skills.rest
minicoohei
minicooheiCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

video-frame-reader

Extract video keyframes and estimate token costs for Claude models.

345|12|Updated Apr 14, 2026
Search Tags:#video#keyframes#image-processing#token-cost#frame-extraction#duplication-removal
One-click install
npx skills add https://github.com/minicoohei/ai-agent-camp --skill video-frame-reader
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: video-frame-reader
Source: https://github.com/minicoohei/ai-agent-camp/tree/main/.claude/skills/video-frame-reader
Command: npx skills add https://github.com/minicoohei/ai-agent-camp --skill video-frame-reader

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires Pillow, numpy, and includes scripts (resource) components.

What problem does it solve?

Extract video keyframes from a long video or screen recording while removing duplicate frames and optimizing images for efficient downstream analysis.

Core Features & Use Cases

  • Keyframe extraction: Identify representative frames by deduplicating similar frames and resizing/compressing images.
  • Token-cost estimation: Provide upfront estimates of token usage and cost for multiple Claude models.
  • Frame analysis: Prepare keyframes for analysis and pass them to subagents based on user intent.

Quick Start

Run the keyframe extraction on a video file to generate keyframes and see the token cost.

Frequently Asked Questions about video-frame-reader

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

FAQPage Schema
How do I extract keyframes from a video while removing duplicate frames?▼

Video keyframe extraction identifies representative frames by deduplicating similar frames and resizing or compressing images for efficient downstream analysis. This process optimizes long videos or screen recordings for further processing.

Can I estimate token cost before sending extracted video keyframes to Claude models?▼

Yes, you can estimate token usage and cost upfront for multiple Claude models. The extraction process generates token-cost estimates alongside structured JSON keyframe data, providing cost insights before analysis.

Do I need ffmpeg and Python to extract keyframes and analyze video content?▼

Yes, you need ffmpeg for frame extraction and Python with Pillow and numpy for image processing. These dependencies are required to process video inputs and produce keyframe summaries with cost estimates.

What is the best way to prepare video keyframes for image processing and analysis?▼

The best way to prepare video keyframes is to extract representative frames, remove duplicates, and resize or compress them. This optimization ensures images are ready for efficient downstream analysis by subagents based on user intent.

Does video frame extraction output structured JSON data with keyframe information?▼

Yes, video frame extraction outputs a structured JSON file containing keyframe data and token cost estimates. This output provides concise keyframe summaries and cost insights for Claude models.

Related Skills

Explore More Software Engineering Skills→
519lab519lab
2

ascii-video

Convert image, video, audio, and text input into ASCII art videos.

Official
Advanced
shige1014-devshige1014-dev

video-understand

Extract frames and transcribe audio from local video files into JSON.

Community
Intermediate
Prathmesh2000Prathmesh2000
1

token-analyzer

Analyze and estimate token usage for LLM API calls.

Community
Intermediate
yokingmayokingma
35

video-frames

Extract video frames by timestamp or index using ffmpeg.

Community
Basic