# Claude Real Video

> Watch a video for the user. Use when the user shares a video URL (YouTube etc.) or local video file and wants it summarized, analyzed, or discussed — Claude can't ingest video directly, so this skill extracts scene-aware keyframes + transcript first, then reads those.

- Skill: `huangchihhungleo/claude-real-video-2` (Agent Skill)
- Install (CLI): `npx skillmds@latest add huangchihhungleo/claude-real-video-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/huangchihhungleo/claude-real-video-2/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: huangchihhungleo (https://skillmd.com/u/huangchihhungleo)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/huangchihhungleo/claude-real-video-2

---


# 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` (installs the `crv` CLI; needs Python 3.10+ and ffmpeg)
- First transcription downloads a faster-whisper model automatically

## Steps

1. Run the extractor (add `--grid` to 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`.

2. Read `crv-out/MANIFEST.txt` first — it lists every frame with timestamps and includes the transcript.

3. Read the contact sheets in `crv-out/grids/` (each is a 3×3 sequence of consecutive keyframes, in chronological order). Only read individual `crv-out/frames/*.jpg` when you need a close-up of one moment.

4. Answer the user's question, citing timestamps from the manifest.

## Notes

- Everything runs locally; nothing is uploaded by the tool itself.
- If the video has no speech or transcription is unnecessary, add `--no-transcribe` (much faster).
- `--kb <dir>` saves a digest into a knowledge-base folder if the user wants to keep notes.