Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

claude-video

claude-video• Pinned

claude-video: Turns videos into timestamped frames and transcripts for coding agents.

What problem it solves

Coding agents need visual and spoken evidence from videos before they can answer questions about them. Watch transforms a URL or local video into frames, transcripts, and timestamped visual evidence that an agent can inspect.

Key features

  • Process URLs and local videos — Accept a remote video URL or a local file and turn it into timestamped frames and a transcript for the agent.

    Source: README

  • Choose cloud or local processing — Use a Gemini-backed workflow when a key is available, or process frames and transcripts locally with FFmpeg and yt-dlp.

    Source: README

  • Select a transcription fallback — Read native captions first and optionally use WhisperX, Groq, or OpenAI when captions are unavailable.

    Source: README

  • Control visual detail and timing — Choose transcript-only, efficient, balanced, or uncapped frame collection, and restrict analysis to a time range or selected timestamps.

    Source: README

  • Install across agent hosts — Install the skill through Claude Code, Codex, or the Skills CLI for other local Agent Skills hosts.

    Source: README, skills

Quick start

Copied verbatim from the project's README.

/plugin marketplace add bradautomates/claude-video
/plugin install watch@claude-video
Use the watch skill on example.mp4 in the folder I shared.
For setup, choose balanced detail and captions only (none).
Summarize what is visible, with timestamps.
Use the watch skill's bundled setup.py to check dependencies in this session.
Tell me which tools are missing and help me install them here.

Who it may suit

Inference: may suit developers who need coding agents to inspect videos, explain on-screen activity, or work from timestamped visual and spoken evidence.

Topics to discuss

  • Which video sources and authentication methods should the skill support next?

  • How should local and cloud processing tradeoffs be presented in the setup wizard?

  • Which evidence formats would help agents summarize videos more accurately?

Written by ReadmeX AI from the project's README, source and public GitHub data; it may contain mistakes.

Read the original README https://github.com/bradautomates/claude-video#readme

ReadmeX opened this community for a trending project; it is not run by the project. Maintainers can claim it from the community page.

github.comhttps://github.com/bradautomates/claude-video

Comments

…