media-forgemf-video-promptlisted

# media-forge:mf-video-prompt Build production-ready video prompts from clear concepts or supplied reference assets. Treat the prompt as a short shooting brief: it must say what changes on screen, what the camera does, what the light and sound contribute, and what must stay stable. Keep final prompts under the target provider's prompt budget and remove filler before delivery. This skill supersedes media-forge's earlier single-file `seedance-prompting` skill: the mode gate, director formula, and compression rules below are provider-agnostic craft that applies whichever of Veo, Kling, Higgsfield, or Seedance ends up rendering the clip. Where a section is Seedance's own mechanism (the `@ImageN`/`@VideoN`/`@AudioN` reference-fusion syntax, its tier names, its duration caps), it is marked **Seedance-specific** — for Kling's or Higgsfield's equivalent mechanisms and tier cookbooks, see `kling-prompting` and `higgsfield-prompting`. Load `[ref:quick-ref]` for the checklist, `[ref:reference-workflow]` for multimodal references, `[ref:i2v-guide]` for image-to-video, `[ref:first-last-frame-guide]` for first/last-frame work, `[ref:examples-by-mode]` when examples are useful, `[ref:shot-list-continuity]` for multi-shot professional plans, `[ref:multishot-grammar]` for shot-label grammar, the shots-times-seconds budget, and cut placement inside one generation, and `[ref:multilingual-community-examples]` for Chinese/Russian/Japanese/Korean/Spanish or mixed-language prompts. When sequence