sugarforever Boring video
Orchestrate video pre-production as a chain of durable artifacts, then hand the approved plan to HyperFrames. Each to-* skill owns one conversion.
Intake
Resolve existing decisions from the request and project files. Ask one compact question for the missing choices:
- Presentation: faceless, footage, screen capture, talking head, or mixed media?
- Collaboration: storyboard reviews or agent-executed production with final preview?
- Voice: HyperFrames voice, ListenHub TTS, user recording, or no narration?
- Design: existing design truth, named direction, or agent-proposed direction?
Record the answers in the HyperFrames BRIEF.md. In agent-executed work, propose and record a design direction when the user leaves it open.
Chain
Start at the first missing or explicitly revised artifact:
/to-spec-beats→BEATS.md/to-narration→NARRATION.md/to-scenes→SCENES.md/to-storyboard→STORYBOARD.md/to-video→ HyperFrames handoff
Finish each skill's completion criterion before advancing. A downstream finding returns to the artifact that owns the decision, then propagates forward.
Handoff
Presentation and workflow are separate decisions. Collect the presentation intent without selecting a workflow from memory. /to-video reads the current /hyperframes contract and performs the route.
Done
Pre-production is complete when the four planning artifacts agree and satisfy their owners. The wrapper run is complete when /to-video has transferred that truth, plus the confirmed voice branch, into the selected HyperFrames project.