ck:ai-multimodal

Process images, audio, video, and documents with Gemini and MiniMax APIs.

Updated Apr 9, 2026

Search Tags:#ocr #image generation #transcription #video generation #multimodal ai #document extraction #gemini vision

One-click install

npx skills add https://github.com/jangtrinh/demo-Lam --skill ck-ai-multimodal-jangtrinh

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: ck:ai-multimodal
Source: https://github.com/jangtrinh/demo-Lam/tree/main/.claude/skills/ai-multimodal
Command: npx skills add https://github.com/jangtrinh/demo-Lam --skill ck-ai-multimodal-jangtrinh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, python-dotenv, pillow, pypdf, python-docx, docx2pdf, markdown, requests, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill removes the friction of working with multimodal inputs by turning images, audio, video, and documents into usable analysis, transcripts, extracted text, and generated media outputs—without you manually stitching together multiple tools.

Core Features & Use Cases

Vision & Multimodal Analysis: Analyze images, screenshots, documents, and video content with Gemini for tasks like OCR, design extraction, and content understanding.
Speech, Music, and Media Generation: Generate images (Gemini/Imagen), videos (Veo), and additional creative assets like speech (MiniMax TTS) and music (MiniMax).
Batch Pipelines & Media Handling: Run deterministic batch scripts for analyze/transcribe/extract/generate while managing large files via File API and chunking guidance.

Quick Start

To analyze the design and extract key UI elements from an image file you provide, run the ai-multimodal skill with the file path and your extraction request.

Frequently Asked Questions about ck:ai-multimodal

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

FAQPage Schema

How do I extract text from images and documents using Gemini vision?▼

To transcribe audio and video with Gemini, you can process long-media inputs by applying chunking guidance and optional File API uploads to handle large files, returning accurate transcripts from the API.

Can I generate images and video from text using Gemini and MiniMax?▼

Yes, you can generate speech and music with MiniMax APIs by running deterministic batch scripts that process your input text to synthesize and save audio files locally.

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

For large file multimodal analysis, you should use the File API to upload your inputs before processing, which allows the scripts to handle large media files that exceed standard inline payload limits.

What's the best way to convert PDF documents to markdown format?▼

The best way to convert PDF documents to markdown format is using batch scripts that process PDFs with Gemini, extracting content and structuring it into markdown files for downstream use.