agentleFS
AY-kkkAY-kkk/ad-gtm/skills/ad-storyboard/SKILL.md

ad-storyboard

Skill1 starsChanged 2 months agoMITView on GitHub

把确认的广告脚本转为分镜、时间轴、参考素材分工、声音和后期计划。用于准备视频模型制作包;不要求重新制定受众或创意方向。

The file

Files
SKILL.md

分镜与素材编排

输入

脚本、产品与主张资料、可用素材、时长和画幅。接受用户直接提供的脚本,也可衔接 ad-creative。

方法

  1. 将脚本拆为信息节点,一镜优先承担一个任务。先完成整条广告时间轴,再考虑模型的单次生成限制。
  2. 按视觉方法确定构图、起点、关键动作和结束状态,写出产品禁改项;指定渠道时读取平台 brief及对应模板。
  3. 逐镜映射 asset_id 与 claim_id。参考素材分别控制外观、构图、动作或声音,不让冲突的 SKU 同时控制商品。
  4. 将生成、实拍、3D、剪辑与图文合成分别安排。准确 Logo、文字、价格和 CTA 指定后期轨道;复杂机构可使用真实演示素材。
  5. 校验起止秒、镜头顺序、总时长、接触关系、转场、音轨和片尾阅读时间。注明重叠区与剪辑方式,不把所有轨道长度简单相加。
  6. 如需分段,保存产品朝向、角色、光线与动作衔接;首帧看主体比例和结构,末帧看下一镜连接及 CTA。

输出

使用制作包模板,填本次任务涉及的部分。至少交付:镜头时间表、每镜画面与动作、素材映射、声音计划、后期项、渠道 profile 和生成任务划分。尚未执行的任务或检查记为 planned 或 not_run。

完成标准与交接

镜头都服务脚本信息,时间轴一致,素材与禁改项明确。尚未指定模型时保留中立制作包;指定后交给 ad-seedance-20 或 ad-seedance-25 转换参数与提示词。本 Skill 自身不依赖这些模块即可完成分镜。

示例

15 秒成片含 3 秒开头、5 秒操作、4 秒结果、3 秒收尾;模型生成只承担需要的画面,CTA 可由后期制作。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.