skills.rest
BotchaVarun
BotchaVarunCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

media-generation

Generate AI images and videos and retrieve stock images from text descriptions.

Updated Mar 8, 2026
Search Tags:#image generation#visual content#video generation#prompt#text to image#ai media#stock images
One-click install
npx skills add https://github.com/BotchaVarun/EduBot --skill media-generation-botchavarun
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: media-generation
Source: https://github.com/BotchaVarun/EduBot/tree/main/.local/skills/media-generation
Command: npx skills add https://github.com/BotchaVarun/EduBot --skill media-generation-botchavarun

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Creating visual content for applications, websites, and marketing materials normally requires design skills, stock photo subscriptions, or manual asset sourcing. This Skill generates custom AI images and videos from text prompts and retrieves licensed stock images, all saved directly to your project. ## Core Features & Use Cases - AI Image Generation: Create up to 10 custom images per call with control over aspect ratio, negative prompts, and background removal, saved as PNG files. - AI Video Generation: Produce short video clips (4-8 seconds) in 720p or 1080p with landscape or portrait orientation. - Stock Image Retrieval: Fetch up to 10 licensed stock photos matching a description with orientation filtering. - Use Case: Building a landing page and need a hero image, product illustrations, and a background video? Generate the hero image in 16:9, create product icons with removed backgrounds, and produce a 6-second ambient video clip in one workflow. ## Quick Start Generate a 16:9 hero image of a mountain landscape at sunset and save it to src/assets/images/hero.png.

Frequently Asked Questions about media-generation

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

FAQPage Schema
How do I generate AI images from a text prompt?▼

Call generateImage with an images array containing objects with a prompt and outputPath. The outputPath must end in .png, and you can generate up to 10 images per call with optional aspect ratio and negative prompt settings.

How to generate short AI videos from text descriptions?▼

Use generateVideo with a detailed prompt describing the scene. You can set aspectRatio to 16:9 or 9:16, resolution to 720p or 1080p, and durationSeconds to 4, 6, or 8 seconds.

Why does image generation fail with an outputPath error?▼

The outputPath must end in .png because it is the only accepted format. Extensions like .jpg, .jpeg, or .webp cause an error, so always use .png for generated image files.

When should I use stock images instead of AI-generated images?▼

Use stockImage when you need authentic professional photography, real-world scenes, people, or corporate imagery. Use AI generation for custom illustrations, creative concepts, or visuals that do not exist in stock libraries.

What are the limitations of AI video generation?▼

Generated videos are limited to a maximum of 8 seconds in length. Text rendered inside generated media is unreliable, and highly specific or complex prompts may not match exactly.

Related Skills

Explore More Design & Creative Skills→
Growthub-aiGrowthub-ai
48

growthub-creative-video-pipeline

Automate video workflows from brief to final edit with staged updates and trace logging.

Official
Advanced
CivicActionsCivicActions
2

performance-frontend

Audit frontend performance by analyzing Core Web Vitals and render-blocking resources.

Official
Advanced
Owl-ListenerOwl-Listener
234

accessible-content

Guide authors to write plain-language interface copy for WCAG-aligned accessibility.

Community
Advanced
nicepkgnicepkg
276

pexels-media

Source and download royalty-free images and videos from the Pexels API with metadata files.

Official
Intermediate