academic-figure-engine

Generate publication-ready figures from raw analysis results with data provenance.

8|Updated Mar 18, 2026
One-click install
npx skills add https://github.com/TerryFYL/ai-research-army --skill academic-figure-engine
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: academic-figure-engine
Source: https://github.com/TerryFYL/ai-research-army/tree/main/skills/academic-figure-engine
Command: npx skills add https://github.com/TerryFYL/ai-research-army --skill academic-figure-engine

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires matplotlib, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This engine automates the generation of publication-grade figures from raw analysis results while enforcing traceable data provenance, reducing manual plotting errors, and ensuring compliance with journal guidelines.

Core Features & Use Cases

  • Automated rendering of common figure types (Kaplan-Meier curves, forest plots, heatmaps, box plots, scatter plots, radar charts, tables) powered by a five-layer quality framework that includes data truth, standardization, verification, manuscript synchronization, and visual refinement.
  • Output in publication-ready formats (PNG, PDF, TIFF) with per-figure data sources and reproducible pipelines, plus verification reports suitable for manuscript submission.
  • Use Case: A biomedical research team analyzes a clinical dataset, automatically generates a complete figure suite, and obtains a delivery package aligned with journal requirements.

Quick Start

Start by providing your analysis results and instruct the engine to generate publication-ready figures.

Frequently Asked Questions about academic-figure-engine

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

FAQPage Schema
How do I generate publication-ready figures with data provenance for a biomedical manuscript?

The engine generates publication-ready figures with data provenance by automating rendering from raw analysis results, enforcing a five-layer quality framework that traces source data and ensures journal compliance.

What chart types are supported for biomedical publication graphics?

Supported biomedical publication graphics include Kaplan-Meier curves, forest plots, heatmaps, box plots, scatter plots, radar charts, and tables, all rendered through a standardized visual refinement layer.

Can I output figures in TIFF, PDF, and PNG formats for journal submission?

Yes, you can output figures in TIFF, PDF, and PNG formats for journal submission. The engine provides per-figure data sources and verification reports suitable for manuscript delivery.

Does the figure generation engine work with matplotlib for style compliance?

Yes, the figure generation engine works with matplotlib to apply style guides and journal presets, ensuring deterministic data rendering and visual refinement for manuscript-ready delivery.

How does data provenance and source traceability work when generating publication figures?

Data provenance and source traceability work by enforcing a data truth layer within the five-layer framework, capturing per-figure data sources and reproducible pipelines to verify figure accuracy.

What is the best way to automate forest plots and Kaplan-Meier curves for clinical datasets?

The best way to automate forest plots and Kaplan-Meier curves is using an engine that applies standardization and automated verification layers to raw clinical data, ensuring deterministic rendering and manuscript synchronization.