skills.rest
Thanh-apero
Thanh-aperoCOMMUNITY
Explore all skills by this author →
GitHub

ck:ai-multimodal

Analyze images, generate videos, transcribe audio, and convert documents via Gemini API.

1|1|Updated Jan 15, 2026
Search Tags:#document conversion#media processing#audio processing#video generation#image analysis
One-click install
npx skills add https://github.com/Thanh-apero/apero-kit-cli --skill ck-ai-multimodal-thanh-apero
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ck:ai-multimodal
Source: https://github.com/Thanh-apero/apero-kit-cli/tree/main/.claude/skills/ai-multimodal
Command: npx skills add https://github.com/Thanh-apero/apero-kit-cli --skill ck-ai-multimodal-thanh-apero

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides a comprehensive suite of AI capabilities for analyzing and generating images, videos, audio, and documents, streamlining tasks like image analysis, video creation, audio transcription, and document conversion.

Core Features & Use Cases

  • Image Analysis: Analyze images, extract text, and identify objects using Gemini API.
  • Video Generation: Create videos from text descriptions and reference images.
  • Audio Processing: Transcribe audio, generate speech, and analyze non-speech audio.
  • Document Conversion: Convert PDFs, images, and office documents to Markdown.
  • Use Case: Imagine you need to analyze a set of images for specific objects, generate a video from a script, transcribe a meeting, or convert a PDF to Markdown for easier reading. This Skill can handle all these tasks.

Quick Start

Use the ai-multimodal skill to analyze an image using the 'analyze' task. For example, to analyze the image 'example.jpg', run the following command:

python scripts/gemini_batch_process.py --files example.jpg --task analyze

Frequently Asked Questions about ck:ai-multimodal

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

FAQPage Schema
How do I convert PDFs and office documents to Markdown?▼

To convert PDFs and office documents to Markdown, this Skill processes the input files via the Gemini API to extract text and formatting. It outputs clean Markdown suitable for easier reading and downstream analytical workflows.

Can I generate a video from text descriptions and reference images?▼

Yes, you can generate a video from text descriptions and reference images using this Skill's media processing capabilities. It uses the Gemini API to synthesize visual content based on your provided script and image inputs.

How do I extract text and identify objects in image analysis?▼

Image analysis extracts text and identifies objects by passing the image to the Gemini API. You run the batch processing script with the analyze task, and the AI returns detected objects and extracted text directly from the visual data.

Do I need a Google GenAI API key to transcribe audio?▼

Yes, you need a Google GenAI API key to transcribe audio because this Skill relies on the google-genai library for API interactions. You must configure it in your environment using python-dotenv before processing audio files.

What Python libraries are required for media processing?▼

The required Python libraries for media processing are google-genai, python-dotenv, pillow, and requests. These dependencies handle API interactions, environment configuration, image manipulation, and HTTP requests respectively.

Does this tool support analyzing non-speech audio files?▼

Yes, this tool supports analyzing non-speech audio files. Beyond standard speech transcription, the audio processing capabilities leverage the Gemini API to interpret and analyze various audio signals for creative workflows.

Related Skills

Explore More Design & Creative Skills→
Svenja-devSvenja-dev
38

gemini-image-gen

Generate branded images from prompts using Google's Gemini API.

Community
Intermediate
dasgltddasgltd
2

pdf-markitdown

Convert PDF documents into structured Markdown text using MarkItDown.

Community
Basic
gvkhoslagvkhosla
49

gemini-imagegen

Generate and edit images via the Gemini API with text prompts.

Community
Intermediate
Hoang130203Hoang130203

ai-multimodal

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

Community
Advanced