YouTube Video Context

Turn a public YouTube video, playlist, or search topic into a local context pack before using it as coding, design, QA, or product context. This skill is evidence-oriented: agents should read generated codex_context.md files first, then inspect captions, manifests, or sampled frames only when a claim needs timestamp support.

How It Works

1. Resolve the source as a single video, playlist, or bounded search.
2. Capture metadata with yt-dlp when available.
3. Download captions unless the caller asks for a faster Gemini-first run with --skip-captions.
4. Ask Gemini to analyze the public YouTube URL when GEMINI_API_KEY or GOOGLE_API_KEY is set.
5. Optionally download media and sample frames when local visual evidence is required.
6. Write a portable context pack under .codex/video-context/.

Setup

Run the setup checker from this skill directory: