ck:ai-multimodal

Analyze and generate images, audio, video, and documents via Gemini's multimodal API.

Updated Feb 27, 2026

Search Tags:#automation #api #multimodal #video #vision #audio #gemini

Ready to run

npx skills add https://github.com/haidonglethqb/CloudSchool --skill ck-ai-multimodal-haidonglethqb

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ck:ai-multimodal
Source: https://github.com/haidonglethqb/CloudSchool/tree/main/.qwen/skills/ai-multimodal
Command: npx skills add https://github.com/haidonglethqb/CloudSchool --skill ck-ai-multimodal-haidonglethqb

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Automate multimodal analysis and content generation from media using Gemini's multimodal API, turning raw media into structured insights and ready-to-use assets.

Core Features & Use Cases

Analyze images, audio, video, and documents to extract captions, classifications, OCR, and scene insights.
Generate new content such as images (Imagen 4) and videos (Veo 3) from prompts, with support for multimodal outputs.
Real-world scenario: convert a batch of product photos and interviews into captions, summaries, and marketing visuals for reports or campaigns.

Quick Start

Provide the path to a media file and a task prompt, and run the Gemini-based multimodal batch processor to analyze or generate content.

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 analysis for images, audio, and video using Gemini?▼

Automate multimodal analysis by providing a media file path and a task prompt to the Gemini-based batch processor. It evaluates images, audio, video, and documents to extract captions, classifications, and scene insights.

Can I generate images and videos from text prompts with this multimodal API workflow?▼

Yes, you can generate images and videos from text prompts. The workflow leverages Imagen 4 for image generation and Veo 3 for video generation to produce ready-to-use visual assets.

What Python dependencies do I need to run multimodal AI workflows?▼

You need the google-genai, python-dotenv, and Pillow Python dependencies installed. These libraries enable the API calls, environment variable management, and image processing required for the workflows.

Does this multimodal AI workflow support OCR and audio transcription?▼

Yes, the multimodal AI workflow supports both OCR and audio transcription. It processes documents and audio files through Gemini's API to extract text and convert speech into structured text insights.

How is API key rotation and error handling managed in Gemini multimodal automation?▼

The workflow manages API key rotation and error handling through a centralized resolver and robust fallback strategies. This ensures continuous automated media processing without interruption.