Claude Real Video

by HUANGCHIHHUNGLeo

Claude Real Video is an AI Engineering skill for Claude Code, published by HUANGCHIHHUNGLeo in claude-real-video.

2K stars175 forkson HUANGCHIHHUNGLeo/claude-real-videoAdded 2026/08/18+1% in starsRepository updated 2026/08/18

View source on GitHub Download repo ZIP

claudeclaude-codecliffmpegkeyframe-extractionllmmultimodalpythonscene-detectiontranscriptionvideo-analysiswhisper

Install in seconds

Install Claude Real Video

Copy Claude Real Video into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/HUANGCHIHHUNGLeo/claude-real-video/tree/master/capafy-staging/.claude/skills/claude-real-video ~/.claude/skills/claude-real-video

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/HUANGCHIHHUNGLeo/claude-real-video.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: capafy-staging/.claude/skills/claude-real-video/SKILL.md in HUANGCHIHHUNGLeo/claude-real-video
Installs to: ~/.claude/skills/claude-real-video
Collection: One of 3 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Claude Real Video does

Claude Real Video extracts scene-aware keyframes and the transcript from a video URL or local file so an agent can summarize, analyze, or answer questions about it. Use it when a video needs to be watched but the model cannot ingest video directly.

Claude Real Video is cataloged under AI Engineering on DirSkills. Claude Real Video comes from a repository tagged claude, claude-code, cli, ffmpeg and keyframe-extraction.

Documentation

README

Excerpt

claude-real-video — let Claude actually watch a video

When to use

The user gives you a video (URL or file path) and asks what's in it, to summarize it, to analyze its structure, or to answer questions about it.

Requirements

pip install "claude-real-video[whisper]" (installs the crv CLI; needs Python 3.10+ and ffmpeg)
The [whisper] extra is required for speech-to-text — pip never installs extras on its own. The first transcription then downloads a whisper base model (~139 MB).

Steps

Run the extractor (add --grid to cut image count ~9x — recommended):
```
crv "<url-or-path>" -o crv-out --grid --why "<what the user wants to know>"
```
For long videos cap the frames: --max-frames 60.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Claude Real Video

What else does HUANGCHIHHUNGLeo publish alongside Claude Real Video?
Claude Real Video is one of 3 skills that DirSkills catalogs from HUANGCHIHHUNGLeo/claude-real-video, the repository it ships in. Its siblings there include Claude Real Video and Real Video. Each one is a separate skill with its own page in this directory, installs the same way Claude Real Video does, and is maintained by HUANGCHIHHUNGLeo in that same repository. The rest of the collection is listed on the HUANGCHIHHUNGLeo/claude-real-video page.
How does Claude Real Video compare to other AI Engineering skills?
Claude Real Video ranks #868 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Claude Real Video against them. Open each page to compare what they document and how they install.