and output capture, surfacing results quickly to keep you informed.

Do I need to manually connect to SSH to check experiment outputs across different machines?▼

No, you do not need to manually connect to SSH for each machine. The skill performs SSH-based session discovery to enumerate active tasks and centrally collects outputs from each session automatically.

Can I send automated experiment summaries to Feishu notifications?▼

Yes, you can send automated experiment summaries to Feishu. The skill provides optional Feishu notifications to keep your team updated on collected results and progress from remote servers.

Related Skills

Explore More Data & Analytics Skills→
zangjeicyzangjeicy

pinggy-tunnel

Expose local network services via SSH-based reverse tunneling.

Community
Intermediate
wanshuiyinwanshuiyin
14.4k

monitor-experiment

Monitor remote machine learning experiments via SSH and collect JSON results.

Community
Intermediate
CyapstayeCyapstaye
9

weights-and-biases

Log machine learning experiment metrics and hyperparameters to Weights & Biases.

Community
Advanced
mammut001mammut001
2

autoresearch

Run autonomous ML experiment loops on a remote VPS via SSH.

Community
Advanced