Plan draft video-ad variations from supplied performance evidence, preserving the distinction between observed data and creative hypotheses.
中文简介正在准备中。当前显示原文说明。
Turn approved video clips, audio, captions, and timing decisions into an ordered, reviewable draft while preserving a reproducible timeline.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Create the final draft timeline from approved parent/child clips. Keep clip order, duration, gaps, transitions, audio treatment, captions, and export settings explicit so another editor or agent can reproduce the assembly.
Use Video Editing when the source itself needs a visual transformation or extension. Use this skill when the shots are already approved and the primary task is the cut, package, or handoff.
Reject unapproved, missing, private, expired, or mismatched assets instead of silently substituting a nearby clip. If no audio mix or caption renderer is available, return a timeline/EDL handoff and state what remains for local post-production.
Build a table such as:
| Order | Clip | Source parent | In/out | Transition | Audio | Caption state | Approval |
|---|---|---|---|---|---|---|---|
| 1 | clip-001 | shot-001 | 0.0–4.0 | opening | narration A | pending | accepted |
Record actual measured duration after rendering. Distinguish a requested duration from a provider's returned duration and call out gaps, overlaps, black frames, silent sections, and aspect-ratio changes.
media.combine_video or the live documented utility with explicit
order and accepted fields. Do not assume it performs transitions, audio
mixing, captions, color correction, or frame extraction.Use MODELS.md and muapi-video-tools.md to verify the current combine operation and its accepted fields.
Return the timeline, asset manifest, assembly operation/schema, prediction ID,
output URL, measured properties, audio/caption status, rights/disclosure
state, QA findings, and a local post-production handoff where applicable. Save
permitted receipts under .video/ using
reports-and-receipts.md.
Assembly is draft-only. Do not publish, overwrite source assets, or represent generated clips as evidence of a real event.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Plan draft video-ad variations from supplied performance evidence, preserving the distinction between observed data and creative hypotheses.
中文简介正在准备中。当前显示原文说明。
Create authorized presenter, avatar, and UGC-style video drafts with explicit voice, likeness, consent, and synthetic-media handling.
中文简介正在准备中。当前显示原文说明。
Analyze a script or existing edit, identify visual gaps, and generate supplemental B-roll coverage with clear parent and factual-status labels.
中文简介正在准备中。当前显示原文说明。
Build a consented continuity system for an authorized person, fictional character, product, or world across video shots.
中文简介正在准备中。当前显示原文说明。
Translate creative intent into coherent cinematography, framing, camera, lens, lighting, motion, and sound direction for a video shot.
中文简介正在准备中。当前显示原文说明。
Create a non-explicit romantic scene from authorized adult references with clear consent, identity boundaries, and synthetic-media labeling.
中文简介正在准备中。当前显示原文说明。