claude-real-video
claude-real-video bridges Claude's text-only interface with video content by automatically extracting scene-aware keyframes and speech-to-text transcripts. Pass a video URL or file path, and the skill generates contact sheets and a transcript that Claude can then read to answer your questions, summarize the content, or perform detailed analysis. Local processing keeps your source video private.
claude-real-video extracts keyframes and transcripts from videos so Claude can analyze and summarize them.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-27
claude-real-video extracts keyframes and transcripts from videos so Claude can analyze and summarize them. claude-real-video bridges Claude's text-only interface with video content by automatically extracting scene-aware keyframes and speech-to-text transcripts. Pass a video URL or file path, and the skill generates contact sheets and a transcript that Claude can then read to answer your questions, summarize the content, or perform detailed analysis. Local processing keeps your source video private.
Use it when
- Yes, claude-real-video works with both YouTube URLs and local video files.
- claude-real-video's extracted keyframes and transcript enable you to summarize video content.
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Install
HUANGCHIHHUNGLeo/claude-real-video/claude-real-video · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I extract keyframes and transcript from video?
claude-real-video automatically extracts both scene-aware keyframes and speech-to-text transcripts from your video. Pass a video URL or local file path to the tool, and it generates a contact sheet of keyframes and a full transcript that Claude can then analyze, summarize, or answer questions about.
Can claude-real-video analyze YouTube videos and local files?
Yes, claude-real-video works with both YouTube URLs and local video files. The tool processes your source video locally, keeping it private while generating keyframes and transcripts that Claude can read and analyze for you.
What can I do with the extracted keyframes and transcript?
claude-real-video's extracted keyframes and transcript enable you to summarize video content, answer questions about what happens in the video, identify speakers and scenes, and convert video into searchable text and image artifacts—all by having Claude read the generated materials.
How does claude-real-video handle interviews and podcasts?
claude-real-video processes interviews, podcasts, and meetings by extracting transcripts with speaker identification and organizing scenes. This lets Claude analyze speaker labels, extract key discussion points, and answer detailed questions about the content.
Is my video data kept private with claude-real-video?
Yes. claude-real-video processes your source video locally, so your original video file never leaves your machine. Only the generated keyframes and transcript are passed to Claude for analysis, keeping your source content private.
Can I batch process multiple videos with claude-real-video?
claude-real-video is designed to process individual video files or URLs. For batch workflows, you can run the tool on multiple videos sequentially and have Claude analyze each transcript and keyframe set separately or compare results across videos.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
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 thecrvCLI; 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
--gridto cut image count ~9x — recommended):
bash
crv "<url-or-path>" -o crv-out --grid --why "<what the user wants to know>"
For long videos cap the frames: --max-frames 60.
Use one output folder per video (e.g. -o crv-out/<slug>). A folder that
already holds an analysis is refused; pass --overwrite to
(truncated - see the full file via the links below)
File tree — 1 file
skills/claude-real-video/SKILL.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Summarize and analyze video content by extracting keyframes and transcript”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Claude Real Video lets AI agents process videos by intelligently extracting scene-aware keyframes and audio transcripts. It uses scene-change detection and deduplication to reduce token usage—a 58-second clip yields 26 meaningful frames instead of 58, packed into contact sheets for efficient LLM consumption.
Faceswap uses HeyGen's API to replace faces in videos by applying a source image onto target video content. Submit a source face photo and target video, then poll for completion as the AI processes the swap. Works with any video format and chains with other workflows for personalized video creation.
Watch lets you analyze any video—from YouTube, local files, or other sources—by automatically pulling frames and transcripts so Claude can answer your questions about the content. It handles caption extraction, falls back to Whisper when needed, and scales frame detail to match your needs.
Fetch videos and audio directly from URLs using yt-dlp, supporting YouTube and over 1000 other platforms. Extract audio tracks, retrieve captions in multiple languages, or inspect metadata without storing files. Customize resolution, format, and output paths to fit your needs.
Watch Skill processes any video—URLs, local files, streams, recordings—by extracting frames, running OCR, and transcribing audio into a unified searchable index. Query the index directly instead of re-watching, and batch-process playlists or folders in one pass.
Grab YouTube videos with precise control over resolution and file type. Choose from quality levels ranging best to 360p, output as MP4, WebM, or MKV, or extract audio as MP3. Downloads go to your specified folder by default.
More skills playwright-recording (MIT)