Verified:GitHub

nature-figure

Generate Nature-style multi-panel scientific figures with Python or R and editable SVG exports.

Updated May 11, 2026

Search Tags:#scientific visualization #multi-panel layout #figure QA #nature-style figures #svg editable text #python or r backend gate #publication export

One-click install

npx skills add https://github.com/IceYuanyyy/awesome-skills-collection --skill nature-figure-iceyuanyyy

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: nature-figure
Source: https://github.com/IceYuanyyy/awesome-skills-collection/tree/main/collections/nature-skills/skills/nature-figure
Command: npx skills add https://github.com/IceYuanyyy/awesome-skills-collection --skill nature-figure-iceyuanyyy

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve?

Producing publication-ready scientific figures that communicate a clear claim, correct evidence hierarchy, and review-safe export assets is slow and error-prone, especially when layout, typography, and journal constraints must be handled consistently.

Core Features & Use Cases

Figure contract first: converts the user request into a claim, archetype, panel map, evidence hierarchy, and reviewer-risk checklist before writing any plotting code.
Python or R, exclusively: enforces a blocking backend gate (“Python or R?”), then uses only the selected runtime for all rendering, previews, exports, and visual QA to avoid cross-backend inconsistencies.
Nature-style output discipline: ensures editable text in SVG (via mandatory matplotlib rcParams), publication-appropriate typography, restrained palettes, and consistent multi-panel architecture.
Multi-panel scientific plot patterns: supports dense comparison bars, trends with uncertainty, heatmaps, radar/polar charts, and complex scientific layouts where each panel answers a unique question.
Export/QA readiness: produces editable SVG as primary output and optional PDF/TIFF/PNG exports, with explicit rules for privacy (no private paths/templates/provenance in user-facing output).

Quick Start

Use the nature-figure skill to generate a journal-ready multi-panel scientific figure from your figure contract and requested backend by asking the AI: "Make a Nature-style publication figure: choose Python or R, define the figure claim and panel map, then generate editable SVG exports (and PDF/TIFF if needed) that match the evidence logic."

Frequently Asked Questions about nature-figure

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

FAQPage Schema

How do I generate a Nature-style publication figure with Python or R?▼

A Nature-style figure contract translates your user request into a scientific claim, archetype, panel map, evidence hierarchy, and reviewer-risk checklist before writing any plotting code, ensuring the final multi-panel layout communicates correct evidence logic.

How do I export editable SVG text from matplotlib for journal submission?▼

Yes, you can create multi-panel layouts in R using ggplot2 and ComplexHeatmap or patchwork, as the workflow enforces a Python or R backend gate to ensure all rendering, previews, exports, and visual QA use only the selected runtime exclusively.

Does this workflow support complex heatmaps and radar charts for scientific visualization?▼

You start by asking the AI to define your figure claim and panel map, select your exclusive Python or R backend, and then generate editable SVG exports along with optional PDF, TIFF, or PNG files that match your evidence logic.

Why does the figure generation process require choosing between Python or R exclusively?▼

The workflow includes privacy-safe user-facing output rules and reviewer-oriented QA checks, ensuring no private paths, templates, or provenance appear in exported files, making the final figures revision-safe for reviewer evaluation.