Gemini Video Understanding Skill

gemini-video-understanding

Analyze videos using Google's Gemini API - describe content, answer questions, transcribe audio with visual descriptions, reference timestamps, clip videos, and process YouTube URLs. Supports 9 video formats, multiple models (Gemini 2.5/2.0), and context windows up to 2M tokens (6 hours of video).

mattnigh/skills_collection·0installs24stars

SKILL.md

Full skill instructions

Gemini Video Understanding Skill

This skill enables comprehensive video analysis using Google's Gemini API, including video summarization, question answering, transcription, timestamp references, and more.

Capabilities

Video Summarization: Create concise summaries of video content
Question Answering: Answer specific questions about video content
Transcription: Transcribe audio with visual descriptions and timestamps
Timestamp References: Query specific moments in videos (MM:SS format)
Video Clipping: Process specific segments using start/end offsets
Multiple Videos: Compare and analyze up to 10 videos (Gemini 2.5+)
YouTube Support: Analyze YouTube videos directly (preview feature)
Custom Frame Rate: Adjust FPS sampling for different video types

Supported Formats

MP4, MPEG, MOV, AVI, FLV, MPG, WebM, WMV, 3GPP

Models Available

Gemini 2.5 Series:

gemini-2.5-pro - Best quality, 1M context
gemini-2.5-flash - Balanced quality/speed, 1M context
gemini-2.5-flash-preview-09-2025 - Preview features, 1M context

Gemini 2.0 Series:

gemini-2.0-flash - Fast processing
gemini-2.0-flash-lite - Lightweight option

Context Windows:

2M token models: ~2 hours (default) or ~6 hours (low-res)
1M token models: ~1 hour (default) or ~3 hours (low-res)

API Key Configuration

The skill checks for GEMINI_API_KEY in this order:

Process environment: process.env.GEMINI_API_KEY or $GEMINI_API_KEY
Skill directory: .claude/skills/gemini-video-understanding/.env
Project root: .env file in project root

To set up:

# Option 1: Environment variable (recommended)
export GEMINI_API_KEY="your-api-key-here"

# Option 2: Skill directory .env file
echo "GEMINI_API_KEY=your-api-key-here" > .claude/skills/gemini-video-understanding/.env

# Option 3: Project root .env file
echo "GEMINI_API_KEY=your-api-key-here" > .env

Get your API key at: https://aistudio.google.com/apikey

Usage Instructions

When to Use This Skill

Use this skill when the user asks to:

Analyze, summarize, or describe video content
Answer questions about videos
Transcribe video audio with visual context
Extract information from specific timestamps
Compare multiple videos
Process YouTube video content
Create quizzes or educational content from videos

Basic Video Analysis

For video files:

python .claude/skills/gemini-video-understanding/scripts/analyze_video.py \
  --video-path "/path/to/video.mp4" \
  --prompt "Summarize this video in 3 key points"

For YouTube URLs:

python .claude/skills/gemini-video-understanding/scripts/analyze_video.py \
  --youtube-url "https://www.youtube.com/watch?v=VIDEO_ID" \
  --prompt "What are the main topics discussed?"

Advanced Features

Video Clipping (specific time range):

python .claude/skills/gemini-video-understanding/scripts/analyze_video.py \
  --video-path "/path/to/video.mp4" \
  --prompt "Summarize this segment" \
  --start-offset "40s" \
  --end-offset "80s"

Custom Frame Rate:

python .claude/skills/gemini-video-understanding/scripts/analyze_video.py \
  --video-path "/path/to/video.mp4" \
  --prompt "Analyze the rapid movements" \
  --fps 5

Transcription with Timestamps:

python .claude/skills/gemini-video-understanding/scripts/analyze_video.py \
  --video-path "/path/to/video.mp4" \
  --prompt "Transcribe the audio with timestamps and visual descriptions"

Multiple Videos (Gemini 2.5+ only):

python .claude/skills/gemini-video-understanding/scripts/analyze_video.py \
  --video-paths "/path/video1.mp4" "/path/video2.mp4" \
  --prompt "Compare these two videos and highlight the differences"

Model Selection:

python .claude/skills/gemini-video-understanding/scripts/analyze_video.py \
  --video-path "/path/to/video.mp4" \
  --prompt "Detailed analysis" \
  --model "gemini-2.5-pro"

Script Parameters

Required (one of):
  --video-path PATH           Path to local video file
  --youtube-url URL           YouTube video URL
  --video-paths PATH [PATH..] Multiple video paths (Gemini 2.5+)

Required:
  --prompt TEXT              Analysis prompt/question

Optional:
  --model NAME               Model to use (default: gemini-2.5-flash)
  --start-offset TIME        Video clip start (e.g., "40s", "1m30s")
  --end-offset TIME          Video clip end (e.g., "80s", "2m")
  --fps NUMBER               Frame sampling rate (default: 1)
  --output-file PATH         Save response to file
  --verbose                  Show detailed processing info

Common Use Cases

1. Video Summarization

Prompt: "Summarize this video in 3 key points with timestamps"

2. Educational Content

Prompt: "Create a quiz with 5 questions and answer key based on this video"

3. Timestamp-Specific Questions

Prompt: "What happens at 01:15 and how does it relate to the topic at 02:30?"

