Claude Real Video skill
claude-real-video
A skill that lets Claude watch a video: it pulls scene-aware, deduplicated frames and a speech transcript through whisper from a link or file
- 2,216 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Downloads and processes video on your machine
- Frames and text of the video land in the model context
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/claude-real-videoDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Downloads and processes video on your machine
- Frames and text of the video land in the model context
This is third-party code. Review the repository files before installing.
What it does
The skill gets a video from a link or file, picks frames with scene changes in mind, removes duplicates and adds a speech transcript through whisper. The agent gets a set of frames and text from which it can answer questions about the video. Installation: `pip install "claude-real-video[whisper]"`, then `npx skills add HUANGCHIHHUNGLeo/claude-real-video` installs the skill into Claude Code, Cursor, Codex, Copilot, Gemini CLI and other clients. There is also a Claude Code marketplace. Version 0.10.7 from 26.09.2026, PyPI `claude-real-video`, MIT license.
Who it is for. For people who need an agent to retell, analyze and find moments in videos: lectures, meetings, reviews.
Good fit when
- You need notes of a lecture or meeting from a recording
- You need to find the moment in a video where a screen or slide is shown
- You need one video skill for several agents
Not a fit when
- The video cannot be processed on a machine with whisper: transcription runs locally
- You need to work with live streaming video
Example request
Watch the call recording at the link, write notes by topic and say at which minute they decided to move the deadlineLimitations
The skill downloads and processes video on your machine, so disk space and time are needed, and speech transcription through whisper requires computation. Do not send through the agent videos that must not be shown to a model: frames and text land in the context. Computation and downloading depend on the video source.
How to disable. Remove the skill folder from the agent's skills directory and run pip uninstall claude-real-video.
FAQ
What does the skill do?
It gets scene-aware deduplicated frames and a speech transcript from a video by link or file.
How do I install it?
pip install "claude-real-video[whisper]" and npx skills add HUANGCHIHHUNGLeo/claude-real-video.
Which agents does it work with?
Claude Code, Cursor, Codex, Copilot, Gemini CLI and other clients through npx skills add.
Discussion
No questions or reviews yet.
Related
SkillsA video editing skill for Claude Code and Codex: the agent cuts pauses and filler words, grades color, burns subtitles and adds animated overlays
Claude Video Vision
claude-video-vision
An MCP server and Claude Code plugin that let the agent watch video: frames via ffmpeg and audio transcription via Gemini, local Whisper or OpenAI
Claude Code Video Toolkit
claude-code-video-toolkit
A video production kit for Claude Code: script, voiceover, music, visuals and MP4 rendering through Remotion, with some steps on paid cloud services
VK video watching plugin
vk-video
A Claude Code plugin that analyzes video from vkvideo.ru, vk.com and vk.ru: downloads the clip, transcribes audio with whisper and extracts frames
A set of SKILL.md skills for short-video and content production: topic, script, voice, avatar, editing, covers and motion graphics
Claude Remotion Skill
claude-remotion-skill
Teaches Claude Code, Claude Desktop and other agents to make video on Remotion, that is on React code. Check the Remotion license terms yourself
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Repository stars | Main difference |
|---|---|---|---|
| Claude Real Video (this entry) | no | 2,216 | |
| Claude Code Video Toolkit | no | 2,206 | video production from script to MP4 render through Remotion |
| Motion Skills for AI agents | no | 789 | skills for animation and motion graphics in audience packs |
| Lanshu AI Presenter Video | no | 2,646 | videos with an AI presenter from a script and an authorized portrait |
README in short
The README describes a skill that picks frames by scene, removes duplicates and transcribes speech through whisper, installed through pip and npx skills add. MIT license.