generate-image

Generate or edit general-purpose images from natural-language prompts.

Updated May 27, 2026
One-click install
npx skills add https://github.com/rauffatali/my-research-copilot --skill generate-image-rauffatali
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: generate-image
Source: https://github.com/rauffatali/my-research-copilot/tree/main/.agents/skills/generate-image
Command: npx skills add https://github.com/rauffatali/my-research-copilot --skill generate-image-rauffatali

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Generate Image turns a text description into a reusable, general-purpose image asset without mixing in evidence-sensitive or technical diagram content.

Core Features & Use Cases

  • General image generation & editing: Create photos, illustrations, artwork, concept art, and background visuals, plus edits to existing images.
  • Style- and intent-aware prompting: Encourages non-technical, non-evidence portrayals and explicitly avoids technical schematics, workflows, plots, and result figures.
  • Integration with repo workflows: Pairs with scientific-writing for captions/prose and with venue-templates for final sizing/format checks.

Quick Start

Ask for a non-technical background image in your desired style and exclusion constraints, then save the output image to your target folder.

Frequently Asked Questions about generate-image

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

FAQPage Schema
How do I generate non-technical images for presentation backgrounds from text?

To generate non-technical images for presentation backgrounds, provide a natural-language prompt describing your desired style and exclusion constraints. The tool outputs general-purpose visual assets like photos, illustrations, and background textures directly to your target folder.

Can I use image generation to edit existing visual assets?

Yes, you can edit existing visual assets by providing optional image edit inputs alongside your text prompt. This allows you to modify photos, illustrations, and concept art while enforcing prompt boundaries against technical schematics and result figures.

Does this image generation tool support technical schematics and result figures?

No, this image generation tool explicitly avoids technical schematics, workflows, plots, and result figures. It enforces prompt boundaries to ensure visuals do not imply experiments, datasets, results, or technical claims, focusing solely on non-evidence portrayals.

Do I need an API key to generate images via CLI or API execution?

Yes, you need provider-specific API keys for deterministic CLI or API execution. The tool uses the requests dependency to process natural-language prompts and optional image edit inputs, producing visual assets for reports, slides, and presentation materials.

What is the best way to create concept art without implying technical claims?

The best way to create concept art without implying technical claims is to use style- and intent-aware prompting that encourages non-technical, non-evidence portrayals. This ensures your generated artwork avoids technical diagrams and result figures while meeting visual asset needs.

Why does image generation enforce boundaries against technical schematic content?

Image generation enforces boundaries against technical schematic content to prevent visuals from implying experiments, datasets, or technical claims. This ensures the generated photos, illustrations, and background textures remain safe, non-technical assets for reports and presentation materials.