Use when the user gives a topic, campaign idea, product angle, or raw creative brief and needs it turned into a structured storyboard with hooks, scene beats, narration, and visual intent.
Use this skill when the user is still at the concept-development stage and needs a production-ready plan before generating media.
narration-to-visual-promptsTextTransformExpert directly.If some inputs are missing, infer the smallest reasonable defaults and state them explicitly.
TextTransformExpert for atomic text jobs:
mode="title" for title optionsmode="script" for polishing narrationmode="structure" for cleaning up a messy briefKnowledgeAgent only when the user explicitly wants multiple creative directions or deeper ideation.ImageGenerationAgent or VideoGenerationAgent during the planning stage unless the user explicitly asks to move into production.If the brief is messy and needs structuring first:
{"input_text":"launch a spring tea drink for office workers, soothing and premium, vertical short video","mode":"structure"}
If the user wants the narration polished after the storyboard is drafted:
{"input_text":"<scene narration draft>","mode":"script","style":"natural spoken delivery","constraints":"keep one scene only"}
Return a compact structured block like this:
{
"brief_summary": {
"objective": "...",
"audience": "...",
"platform": "9:16 short video",
"tone": "...",
"assumptions": ["..."]
},
"titles": ["...", "...", "..."],
"primary_hook": "...",
"story_arc": "...",
"scenes": [
{
"scene_id": 1,
"purpose": "...",
"narration": "...",
"visual_intent": "...",
"on_screen_text": "...",
"duration_seconds": 4
}
]
}