Turn video into searchable evidence. Start immediately when the user supplied it as a source.

Ingest

Resolve accessible URL/absolute attachment path. Use only authorized media; ask before browser cookies or another auth boundary.
Use untracked .context/video-research/<slug>/ when ignored, else temporary output.
From the absolute skill directory run:

bash <skill-dir>/scripts/analyze-video.sh \
  --output-dir <untracked-output-dir> \
  <video-url-or-path>

It prefers captions, then local Whisper, samples frames, OCRs text, and writes analysis.json, transcript.txt, research.md. One-shot tools are pinned; first run may download a local model. Report progress; never add runtimes to target dependencies.

Optional: --language <code>, difficult audio --model medium, non-English visuals --ocr-language <codes>. Transcription is local by default. Cloud transcription uploads audio and may cost money, so requires explicit approval.

video-research

Ingest

Research