check-status

Report experiment, SLURM job, and pipeline status per dataset.

Updated Jan 25, 2026
One-click install
npx skills add https://github.com/RobertFrenken/DQN-Fusion --skill check-status
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: check-status
Source: https://github.com/RobertFrenken/DQN-Fusion/tree/main/.claude/skills/check-status
Command: npx skills add https://github.com/RobertFrenken/DQN-Fusion --skill check-status

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a consolidated view of ongoing experiments, job queues, and pipeline progress, reducing manual checks and improving awareness of system health.

Core Features & Use Cases

  • Real-time visibility into experiment progress across datasets.
  • Snapshot of the SLURM queue, recent job errors, and completed stages in pipelines.
  • Use Case: Teams can confirm which datasets have completed critical stages and identify stalled jobs to prioritize remediation.

Quick Start

Run the status check to view the latest progress of experiments, SLURM jobs, and pipeline stages.

Frequently Asked Questions about check-status

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

FAQPage Schema
How do I check the status of running SLURM jobs and experiments?

To check SLURM job and experiment status, run the status check to read local experiment directories and log files, aggregating the latest progress, recent job errors, and completed stages into a compact table.

Can I monitor pipeline progress across specific datasets instead of all of them?

Yes, you can monitor pipeline progress by applying status checks to a given dataset filter, providing per-dataset stage statuses to confirm which datasets have completed critical stages.

What is the best way to view stalled jobs and recent errors in my SLURM queue?

The best way to view stalled jobs and errors is to generate a snapshot of the SLURM queue and local logs, aggregating results into a human-readable table to prioritize remediation for failed jobs.

Does this pipeline monitoring approach require any external dependencies?

No external dependencies are required to monitor pipeline progress, as the approach directly reads local experiment directories and log files to aggregate system health awareness.

Why do I need a consolidated view of my experiment and pipeline progress?

You need a consolidated view of experiment progress to reduce manual checks across multiple datasets, improving awareness of system health and helping identify stalled jobs to quickly prioritize remediation.