skills.rest
IoT-VN
IoT-VNCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

ai-multimodal

Process media and documents with Gemini API for analysis, transcription, and generation.

Updated Feb 11, 2026
Search Tags:#document processing#ai#multimodal#gemini#video generation#image analysis
One-click install
npx skills add https://github.com/IoT-VN/tuya-energy-dashboard --skill ai-multimodal-iot-vn
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-multimodal
Source: https://github.com/IoT-VN/tuya-energy-dashboard/tree/main/.opencode/skills/ai-multimodal
Command: npx skills add https://github.com/IoT-VN/tuya-energy-dashboard --skill ai-multimodal-iot-vn

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill streamlines complex media and document processing tasks by leveraging advanced AI models, eliminating the need for specialized tools and manual workflows.

Core Features & Use Cases

  • Multimodal Analysis: Analyze images, audio, and video for insights, transcription, and data extraction.
  • Content Generation: Create images and videos from text prompts.
  • Document Conversion: Convert PDFs and other documents into structured Markdown.
  • Use Case: Automatically transcribe a meeting recording, summarize key discussion points, extract action items, and generate a follow-up image for a presentation slide.

Quick Start

Use the ai-multimodal skill to analyze the attached image 'product-shot.png' and describe its key features.

Frequently Asked Questions about ai-multimodal

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

FAQPage Schema
How do I transcribe audio and extract action items from a meeting recording?▼

To transcribe audio and extract action items, multimodal analysis processes the meeting recording using the Gemini API to generate text transcription, summarize key discussion points, and identify follow-up tasks automatically.

Can I convert a PDF document into structured Markdown?▼

Yes, you can convert PDF documents into structured Markdown. The Skill processes PDF files using pypdf to extract content and formats the extracted text into Markdown for structured documentation.

How do I generate images and videos from text prompts?▼

Generating images and videos from text prompts utilizes integrated Imagen 4 for image creation and Veo models for video generation, while Lyria handles music generation to produce multimedia content.

What is the best way to analyze an image for object detection and OCR?▼

The best way to perform object detection and OCR on an image is through multimodal analysis using the Gemini API and Pillow, which extracts visual data and text directly from the provided image formats.

Does this multimodal processing work with Python document dependencies?▼

Yes, multimodal processing works with Python document dependencies including python-docx, pypdf, and docx2pdf, enabling seamless document conversion and extraction within Python environments.

Related Skills

Explore More Content & Communication Skills→
nguyenvanlinh1902nguyenvanlinh1902

ai-multimodal

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

Community
Advanced
mirmir

google-docs-sheets

Export Google Docs and Sheets content as Markdown.

Community
Advanced
LogauaEngstromLogauaEngstrom
18

pdf

Extract text and tables from PDFs using Python libraries.

Community
Advanced
ThedouglerThedougler

multimodal-models

Run CLIP, Whisper, and Stable Diffusion models for multimodal AI tasks.

Community
Advanced