#4242nd of 53 in Skills, plugins and rules

claude-video

Agent skill that turns a video URL or file into timestamped frames and transcript

Repository on GitHub ↗

Stars: 18.5k
License: MIT
Last commit: Sep 2026
Last release: Sep 2026
Language: Python

Stars, last 25 weeks+18,509

20 on 21 Apr 202618,529 on 13 Oct 2026

From GitHub's daily star counts.

Checked 14 Oct 2026 on GitHub.

Overview

Watch is a skill/plugin for Claude Code, Codex and other Agent Skills hosts. It converts a video URL or local file into timestamped frames and a transcript, using native captions first and optional WhisperX, Groq or OpenAI transcription otherwise. With a GEMINI_API_KEY it can instead send the video to Gemini and relay the timestamped answer.

Who it is for: Claude Code and Codex users who want agents to analyze video

Strengths

Installs as a plugin in Claude Code or as a skill in Codex and other hosts
Local engine works without an API key, using ffmpeg and yt-dlp
Frame detail levels, caps, start/end ranges and cue timestamps are configurable
Captions are used first; WhisperX, Groq or OpenAI only as fallback

Weaknesses

Does not work in Claude Chat or Cowork
Requires Python 3.10+, FFmpeg and current yt-dlp installed separately
YouTube also needs a JavaScript runtime such as Deno
WhisperX is verified only on Apple Silicon; other platforms untested

What it needs

RAM ≥ 8 GB
GPU optional
Needs Python 3.10+, FFmpeg, yt-dlp, Deno (YouTube), WhisperX 3.8.6 (optional), Node.js (Skills CLI install only)
Models: Gemini (gemini-3.7-flash default), WhisperX, Groq whisper-large-v3, OpenAI whisper-1

Also in Skills, plugins and rules

See all 53

Also in Skills, plugins and rules
Rank	Project	Score
1	skillsAgent skills for planning, TDD, debugging and code review290.6k starsMIT	94 out of 100
2	eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses279k starsMIT	93 out of 100
3	cavemanCuts token use in coding agents with terse replies and compressed inputs Live demo ↗ (opens in a new tab)111.7k starsApache-2.0	93 out of 100
#4	ponytailSkill prompt that makes coding agents write less code and add tests163.2k starsMIT	91 out of 100
#5	ui-ux-pro-max-skillDesign-system skill that gives coding agents searchable UI styles, palettes and fonts135.7k starsMIT	90 out of 100

How to choose

Check which agent it targets and whether it works with the version you run.
Read what it adds to every prompt; big rule sets cost tokens on each call.
Prefer add-ons you can turn off per project.

Health

Releases: 8 in the last 12 monthsLast one 19 days ago
Top contributor: 100% of commits33 of 33 in the last 12 months
Security advisories: NoneOn GitHub, in the last 12 months
OpenSSF Scorecard: Not checked

Read from GitHub, deps.dev and OpenSSF on 14 Oct 2026. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check.

License in plain words

MIT Permissive

Use it at work: Yes
Change it and rebrand it: Yes
Sell it or host it for others: Yes

Your part: Keep the copyright and license notice in copies you ship.

A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)

#42 of 53 in Skills, plugins and rules on Archestack, as of 14 Oct 2026.

In your README

The badge updates twice a day.

[![Archestack](https://archestack.com/badge/bradautomates/claude-video.svg)](https://archestack.com/best-of-vibe-coding/projects/claude-video/)

How badges work

On your site or blog

A card with the rank, score and signals, in light or dark to match the reader.

<iframe src="https://archestack.com/embed/best-of-vibe-coding/claude-video/" title="claude-video on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>

Preview the card

Best of Vibe Coding on GitHub

Each review comes from the project's README and facts we check on GitHub. The fix form opens with claude-video filled in.