Video Add Content Cards

Turn approved semantic moments into one coherent HyperFrames graphics overlay. Use shared evidence and the canonical timeline; do not re-transcribe or re-analyze the source inside this skill.

Dependencies

/video-understand is a prerequisite. Run it first so cards use validated semantic evidence and the canonical timeline. Before starting, verify that it is installed. If it is not, warn the user that this prerequisite is missing and stop before processing media.

Require ffmpeg on PATH, Python, and Node.js >= 22 (for npx hyperframes, fetched on demand). hyperframes render/snapshot drives a headless Chrome — it manages its own chrome-headless-shell, and falls back to a system Chrome (set CHROME to override) when the cached one is unusable. Check these before processing media.

Inputs

• work/project.json: operation revisions and dependencies
• work/understand/understanding.json: reviewed semantic moments and evidence
• work/timeline.json: source-to-program mapping, or an identity timeline when no cut exists
• optional selected color-grade revision when contrast or palette is judged against that look