meow:multimodal

Analyze and generate images, videos, audio, and documents with Gemini.

14|2|Updated Mar 25, 2026
One-click install
npx skills add https://github.com/ngocsangyem/MeowKit --skill meow-multimodal
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: meow:multimodal
Source: https://github.com/ngocsangyem/MeowKit/tree/main/.claude/skills/meow%3Amultimodal
Command: npx skills add https://github.com/ngocsangyem/MeowKit --skill meow-multimodal

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Gemini-based multimodal analysis and generation is integrated into MeowKit to handle images, videos, audio, and documents, enabling automated understanding, transcription, OCR, and media creation where Claude Code would otherwise struggle with binary content.

Core Features & Use Cases

  • Multimodal analysis: analyze, describe, OCR, and extract information from images, videos, audio, PDFs, and other documents.
  • Transcription & OCR: automatic transcription of audio/video and OCR for images and scanned documents.
  • Data extraction: extract structured content from documents (tables, text) and produce Markdown or structured outputs.
  • Media generation: generate images (Imagen) and videos (Veo) from prompts for design, mockups, or visual storytelling.
  • Auto-activation: activates automatically on file references or prompts like "analyze", "describe", "transcribe", "extract from" or "generate image/video".
  • Security & env: requires GEMINI_API_KEY and runs with a MeowKit security anchor system to bound outputs within policy.

Quick Start

Provide a media file path and a task to run multimodal analysis or generation.

Frequently Asked Questions about meow:multimodal

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

FAQPage Schema
How do I extract text from scanned PDFs and images using multimodal AI?

You can transcribe audio and video files by passing the media path to Gemini for multimodal transcription. Large files are supported via the File API to ensure reliable audio and video processing.

How do I transcribe audio and video files with Gemini?

Yes, you can generate images and videos from text prompts by utilizing Imagen and Veo models. This media generation capability supports design mockups and visual storytelling directly from descriptive prompts.

Can I generate images and videos from text prompts?

You need a valid GEMINI_API_KEY configured in your environment, optionally loaded via a .env file. The skill uses this key to authenticate Gemini, Imagen, and Veo API requests for analysis and generation.

Do I need a specific API key to run multimodal analysis?

You need a valid GEMINI_API_KEY configured in your environment, optionally loaded via a .env file. The skill uses this key to authenticate Gemini, Imagen, and Veo API requests for analysis and generation.

What is the best way to analyze binary media files when my main AI struggles with them?

To extract structured data from documents, provide a media file path and an extraction task. Gemini analyzes the document to pull tables and text, producing structured Markdown outputs.

How do I extract structured data from PDFs into Markdown?

To extract structured data from documents, provide a media file path and an extraction task. Gemini analyzes the document to pull tables and text, producing structured Markdown outputs.