summarize-run

Official

Automate extraction of W&B run summaries for quick experiment insights.

Authorhao-ai-lab
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill simplifies the process of retrieving and summarizing key metrics from W&B run data, enabling faster analysis of machine learning experiments.

Core Features & Use Cases

  • Data Extraction: Retrieves metrics such as train loss, step time, gradient norm, and validation results from W&B APIs or local JSON summaries.
  • Comparison & Reporting: Generates detailed markdown reports comparing current results against reference run data for monitoring progress.
  • Use Case: Researchers and engineers can quickly generate structured experiment summaries after training to document performance and identify issues, either online via W&B or offline from stored JSON files.

Quick Start

Summarize the latest training metrics from the output directory 'outputs/wan_finetune' using a reference summary file to generate a report.

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: summarize-run
Download link: https://github.com/hao-ai-lab/FastVideo/archive/main.zip#summarize-run

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 471,000+ vetted skills library on demand.