4. Transcription

Prompt: "Transcribe the audio from this video with timestamps for salient events and visual descriptions"

5. Content Comparison

Prompt: "Compare these two product demo videos. Which one explains the features more clearly?"

6. Action Detection

Prompt: "List all the actions performed in this tutorial video with timestamps"

Rate Limits & Quotas

Free Tier (per model):

10-15 RPM (requests per minute)
1M-4M TPM (tokens per minute)
1,500 RPD (requests per day)

YouTube Limitations:

Free tier: 8 hours of YouTube video per day
Paid tier: No length-based limits
Public videos only (no private/unlisted)

Storage (Files API):

20GB per project
2GB per file
48-hour retention period

Token Calculation

Video tokens depend on resolution:

Default resolution: ~300 tokens per second of video
Low resolution: ~100 tokens per second of video

Example: A 10-minute video = 600 seconds × 300 tokens = ~180,000 tokens

Error Handling

Common errors and solutions:

Error	Cause	Solution
400 Bad Request	Invalid video format or corrupt file	Check file format and integrity
403 Forbidden	Invalid/missing API key	Verify GEMINI_API_KEY configuration
404 Not Found	File URI not found	Ensure file is uploaded and active
429 Too Many Requests	Rate limit exceeded	Implement backoff, upgrade to paid tier
500 Internal Error	Server-side issue	Retry with exponential backoff

Best Practices

Use Files API for videos >20MB - More reliable than inline data
Wait for file processing - Poll until state is ACTIVE before analysis
Optimize FPS - Use lower FPS for static content to save tokens
Clip long videos - Process specific segments instead of entire video
Cache context - Reuse uploaded files for multiple queries
Batch processing - Process multiple short videos in one request (2.5+)
Specific prompts - Be precise about what you want to extract

Implementation Notes

For Claude Code:

When a user requests video analysis:

Check API key availability first using the helper script
Determine video source: local file, YouTube URL, or multiple videos
Select appropriate model based on requirements (default: gemini-2.5-flash)
Run the analysis script with proper parameters
Parse and present results to the user clearly
Handle errors gracefully with helpful suggestions

Files API Workflow:

For videos >20MB or reusable content:

Upload video using Files API (script handles this automatically)
Wait for ACTIVE state (polling included in script)
Use file URI for analysis
Files auto-delete after 48 hours

Inline Data Workflow:

For videos <20MB:

Read video file as bytes
Base64 encode for API
Send in generateContent request
Single-use, no upload needed

Example Workflows

Workflow 1: YouTube Video Summary

# User: "Analyze this YouTube tutorial video"
python .claude/skills/gemini-video-understanding/scripts/analyze_video.py \
  --youtube-url "https://www.youtube.com/watch?v=abc123" \
  --prompt "Create a structured summary with: 1) Main topics, 2) Key takeaways, 3) Recommended audience"

Workflow 2: Interview Transcription

# User: "Transcribe this interview with timestamps"
python .claude/skills/gemini-video-understanding/scripts/analyze_video.py \
  --video-path "interview.mp4" \
  --prompt "Transcribe this interview with speaker labels, timestamps, and visual descriptions of gestures or slides shown"

Workflow 3: Product Comparison

# User: "Compare these two product demo videos"
python .claude/skills/gemini-video-understanding/scripts/analyze_video.py \
  --video-paths "demo1.mp4" "demo2.mp4" \
  --model "gemini-2.5-pro" \
  --prompt "Compare these product demos on: features shown, presentation quality, clarity of explanation, and overall effectiveness"

Troubleshooting

API Key Not Found:

# Check API key detection
python .claude/skills/gemini-video-understanding/scripts/check_api_key.py

Video Too Large:

Error: Request size exceeds 20MB
Solution: Script automatically uses Files API for large videos

Processing Timeout:

Error: File not reaching ACTIVE state
Solution: Check video integrity, try smaller file, or different format

Rate Limit Errors:

Error: 429 Too Many Requests
Solution: Wait before retry, or upgrade to paid tier

