skills.rest
mafvietnam
mafvietnamCOMMUNITY
Explore all skills by this author →
GitHub

ck:ai-multimodal

Analyze and generate images, audio, and video using Gemini and MiniMax APIs.

Updated Mar 30, 2026
Search Tags:#automation#ocr#multimodal#transcription#vision#generation#gemini
One-click install
npx skills add https://github.com/mafvietnam/mafapp --skill ck-ai-multimodal-mafvietnam
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ck:ai-multimodal
Source: https://github.com/mafvietnam/mafapp/tree/main/.claude/skills/ai-multimodal
Command: npx skills add https://github.com/mafvietnam/mafapp --skill ck-ai-multimodal-mafvietnam

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Automates multimodal analysis and generation across images, audio, video, and documents using Gemini and MiniMax, enabling rapid transformation of media into actionable insights and assets.

Core Features & Use Cases

  • Analyze images, audio, and video with Gemini for captions, classifications, OCR, and visual QA.
  • Generate images (Imagen 4, Nano Banana) and videos (Veo 3, Veo 3.1), speech (TTS), and music (MiniMax) from prompts or file inputs.
  • Use cases include transcription of meetings, extraction of data from PDFs, and creation of publish-ready media assets for product and marketing workflows.

Quick Start

Run a simple media-through-Gemini workflow: analyze or generate, then save outputs to docs/assets for reuse.

Frequently Asked Questions about ck:ai-multimodal

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

FAQPage Schema
How do I automate multimodal content analysis and media generation using Gemini?▼

Automate multimodal content analysis by routing images, audio, and video through Gemini APIs to extract captions, perform OCR, and generate new media assets using deterministic scripts with centralized API key resolution.

Can I use Gemini for transcription of meetings and data extraction from PDFs?▼

Yes, Gemini supports transcription of meetings and data extraction from PDFs by processing audio and document inputs to convert media into actionable text insights and structured data within automated pipelines.

What's the best way to generate images and videos from text prompts in an automated pipeline?▼

Generate images and videos from text prompts in automated pipelines by calling Gemini and MiniMax APIs through deterministic scripts, producing visual assets using models like Imagen 4 and Veo 3.

Do I need Python and specific API keys to run Gemini vision and OCR workflows?▼

Yes, running Gemini vision and OCR workflows requires Python dependencies including google-genai, python-dotenv, requests, and Pillow, along with centralized API key resolution to execute automated media processing scripts.

Does this multimodal AI skill support generating speech and music with MiniMax APIs?▼

Yes, this skill supports generating speech and music with MiniMax APIs, integrating text-to-speech and music generation alongside Gemini visual analysis to produce comprehensive multimedia assets.

What are the limitations of using Gemini for visual QA and multimedia generation in production?▼

Limitations of using Gemini for visual QA and multimedia generation include dependency on external API availability and rate limits, mitigated by robust error handling but constrained by the deterministic nature of scripted production pipelines.

Related Skills

Explore More Software Engineering Skills→
nguyenvanlinh1902nguyenvanlinh1902

ai-multimodal

Extract insights from images, audio, and video using Gemini multimodal APIs.

Community
Advanced
broomvabroomva
3

blog-post

Orchestrate blog post production from brief to multi-format content packages.

Community
Advanced
jangtrinhjangtrinh

ck:ai-multimodal

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

Community
Advanced
DevattomDevattom

ai-multimodal

Process and generate multimedia content using the Google Gemini API.

Community
Advanced