Verified:GitHub

/exp-status

Monitor experiment runtime states and flag anomalies from screen or GPU/SSH runs.

77|16|Updated May 9, 2026

Search Tags:#automation #anomaly detection #research pipeline #experiment monitoring #screen sessions #wiki status #remote job checks

Ready to run

npx skills add https://github.com/Lambenthan/empiricalwiki --skill exp-status-lambenthan

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: /exp-status
Source: https://github.com/Lambenthan/empiricalwiki/tree/main/.claude/skills/exp-status
Command: npx skills add https://github.com/Lambenthan/empiricalwiki --skill exp-status-lambenthan

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you keep track of many concurrent experiments by detecting which ones are still running, which ones look anomalous, and which ones finished but still need result collection.

Core Features & Use Cases

Live experiment status monitoring: Scans wiki/experiments/{slug}.md for running experiments (or a specified pipeline) and checks local screen sessions or remote jobs to classify them as running, anomaly, or completed-pending-collect.
Anomaly reporting without auto-fixing: Flags issues such as NaN/OOM/Traceback/Inf patterns and clearly tells you what to do next (typically manual collect via /exp-run).
Pipeline-aware automation: With --collect-ready, it triggers result collection for completed-but-not-collected runs; with --auto-advance, it advances research when all pipeline experiments have completed.

Quick Start

Run the experiment monitor for all running experiments by typing: /exp-status.

Frequently Asked Questions about /exp-status

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

FAQPage Schema

How do I monitor running experiments across local screen sessions and remote SSH jobs?▼

To monitor running experiments, the system scans wiki experiment pages and checks process liveness or log tails for local screen sessions and remote SSH jobs, classifying each run as running, anomalous, or pending collection.

How does anomaly detection work for empirical research pipelines?▼

Anomaly detection for research pipelines works by scanning experiment log tails to flag patterns like NaN, OOM, Traceback, or Inf, reporting these issues without auto-fixing so users can manually decide the next action.

Can I schedule periodic automated checks for my empirical experiments?▼

Yes, you can schedule automated experiment monitoring as periodic cron checks by scoping the status checks to a specific research pipeline, ensuring continuous tracking without manual intervention.

How do I auto-advance a research pipeline when all experiments finish?▼

To auto-advance a research pipeline, the monitor checks if all experiments within the specified pipeline have completed, then automatically triggers the pipeline advancement process to proceed to the next stage.

What is the best way to collect results from completed but uncollected screen runs?▼

The best way to collect results from completed screen runs is using the collection-ready monitor flag, which identifies finished experiments pending collection and triggers the result collection process automatically.

Does experiment monitoring support remote GPU runs or only local processes?▼

Experiment monitoring supports both local screen-based runs and remote GPU SSH jobs, checking process liveness and log tails across both environments to provide a unified status overview.