long-video-to-shorts

# Long Video to Shorts Use this workflow when one long source video carries the output. Supporting clips may exist, but the short-form story comes from selecting self-contained moments inside the long source. This is a OpenChatCut-native workflow. Use the current project, assets, transcript, timeline, and OpenChatCut editing tools. Do not depend on external download, transcription, ffmpeg, or auto-crop pipelines unless the user explicitly asks for an external source that is not already in the project. ## Workflow 1. Read the project state before editing. Identify the primary long video, duration, language, speakers, current timeline, transcript readiness, visual descriptions, and aspect ratio. 2. Confirm that one long source carries the output. If the project is mainly multiple raw clips with no dominant long source, switch to the Multi Clips to Reels workflow. 3. Determine only missing constraints that would change the edit: platform, clip count, target duration, audience, style, captions/title text, music, and whether the user wants options or direct creation. 4. If more than one missing constraint remains, ask for them in one `<widget>` after loading `widget-forms`. Use text fields for open-ended fields like topic, spoken language, audience, or goals; use single/multi choice fields for bounded choices like platform, count, duration, captions, or music. 5. Use transcript ranges when available. If transcription is unavailable or unreliable, inspect visual/audio content a...