crazyooo Whiteboard Explainer Video Producer
Create a finished explainer in which ideas become visible through progressive drawing. The skill is portable: do not assume a particular workbench, editor, project API, or directory layout already exists.
Establish the production
Use user-facing language first. Ask what material the user already has only when it is not evident:
- Script: pasted text or an uploaded text/document file. Generate narration with a configured MiniMax voice.
- Existing narration: an audio file, or a video whose audio is the intended narration. Extract or normalize the audio, then transcribe and align it.
- Subtitle file: an advanced optional input such as SRT, VTT, or ASS. Use matching supplied narration when present; otherwise generate narration with MiniMax.
Do not require the user to know what SRT means. Internally normalize every route to one narration master and one canonical subtitle timeline. Determine audience, learning goal, platform, aspect ratio, language, visual constraints, and delivery format. Infer ordinary defaults when safe: use 1920x1080, 30 fps, and 16:9 when no platform or source suggests otherwise.
Read references/narration-inputs.md before planning drawing time. Establish the narration master first:
- For existing audio or video, use the actual narration as timing authority and create the internal subtitle timeline by transcription and alignment. Do not make semantic deletions unless the user requests narration cleanup.
- For text, require a configured MiniMax model and voice, generate a short sample when the voice has not been approved, then synthesize the full narration.
- For a subtitle file, validate its cues and pair it with supplied narration or MiniMax generation.
- Measure actual audio and create the canonical internal subtitle timeline from real speech timing. Text length or requested timestamps are not proof of duration.
MiniMax generation may incur cost. Apply MiniMax authorization rules only when generating voice: do not send a paid request without explicit authorization, do not expose credentials, and do not automatically retry failed or cancelled generation.
If brand materials exist, adapt them to a legible line-art system. Otherwise offer or select a preset from references/presets.md. A preset governs paper, stroke, accent use, typography, and transition behavior—not merely color.
Production order
For end-to-end work, read references/workflow.md. Lock the narration master and canonical subtitle timeline before finalizing draw timing. Do not route this workflow through raw-video or A-roll rough cutting. Divide the explanation by conceptual transformation: introduce objects, reveal relationships, change state, compare alternatives, and resolve the model. Do not create a new scene for every subtitle cue.
Each scene needs:
- One core idea and a clear start/end state.
- A composition that reserves space for later strokes and captions.
- Semantic regions and an explicit draw order tied to narration beats.
- Short labels only where they improve comprehension.
- A transition decision: hold, pan, erase, morph, or cut to a new board.
Prefer clean, editable vector or high-resolution line art. Keep stroke language, object vocabulary, character proportions, and accent colors consistent. AI-generated illegible text is never acceptable; add labels with reliable typography after illustration generation.
If true stroke paths are unavailable, use an honest progressive reveal by semantic region. Do not describe a simple crossfade or arbitrary wipe as hand drawing. Preserve enough hold time after a reveal for the viewer to understand the completed relationship.
Default to a voice-sample checkpoint when MiniMax is used, then checkpoints after the scene strategy, representative line art, and one real animated sample. If the user explicitly requests uninterrupted end-to-end execution, continue without routine pauses, but still stop for a required missing input, external spending, rights questions, and destructive actions.
Truthful completion
Use supplied narration or the configured MiniMax voice service, plus available transcription, alignment, illustration, image, vector, animation, audio, editing, media inspection, and rendering capabilities. Follow the instructions of specialized tools or skills actually used. Never claim that voice generation, transcription, line art, animation, synchronization, viewing, or rendering occurred unless it did.
Before delivery, read and apply references/quality-gates.md. Deliver the playable final file when rendering is available, plus scene plans and source artwork needed for revision. If a capability is unavailable, preserve completed artifacts, state the exact blocker, and do not call static boards or an animatic the final video.