Analyze video files via Google Gemini to generate structured Markdown reports.
npx skills add https://github.com/mikefutia/claude-vision --skill video-analyzer-mikefutia
Please help me install this Agent Skill. Skill: video-analyzer Source: https://github.com/mikefutia/claude-vision/tree/main Command: npx skills add https://github.com/mikefutia/claude-vision --skill video-analyzer-mikefutia
Analyzes video content by routing a video file through Google's Gemini API to produce a structured markdown report that covers a top-level summary, scene-by-scene breakdown with timestamps, audio transcript (or notes on silence), visual details, and key moments.
Analyze a video file with Gemini to generate the full markdown report.
High-intent search queries and answers about installing and using this skill.
To generate a scene-by-scene breakdown with timestamps from a video file, route the file through the Gemini API to produce a structured Markdown report detailing visual elements, transcripts, and key moments.
Yes, you can use Gemini to create a transcript and visual analysis for ad teardowns by processing the video file to extract beat-by-beat breakdowns, audio transcripts, and visual details into a structured Markdown format.
You can analyze common video formats to convert screen recordings into actionable guides. The Skill accepts standard video files, uploading them inline if small or via the Files API for larger files.
Yes, you need a GEMINI_API_KEY to extract meeting recaps and visual notes from videos, as the Skill routes the video content through Google's Gemini API to generate the structured Markdown report.
Video analysis handles silent audio tracks by including notes on the silence within the generated Markdown report, ensuring the audio transcript section remains accurate even without spoken dialogue.
The best way to summarize decisions and visuals from recorded demos is processing the file through Gemini to output a complete Markdown report covering top-level summaries, scene-by-scene breakdowns, and visual details.
HsnSaboorProcess and generate audio, image, video, and document content via the Google Gemini API.
Adityaraj0421Convert storyboard text into structured AI video prompts with shot lists and timelines.
michalparkolaDownload YouTube video transcripts via yt-dlp with Whisper fallback.
zeroix07Analyze video content to extract scenes, actions, and temporal events.
