publication-plots

Convert saved run artifacts into publication-ready plots and metric summaries.

Updated Feb 18, 2026
One-click install
npx skills add https://github.com/rilical/OpenWorld-AI-Image-Detection --skill publication-plots
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: publication-plots
Source: https://github.com/rilical/OpenWorld-AI-Image-Detection/tree/main/.agents/skills/publication-plots
Command: npx skills add https://github.com/rilical/OpenWorld-AI-Image-Detection --skill publication-plots

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps teams transform saved run artifacts into publication-ready plots and tables, enabling clear communication of results without re-running experiments.

Core Features & Use Cases

  • Generate figures from artifacts: risk-coverage curves, reliability diagrams, and metric summaries using saved outputs.
  • Produce per-generator breakdowns and consolidated reports for dashboards or papers.
  • Ensure reproducibility by basing all visuals on artifacts stored in outputs/runs.

Quick Start

Process saved run artifacts from outputs/runs/ to generate ready-to-share plots.

Frequently Asked Questions about publication-plots

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

FAQPage Schema
How do I generate publication-ready plots from saved run artifacts?

To generate publication-ready plots from saved run artifacts, this Skill reads directly from your outputs/runs data and converts the artifacts into risk-coverage curves, reliability diagrams, and metric summaries without re-running experiments.

Can I create reliability diagrams and risk-coverage curves without re-running experiments?

Yes, you can create reliability diagrams and risk-coverage curves without re-running experiments by reading directly from saved artifacts stored in your outputs/runs directory to ensure full reproducibility.

What is the best way to visualize per-generator breakdowns for consolidated reports?

The best way to visualize per-generator breakdowns for consolidated reports is to process saved run artifacts, which automatically parses the data to produce consolidated figures and tables ready for dashboards or papers.

Does this approach ensure reproducibility when exporting evaluation plots?

Yes, this approach ensures reproducibility when exporting evaluation plots by strictly basing all generated visuals on saved artifacts and exporting the underlying plot data alongside the figures.

How do I export plot data alongside publication-ready figures?

To export plot data alongside publication-ready figures, the Skill processes your saved outputs and automatically generates the visual figures while simultaneously exporting the corresponding data used to create them.