skills.rest
felixmin
felixminCOMMUNITY
Explore all skills by this author →
GitHub

evaluate-run

Evaluate HLRP runs by inspecting status, performance trends, and artifacts.

Updated Oct 23, 2025
Search Tags:#debugging#performance analysis#experiment tracking#hlrp#run evaluation#log inspection
One-click install
npx skills add https://github.com/felixmin/robot-learning-from-video --skill evaluate-run
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: evaluate-run
Source: https://github.com/felixmin/robot-learning-from-video/tree/main/.codex/skills/evaluate-run
Command: npx skills add https://github.com/felixmin/robot-learning-from-video --skill evaluate-run

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you quickly understand the status and performance of your High-Level Reinforcement Learning (HLRP) runs without needing to manually sift through logs and cluster outputs.

Core Features & Use Cases

  • Run Evaluation: Analyze the status, performance trends, and key artifacts of HLRP runs.
  • Flexible Referencing: Identify runs using job IDs, directory paths, documented stems, or simply by checking the last run.
  • Use Case: After a long training job finishes on the cluster, use this Skill to get a concise summary of its success, failure points, and key metrics.

Quick Start

Use the evaluate-run skill to check the last run on this system.

Frequently Asked Questions about evaluate-run

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

FAQPage Schema
How do I check the status of my HLRP training run after it finishes?▼

You can check HLRP training run status by referencing job IDs, directory paths, or asking to check the last run. The evaluation inspects unified logs, .out/.err files, and .hydra configurations to report success or failure points.

How do I inspect HLRP logs and checkpoints without manual sifting?▼

Inspect HLRP logs and checkpoints by pointing the evaluation to a run directory or documented run stem. It analyzes .out/.err files and visualization outputs automatically to summarize performance trends and key artifacts.

What is the best way to analyze reinforcement learning run performance trends?▼

Analyzing reinforcement learning run performance trends requires inspecting unified logs and visualization outputs from the run directory. This process evaluates training success and extracts key metrics without manual log searching.

Can I evaluate an HLRP run using just a job ID?▼

Yes, you can evaluate an HLRP run using a job ID, directory path, documented run stem, or the phrase 'check last run'. Flexible referencing allows quick access to run artifacts and performance analysis.

Does run evaluation work with Hydra configuration files?▼

Run evaluation works with Hydra configurations by inspecting .hydra config files within the run directory. It extracts configuration parameters to provide comprehensive reporting alongside checkpoint and log analysis.

Why does my HLRP run evaluation show incomplete performance trends?▼

HLRP run evaluation may show incomplete performance trends if unified logs, .out/.err files, or visualization outputs are missing from the run directory. Comprehensive reporting requires all artifacts to be present for analysis.

Related Skills

Explore More Software Engineering Skills→
gyy0592gyy0592
7

gen-report-concise

Generate concise experiment reports from training run artifacts and logs.

Community
Advanced
ovachieverovachiever
52

weights-and-biases

Automate ML experiment tracking and model registry management via the wandb API.

Community
Advanced
dominodatalabdominodatalab
6

domino-experiment-tracking

Track MLflow experiments in Domino Data Lab with auto-logging.

Official
Intermediate
nuno7lopesnuno7lopes

gemini

Answer questions and summarize text using the Gemini CLI.

Community
Intermediate