Video & Audio Production Skills

Design review layer for OrkasVideoStudio COMPOSE previews and drafts. Review every immutable snapshot frame before showing a visual preview; when preview is skipped, use the draft as the fallback evidence. Return one complete, actionable repair set without opening another user gate.

Reference-media and design-system input layer for OrkasVideoStudio. Treat reference images, videos, screenshots, brand guides, and design notes uniformly, compiling reproduce/edit/guide intent into executable spatial and temporal constraints.

Canonical VideoStudio review authorization and state-transition policy. Use after any Gate B/C/Preview/D decision, post-gate revision, resumed approval, or exhausted visual-QA result across COMPOSE/AUTO/GENERATE/EDIT; maps explicit user authority and durable artifact state to one next action with ovs gate transition. Do not use for ordinary planning or craft decisions before a gate exists.

Deterministically assemble an approved cross-modal EDL (plan.json) into a finished video — produce each segment (edit/compose/generate/provided, delegated to its line), then assemble in ffmpeg tiers: concat primaries → overlay composed layers → mix narration once (coverage check) → burn captions → verify loudness; idempotent-resumable, with QA before the draft gate. Trigger after a plan is validated and approved; do NOT trigger to ingest or re-author the plan (stage-plan).

Authoring knowledge for Orkas/OVS HTML video compositions -- write an index.html, drive animation from a paused timeline, declare canvas + duration, then run the VideoStudio draft gate to render an mp4. Trigger for explainer / animation / motion-graphics / caption / lower-third / title-card work, or to build a compose segment inside an AUTO plan; do NOT trigger for cutting real footage (stage-edit) or AI footage (stage-generate).

Multi-shot narrative & character consistency — a character bible with a locked front-portrait anchor, view-matched reference selection, recent-frame carry-forward, Cameo (a user photo as the lead), and global planning for long scripts/novels. Trigger on top of the generation line when the SAME character must look the same across many shots/scenes, or for long-form story→video; do NOT trigger for one-off single-shot generation.

The decision layer for real footage — understand → select → produce an EVIDENCE-bearing rough cut. Trigger when the EDIT task is "find / select / reduce / clean" (remove dead air, drop fillers, pick highlights, cut 1 hour to 3 minutes), NOT executing a known timecode edit (that is stage-edit). Deterministic auto-cuts (silence/filler/quality) are reliable; narrative/emotional selection is a low-confidence DRAFT for the user to review.

Intelligent editing of real user-supplied footage—understand it with transcript/OCR/scene/silence/quality/vision evidence, then choose deterministic timeline operations or a constrained semantic AI edit. Trigger for repurpose, montage, cleanup, localization, narration, or local content changes.

AI-generated footage plus execution of bounded semantic video-edit segments already approved by EDIT/AUTO. Generate per shot with ovs video, preserve signed reference/settings, then assemble. For recurring characters also read stage-consistency.

Read this FIRST on any video-production request to pick and lock the line — generate (AI footage), compose (designed HTML), edit (cut real footage), or AUTO end-to-end. Trigger when classifying a brief and committing to a primary path; do NOT trigger for authoring compositions, generating assets, or rendering output (those have their own stage skills).