figure

Generate images from descriptive prompts and context using Google Gemini Nano Banana 2 API.

53|11|Updated Feb 26, 2026
One-click install
npx skills add https://github.com/a554b554/Reactant --skill figure-a554b554
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: figure
Source: https://github.com/a554b554/Reactant/tree/main/skills/figure
Command: npx skills add https://github.com/a554b554/Reactant --skill figure-a554b554

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables users to generate visual figures directly from textual prompts and surrounding content, streamlining visual creation for reports, presentations, and research.

Core Features & Use Cases

  • Automated Figure Generation: Converts descriptive prompts and contextual information into images using Google Gemini Nano Banana 2 API.
  • Context-Sensitive: Reads additional resources referenced within the prompt to produce more accurate and relevant visuals.
  • Use Case: For example, generate an architecture diagram based on a textual description and supplementary system specifications, saving time on manual drawing.

Quick Start

Use the figure skill to generate a diagram based on the architecture description in the current document and save it alongside your work.

Frequently Asked Questions about figure

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

FAQPage Schema
How do I generate a diagram from a text description in my document?

To generate a diagram from text, provide a descriptive prompt and the surrounding context. The Skill converts this input into an image, automatically saving the visual with a meaningful filename alongside your work.

Can I use external reference files to create more accurate AI-generated graphics?

Yes, you can incorporate context references from external files. The Skill reads these additional resources to produce visuals that are more accurate and relevant to your specific architectural or system specifications.

How does context-sensitive image generation work for reports and presentations?

Context-sensitive image generation works by analyzing your descriptive prompt alongside surrounding document content. It uses this combined information to create tailored visuals, streamlining graphic creation for professional reports and presentations.

What is the best way to automate architecture diagram creation from system specifications?

The best way to automate architecture diagram creation is using a Skill that interprets textual descriptions and supplementary specifications. It directly translates your system context into a saved visual, replacing manual drawing steps.

Do I need to manually name image files generated from prompts?

No, you do not need to manually name generated image files. The Skill automatically saves the output with a meaningful filename, replacing the original placeholder prompt to keep your visual assets organized.