skills.rest
dthuy62
dthuy62COMMUNITY
Explore all skills by this author →
GitHub

ck:ai-multimodal

Analyze media files and generate structured outputs via Gemini and MiniMax APIs.

Updated May 10, 2026
Search Tags:#multimodal#transcription#gemini#image-generation#video-analysis#minimax#document-conversion
One-click install
npx skills add https://github.com/dthuy62/kollet-app --skill ck-ai-multimodal-dthuy62
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ck:ai-multimodal
Source: https://github.com/dthuy62/kollet-app/tree/main/.opencode/skills/ai-multimodal
Command: npx skills add https://github.com/dthuy62/kollet-app --skill ck-ai-multimodal-dthuy62

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill removes the friction of manually inspecting media files by turning images, audio, video, and documents into searchable insights, transcripts, and generated assets.

Core Features & Use Cases

  • Multimodal Analysis: Inspect images for OCR, classification, object detection, scene understanding, and document extraction.
  • Audio and Video Workflows: Transcribe speech, summarize videos, detect scenes, and analyze long recordings with timestamps and speaker context.
  • Generation Workflows: Create images, videos, speech, and music with Gemini and MiniMax models for creative and production use cases.
  • Document Conversion: Convert PDFs, Office files, and web content into clean Markdown for knowledge capture and reuse.
  • Use Case: A product team can upload screenshots, meeting audio, and demo videos, then extract text, summarize feedback, and generate polished marketing visuals from the same workflow.

Quick Start

Ask the skill to analyze the attached media file or generate a new image, video, speech, music, or document summary using the appropriate Gemini or MiniMax model.

Frequently Asked Questions about ck:ai-multimodal

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

FAQPage Schema
How do I transcribe audio and analyze video files in a single workflow?▼

Audio transcription and video analysis are handled by turning media files into searchable insights, transcripts, and scene summaries with timestamps using Python helper scripts. You can process speech, detect scenes, and analyze long recordings within a unified workflow.

Can I generate images, videos, and music using Gemini and MiniMax models?▼

Yes, you can generate images, videos, speech, and music using Gemini and MiniMax models. This allows creative and production teams to create polished marketing visuals and multimedia assets directly from text prompts.

What is the best way to convert PDFs and Office documents into Markdown?▼

The best way to convert PDFs and Office files into clean Markdown is through document conversion workflows that extract text and structure for knowledge capture. This transforms web content and documents into reusable formats.

Do I need ffmpeg and Pillow to process images and optimize media files?▼

You need optional ffmpeg and Pillow support for file handling, optimization, and batch processing of media files. They enhance the core Python helper scripts for image processing and multimedia handling.

Does multimodal analysis support OCR and object detection from images?▼

Multimodal analysis supports OCR, classification, object detection, scene understanding, and document extraction from images. This removes the friction of manually inspecting media files by generating structured outputs.

What are the limitations of batch processing media without API access?▼

Without Gemini and MiniMax API access, batch processing and media generation cannot function. The Skill requires these API connections to analyze media files and generate structured outputs at scale.

Related Skills

Explore More Design & Creative Skills→
VoDaiLoczVoDaiLocz
24

ai-multimodal

Process and generate multimedia content using the Google Gemini API.

Community
Advanced
zephyrwang6zephyrwang6
333

youtube-transcript-cn

Extract YouTube subtitles and convert them into Chinese transcripts.

Community
Intermediate
jason660519jason660519

llava

Integrate LLaVA models for image-based conversations and visual question answering.

Community
Advanced
Hoang130203Hoang130203

ai-multimodal

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

Community
Advanced