spark-video

Install, set up, diagnose, and run the full spark-video AI video production pipeline from premise to screenplay, storyboard, render, review, and final mp4. Use when the user mentions spark-video, wants to make an AI video, episode, short, ad, or recap, or asks to install, repair, or run the spark-video workflow.

Scaffold and generate reference assets for characters (cast), locations (movie-set / set dressing), and key props — the three pillars of visual consistency in spark-video. Wraps bl image generate / edit for cast reference sheet creation. Use when adding new characters/locations/props or when costume/state changes are needed.

Translate a screenplay (one scene at a time) into a provider-agnostic storyboard fragment for the spark-video pipeline. Wraps Shanyin Super Director Master when available — the upstream Shanyin SKILL is the single source of truth for craft when present.

Producer stage for the spark-video pipeline. Orchestrates screenwriter, director, cast, VFX review, clip review, render chain DAGs, and final stitching with the 4+2 user confirmation gates. Use internally when running the end-to-end spark-video production workflow.

Turn a user's premise into a structured screenplay (one scene at a time) for the spark-video pipeline. Wraps Shanyin Super Screenwriting Master when available — that upstream Shanyin SKILL is the single source of truth for craft when present.

Pre-render quality gate. Read a finished storyboard.json and produce a structured review report flagging visual inconsistencies, prompt defects, and continuity errors that would waste render budget. You find problems; the director fixes them. Opt-in — bypassed unless the producer explicitly invokes you.

Per-clip quality reviewer + render retry state machine. After each rendered shot, score it on 6 axes via `bl omni` (qwen3.5-omni-plus), then decide ACCEPT / REJECT-and-rewrite / REJECT-and-escalate. Handles up to N retry rounds with auto prompt rewriting; escalates to spark-video-director when retries are exhausted.