← ClaudeAtlas

video-to-shortslisted

Select complete short-form moments from a verified Open Recut main delivery, extract approved horizontal derivatives, and optionally render reviewed 9:16 versions. Uses the shared program transcript/timeline, hash-bound human or delegated-agent decisions, and Project Protocol V1 output locations.
WhiteTowerAI/cut-as-code · ★ 7 · Code & Development · score 75
Install: claude install-skill WhiteTowerAI/cut-as-code
# Video To Shorts ## Dependencies `/video-understand` is a prerequisite. Run it first so shorts use the validated source transcript and 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`/`ffprobe` on PATH and Python with `Pillow`. Check them before processing media. ## Scope This skill owns short candidate judgment, deterministic qualification, horizontal extraction, short-relative transcripts, and optional deterministic vertical delivery. It does not transcribe in project mode, change the main sequence, add captions/graphics, grade, publish, or perform continuous subject tracking. Shorts are derivatives of `final/final-video.mp4`. Record the operation in the project DAG, but never add it to `sequences.main.operations`; the main delivery and its original-vs-final comparison remain unchanged. ## Project Inputs - `work/project.json`, whose main render status is `verified` - `final/final-video.mp4`, exactly matching the project render path - `work/understand/transcript.json` in source time - `work/timeline.json` - active main-operation revisions `prepare_transcript.py --timeline` calls the shared `projectlib.map_transcript_to_timeline`. Candidate/extraction times are therefore program seconds on the actual final video. Words removed by the main edit are not available to shorts. Each retained word keeps its `source_range`, `program_range`, and `