a6-gemini-video-analyzer

Name: a6-gemini-video-analyzer
Author: berabuddies

555stars59forks

How to install a6-gemini-video-analyzer?

berabuddies/semia/a6-gemini-video-analyzer

$npx -y skills add berabuddies/Semia --skill a6-gemini-video-analyzer

Installs into the current project.

Summary

Native video analysis using Google Gemini API. Upload and analyze video files — describe scenes, extract text/UI, answer questions about content, transcribe speech, identify objects and actions. Use when: (1) User sends a video file and wants it analyzed, (2) Video summarization

Files · 1

View on GitHub

SKILL.md

1	# Gemini Video Analyzer
2
3	Analyze videos natively using Google Gemini's multimodal API. No frame extraction needed — Gemini processes video at 1 FPS with full motion, audio, and visual understanding.
4
5	## Quick Start
6
7	```bash
8	# Analyze a video with default prompt (full description)
9	GOOGLE_AI_API_KEY=$GOOGLE_AI_API_KEY python3 {baseDir}/scripts/analyze.py /path/to/video.mp4
10
11	# Ask a specific question
12	GOOGLE_AI_API_KEY=$GOOGLE_AI_API_KEY python3 {baseDir}/scripts/analyze.py /path/to/video.mp4 "What text is visible on screen?"
13
14	# Manage uploaded files
15	GOOGLE_AI_API_KEY=$GOOGLE_AI_API_KEY python3 {baseDir}/scripts/manage_files.py list
16	GOOGLE_AI_API_KEY=$GOOGLE_AI_API_KEY python3 {baseDir}/scripts/manage_files.py cleanup
17	```
18
19	## Supported Formats
20
21	MP4, AVI, MOV, MKV, WebM, FLV, MPEG, MPG, WMV, 3GP — up to 2GB per file.
22
23	## How It Works
24
25	1. Video uploads to Google's Files API (temporary, auto-deletes after 48h)
26	2. Gemini processes at 1 frame/sec — understands motion, transitions, audio context
27	3. Model generates response based on your prompt
28	4. Way better than frame extraction for understanding temporal content
29
30	## Use Cases
31
32	\| Task \| Example Prompt \|
33	\|------\|---------------\|
34	\| General description \| (default — no prompt needed) \|
35	\| UI/text extraction \| `"What text and UI elements are visible?"` \|
36	\| Tutorial summary \| `"Summarize the steps shown in this tutorial"` \|
37	\| Bug report from video \| `"Describe what went wrong in this screen recording"` \|
38	\| Meeting notes \| `"Summarize the key points discussed"` \|
39	\| Content comparison \| Upload 2 videos, ask for differences \|
40
41	## Configuration
42
43	Set `GOOGLE_AI_API_KEY` in your environment or `.env` file. Get a free key at [aistudio.google.com](https://aistudio.google.com/apikey).
44
45	Default model: `gemini-2.5-flash` (fast, cheap, excellent vision). Override with `--model gemini-2.5-pro` for complex analysis.
46
47	## API Reference
48
49	See [references/gemini-files-api.md](references/gemini-files-api.md) for file upload limits, processing details, and advanced options.

People who liked this also viewed

6 picks

Type

a6-gemini-video-analyzer

555stars59forks

View on GitHub

How to install a6-gemini-video-analyzer?

berabuddies/semia/a6-gemini-video-analyzer

$npx -y skills add berabuddies/Semia --skill a6-gemini-video-analyzer

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Gemini Video Analyzer
2
3	Analyze videos natively using Google Gemini's multimodal API. No frame extraction needed — Gemini processes video at 1 FPS with full motion, audio, and visual understanding.
4
5	## Quick Start
6
7	```bash
8	# Analyze a video with default prompt (full description)
9	GOOGLE_AI_API_KEY=$GOOGLE_AI_API_KEY python3 {baseDir}/scripts/analyze.py /path/to/video.mp4
10
11	# Ask a specific question
12	GOOGLE_AI_API_KEY=$GOOGLE_AI_API_KEY python3 {baseDir}/scripts/analyze.py /path/to/video.mp4 "What text is visible on screen?"
13
14	# Manage uploaded files
15	GOOGLE_AI_API_KEY=$GOOGLE_AI_API_KEY python3 {baseDir}/scripts/manage_files.py list
16	GOOGLE_AI_API_KEY=$GOOGLE_AI_API_KEY python3 {baseDir}/scripts/manage_files.py cleanup
17	```
18
19	## Supported Formats
20
21	MP4, AVI, MOV, MKV, WebM, FLV, MPEG, MPG, WMV, 3GP — up to 2GB per file.
22
23	## How It Works
24
25	1. Video uploads to Google's Files API (temporary, auto-deletes after 48h)
26	2. Gemini processes at 1 frame/sec — understands motion, transitions, audio context
27	3. Model generates response based on your prompt
28	4. Way better than frame extraction for understanding temporal content
29
30	## Use Cases
31
32	\| Task \| Example Prompt \|
33	\|------\|---------------\|
34	\| General description \| (default — no prompt needed) \|
35	\| UI/text extraction \| `"What text and UI elements are visible?"` \|
36	\| Tutorial summary \| `"Summarize the steps shown in this tutorial"` \|
37	\| Bug report from video \| `"Describe what went wrong in this screen recording"` \|
38	\| Meeting notes \| `"Summarize the key points discussed"` \|
39	\| Content comparison \| Upload 2 videos, ask for differences \|
40
41	## Configuration
42
43	Set `GOOGLE_AI_API_KEY` in your environment or `.env` file. Get a free key at [aistudio.google.com](https://aistudio.google.com/apikey).
44
45	Default model: `gemini-2.5-flash` (fast, cheap, excellent vision). Override with `--model gemini-2.5-pro` for complex analysis.
46
47	## API Reference
48
49	See [references/gemini-files-api.md](references/gemini-files-api.md) for file upload limits, processing details, and advanced options.

People who liked this also viewed

6 picks

Type