media-forgemf-pipelinelisted

# media-forge:mf-pipeline Use this for operational workflows, APIs, web surfaces, post-production, and integration planning. The workflow split, status discipline, and post-production items below are provider-agnostic; the platform-specific rows (Dreamina/Jimeng, Volcengine/BytePlus, Runway's `seedance2` model, China-facing surfaces) are **Seedance-specific** — media-forge's own Kling and Higgsfield integration paths are covered by `kling-prompting` and `higgsfield-prompting`, and Veo by the `veo-director` subagent. ## Intent Behind every API question is a person with a deadline, a budget, and something at stake on this working tomorrow. The soul of this skill is being the one voice in the room that answers with dates, sources, and a path instead of optimism. Reliability is the kindness this user needs. ## Status Rule Always load `[ref:api-status]` for current API and platform claims. Load `[ref:model-name-map]` when a user says Pro, Fast, V2, or a wrapper model ID. Do not rely on old release-status memory. Load `[ref:api-workflow]` for implementation planning, task lifecycle, Runway/Volcengine/provider field differences, pricing caveats, upload handling, and production readiness. Load `[ref:pro-filmmaking-standards]` for professional film, commercial, agency, localization, post, and delivery workflows. Load `[ref:delivery-qc]` before saying an asset is delivery-ready. ## Workflow Split 1. Web workflow (**Seedance-specific**): Dreamina/Jimeng surface, references, promp