Can I ask specific questions about a video's content?

Yes, you can provide a custom prompt to ask about specific events, timestamps, or information contained within the video.

Does this skill require an external API key?

Yes, it requires a MAX_API_KEY environment variable to be configured, which is typically handled via your Max settings.

Is speaker identification available for audio files?

Yes, the skill can identify different speakers in an audio recording and organize the transcription accordingly.

What media formats does this skill support?

It supports common image formats (JPG, PNG, GIF, WebP), video formats (MP4, MOV, WebM), and audio formats (MP3, WAV, FLAC, M4A), as well as direct YouTube URLs.

What are the file size limits for media analysis?

Images are limited to 20MB, while video and audio files have a maximum size limit of 100MB.

Multimodal Media Analysis

Name: Multimodal Media Analysis
Author: InfQuest

byInfQuest

0•

数据科学与机器学习

Analyzes and extracts deep insights from images, videos, and audio files using advanced AI models.

The Media Understand skill integrates Gemini 2.5 Flash into your workflow to process and interpret various multimedia formats. It allows users to perform complex tasks such as Optical Character Recognition (OCR), video summarization (including YouTube URLs), and detailed audio transcription. Whether you need to explain a chart in a screenshot, identify speakers in a meeting recording, or summarize a technical video tutorial, this skill provides a powerful bridge between raw media and actionable text-based data.

主要功能

010 GitHub stars

02Supports comprehensive image, video, and audio file formats up to 100MB.

03High-fidelity audio transcription with speaker identification and diarization.

04Natural language querying for specific details within any media asset.

05Advanced OCR capabilities to extract text from screenshots and documents.

06Processes YouTube URLs directly for video summarization and timestamped analysis.

使用场景

01Summarizing long-form video tutorials or podcasts to capture key takeaways quickly.

02Extracting technical data and trends from charts or screenshots for documentation.

03Automating the transcription and organization of meeting recordings or interviews.

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add infquest/vibe-ops-plugin media-understand

For use in Claude.ai and ChatGPT

Download Skill