Additional Resources

API Documentation: https://ai.google.dev/gemini-api/docs/video-understanding
Files API Guide: https://ai.google.dev/gemini-api/docs/vision#uploading-files
Rate Limits: https://ai.google.dev/gemini-api/docs/rate-limits
Pricing: https://ai.google.dev/pricing
Get API Key: https://aistudio.google.com/apikey

Version History

1.0.0 (2025-10-26): Initial release with full video understanding capabilities

Install skill

Copy and run in your terminal

npx -y skills add https://github.com/mattnigh/skills_collection --skill levanminhduc__LuongHoaThoNew__claude__skills__gemini-video-understanding__SKILL.md

View on GitHub

collection/levanminhduc__LuongHoaThoNew__claude__skills__gemini-video-understanding__SKILL.md

frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications, OR when they provide screenshots/images/designs to replicate or draw inspiration from. For screenshot inputs, extracts design guide...
1 installs
animation-motion
CSS animations, transitions, and scroll-driven effects with accessibility (prefers-reduced-motion). Use when adding motion, hover effects, loading states, or scroll-based animations.
1 installs
laravel
Laravel v12 - The PHP Framework For Web Artisans
1 installs
gemini-document-processing
Guide for implementing Google Gemini API document processing - analyze PDFs with native vision to extract text, images, diagrams, charts, and tables. Use when processing documents, extracting structured data, summarizing PDFs, answering questions about document content, or converting documents to...
0 installs

More skills from mattnigh

mattnigh/skills_collection

spring-framework-patterns

Comprehensive Spring Framework and Spring Boot best practices including dependency injection patterns, bean lifecycle and scopes, REST API development, Spring Data JPA, service layer design, Spring Security, testing strategies, caching, AOP, async processing, error handling, and common anti-patte...

24 0

View

mattnigh/skills_collection

When Stuck - Problem-Solving Dispatch

Dispatch to the right problem-solving technique based on how you're stuck

24 0

View

mattnigh/skills_collection

.claude/skills/type-safety-patterns/SKILL.md

TypeScript厳格モードによる型安全性設計を専門とするスキル。 📖 参照書籍: - 『Effective TypeScript』（Dan Vanderkam）: 型設計 📚 リソース参照: - `resources/Level1_basics.md`: レベル1の基礎ガイド - `resources/Level2_intermediate.md`: レベル2の実務ガイド - `resources/Level3_advanced.md`: レベル3の応用ガイド - `resources/Level4_expert.md`: レベル4の専門ガイド - `resources/di...

24 0

View

mattnigh/skills_collection

deploying-cloud-k8s

Deploys applications to cloud Kubernetes (AKS/GKE/DOKS) with CI/CD pipelines. Use when deploying to production, setting up GitHub Actions, troubleshooting deployments. Covers build-time vs runtime vars, architecture matching, and battle-tested debugging.

24 0

View

mattnigh/skills_collection

moai-alfred-agent-guide

19-agent team structure, decision trees for agent selection, Haiku vs Sonnet model selection, and agent collaboration principles. Use when deciding which sub-agent to invoke, understanding team responsibilities, or learning multi-agent orchestration.

24 0

View

mattnigh/skills_collection

mermaid-diagram-generator

Converts architecture descriptions, module specs, or workflow docs into Mermaid diagrams. Use when visualizing brick module relationships, workflows (DDD, investigation), or system architecture. Supports: flowcharts, sequence diagrams, class diagrams, state machines, entity relationship diagrams,...

24 0

View

mattnigh/skills_collection

pre-flight-check

INVOKE FIRST before any code work. Validates git workflow (branch, issue, worklog) and checks approach. Use at START of every task and END before completing. Prevents skipped steps.

24 0

View

mattnigh/skills_collection

browser-dev-tools

This skill should be used when working with browser-rendered artifacts (i.e. Bun, React/React Native) to proactively validate that development work on localhost is being built appropriately and to support debugging browser-rendered content. Use this skill after making frontend changes to verify t...

24 0

View

mattnigh/skills_collection

lead-dev

Lead Développeur - Coordination technique opérationnelle, code review, mentoring et livraison. Pair de web-dev-process au niveau OPÉRATIONS.

24 0

View

mattnigh/skills_collection

worker-monitor

Monitor Docker workers, RQ queue health, and auto-scale workers (max 4). Use when: checking job progress, monitoring queue depth, scaling workers up/down, diagnosing slow processing, or waiting for jobs to complete. Referenced by data-quality skill during reprocessing.

24 0

View

mattnigh/skills_collection

quality-advisor

Proactive quality guidance system that monitors artifact creation and provides real-time feedback on documentation quality

24 0

View

mattnigh/skills_collection

bump-version

This skill should be used when the user wants to bump the version number in the workspace. It updates versions across all pyproject.toml files (root, tde, and tda packages) and the CHANGELOG.md to keep them synchronized.

24 0

View