# bradautomates/claude-video

Give Claude the ability to watch any video. /watch downloads, extracts frames, transcribes, hands it all to Claude.

Repository: https://github.com/bradautomates/claude-video
Canonical: https://ross.abutalabs.com/products/claude-video
Language: Python
License: MIT
License Family: permissive
Last push: 2026-07-01T01:26:49+00:00

## Health v2 (maintenance only)
Score: 74/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 90, release rhythm 90, longevity 9
- inputs: {"age_days": 131, "days_push": 64, "days_rel": 64, "gap_med": 7.0, "n_releases_24m": 5}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 16260, forks 1604 (observed 2026-08-28T04:11:14.985880+00:00)

## What it is
A Claude Code plugin and Agent Skill that lets AI coding agents watch videos. It downloads videos via yt-dlp, extracts scene-aware frames with ffmpeg, pulls timestamped transcripts (free captions or Whisper API fallback), and feeds everything to the agent for analysis.

## Use cases
- analyze a viral video's hook and structure
- diagnose a bug from a screen recording
- summarize a long YouTube video
- extract the substance from a product launch video
- turn a playlist or course into per-video notes
- ask what happens at a specific timestamp in a video

## When to choose
- you use Claude Code, Codex, Cursor, or another Agent Skills host and want the agent to understand video content
- you need combined visual and audio analysis of a video, not just a transcript
- you want zero-config setup with free captions when available

## When to avoid
- you need a standalone video analysis tool without an AI agent host
- you need real-time or streaming video processing
- your videos have no captions and you don't want to use the Whisper API

## Facets
- artifact type: plugin
- maturity: active
- function: video-processing, speech-recognition, llm-inference, cli
- domain: artificial-intelligence, developer-tools
- platform: windows, cli, cross-platform
- tags: claude-code, agent-skills, yt-dlp, ffmpeg, whisper, video-analysis, transcription, frame-extraction, video, ai-agents, macos, linux

## Member repositories
- bradautomates/claude-video (main) score 74

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:14.985880+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:05:10.017402+00:00, confidence not recorded.
  - readme: https://github.com/bradautomates/claude-video (fetched 2026-08-28T04:11:14.985880+00:00, sha 2b0051bab7d2)
- Data as of 2026-08-30T08:39:29.467469+00:00.