Verified:GitHub

media-processor

Process multimedia content to extract visual details and convert files to Markdown.

113|15|Updated Mar 3, 2026

Search Tags:#image-generation #batch-processing #document-conversion #gemini-api #media-processing #pdf-extraction #ui-design-analysis

Ready to run

npx skills add https://github.com/avibebuilder/claude-prime --skill media-processor-avibebuilder

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: media-processor
Source: https://github.com/avibebuilder/claude-prime/tree/main/.claude/skills/media-processor
Command: npx skills add https://github.com/avibebuilder/claude-prime --skill media-processor-avibebuilder

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, python-dotenv, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Media-heavy tasks require precise visual analysis, media conversion, and automated extraction to reduce manual effort and improve consistency across design reviews and media pipelines.

Core Features & Use Cases

Image analysis & generation: analyze visuals, extract design tokens, and generate or edit images from prompts or provided inputs.
Document & media conversion: convert PDFs, images, and office documents to clean Markdown, extract text from images, and summarize multimedia content.
Batch processing & automation: process multiple files with retry logic, model routing, and outputs in Markdown, JSON, or CSV.
Use Case: audit UI screenshots for colors, spacing, typography, and component hierarchy; transcribe or extract data from complex layouts and PDFs.

Quick Start

Convert the attached design or media file into a structured Markdown extraction showing colors, spacing, and typography.

Frequently Asked Questions about media-processor

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

FAQPage Schema

How do I extract text and data from a PDF or image into Markdown?▼

To extract text and data from PDFs and images into Markdown, you can process multimedia content to convert documents, extract text, and summarize layouts. This handles complex visual layouts and outputs structured Markdown.

Can I batch process multiple media files for visual regression comparisons?▼

Yes, batch processing multiple media files for visual regression comparisons is supported. You can process multiple files with automated retry logic, model routing, and structured outputs in Markdown, JSON, or CSV formats.

How do I audit UI screenshots for colors, spacing, and typography?▼

To audit UI screenshots for colors, spacing, and typography, you perform image analysis to extract precise visual details and design tokens. This process reviews component hierarchy and visual elements from provided inputs.

Do I need a Gemini API key to analyze images and generate media?▼

Yes, you need a Gemini API key to analyze images and generate media. Integration with the Google Gemini API utilizes the gemai client, requiring you to configure your GEMINI_API_KEY via environment keys or a .env file.

What is the best way to convert office documents to clean Markdown for development tasks?▼

The best way to convert office documents to clean Markdown is through media conversion workflows that apply precise visual analysis. This extracts text from images and standardizes multimedia content for development and QA tasks.

Can I generate or edit images from text prompts using the Gemini API?▼

Yes, you can generate or edit images from text prompts or provided inputs using the Gemini API. This functionality analyzes existing visuals, extracts design tokens, and creates new media outputs based on your prompts.