evaluation-display-skill

Generate evaluation figures and LaTeX tables from model metrics.

Updated Feb 7, 2026

Search Tags:#metrics #notebooks #latex #tables #figures #evaluate

Ready to run

npx skills add https://github.com/jluo41/claude-skills --skill evaluation-display-skill

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: evaluation-display-skill
Source: https://github.com/jluo41/claude-skills/tree/main/evaluation-display-skill
Command: npx skills add https://github.com/jluo41/claude-skills --skill evaluation-display-skill

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill streamlines the creation of evaluation outputs by scaffolding Python scripts that compute metrics, generate LaTeX tables, and produce publication-ready figures from model results.

Core Features & Use Cases

Consistent evaluation scaffolding: Provides a repeatable pattern for producing tables and figures from CSV metrics.
Config-driven analysis: Reads configuration from 1-config.yaml to control models, tasks, and outputs, and automatically copies results to display folders.
Notebook conversion support: Integrates with optional notebook conversion to enable interactive exploration of results.

Quick Start

Run the script evaluation/scripts/3-R5-event-comparison.py after configuring the 1-config.yaml to generate the figure and corresponding results.

Frequently Asked Questions about evaluation-display-skill

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

FAQPage Schema

How do I generate LaTeX tables and figures from model evaluation metrics?▼

Generate LaTeX tables and figures from model evaluation metrics by running Python scripts that read CSV inputs and configuration files. This skill automates script scaffolding to compute metrics and produce publication-ready visualizations.

How does configuration-driven analysis work for generating paper evaluation outputs?▼

Configuration-driven analysis reads settings from a YAML file to control models and tasks, automatically generating standardized outputs and copying results to display folders for consistent evaluation scaffolding.

Can I use notebook conversion to explore model evaluation results interactively?▼

Notebook conversion supports interactive exploration of model evaluation results. The skill integrates optional notebook conversion to enable dynamic analysis alongside the generated LaTeX tables and figures.

What is the best way to ensure consistent visualizations across multiple models and tasks?▼

Ensure consistent visualizations across multiple models using standardized paths, color schemes, and configuration-driven scripts. This approach provides a repeatable pattern for producing uniform tables and figures.

Do I need CSV metrics files to automate publication-ready figure generation?▼

CSV metrics files are required to automate publication-ready figure generation. The skill scaffolds Python scripts that read these CSV inputs to compute model metrics and output standardized visual artifacts.

evaluation-display-skill: what publication-ready outputs does it produce?▼

The evaluation-display-skill produces LaTeX tables and publication-ready figures from model metrics. It automates Python script generation to compute metrics, supporting multi-metric analysis and display-ready artifacts.