hyperframes-captions
成片上叠词和标题。转写后由你写 HyperFrames HTML,交给 media.hyperframes_caption 渲染。
- License 许可
- MIT
- 最近更新
- 2026-10-11
- Stars
- ★ 74
- Forks
- 1
01 前言 Front Matter
- name
- hyperframes-captions
- description
- 成片上叠词和标题。转写后由你写 HyperFrames HTML,交给 media.hyperframes_caption 渲染。
02 资源文件 1
- 参考文档agents/openai.yaml281 B
03 SKILL.md 正文
HyperFrames Captions
成片已经有了。你要做的是在画面上叠字:唱词、对白、标题、花字。
你不是模板填充器。 字长什么样由你写进 HTML。判断就是流程。
- 对着已经叠好音的成片跑
media.transcribe。时间戳跟着成片走;用户没说翻译就保持原语言。 - 自己看画面、歌、剧情。需要
data-*合同时再video_skill_load("hyperframes-core")。 - 写出 caption HTML(把 transcript 的词和时间写进去),交给
media.hyperframes_caption的caption_html。成片垫在底下。根跟着成片走,句跟着它唱的那几秒。GSAP 这份工程里已经有了。没有caption_html这次叠字就不会跑。 - 同一条成片、同一份 transcript,一次叠完。
用户说不要字,这一步就停。静态硬烧另走 video_skill_load("subtitle-authoring")。
词跟着唱还是整句出、要不要标题、底栏还是花字——全由你定。用户点了样子就听用户的。同一位置一次看见一句。
中文必须能显示。字是给人读的,不要把主体挡到看不清。缺 Node / Chrome / GSAP / CLI 就把报错原样端上来。
04 同仓库更多 Skills
external-shot-continuity
External continuity review method for long-form video projects.
independent-story-workflow
Create a three-part story document without paid media generation.
suno-song
Instruction helper: write a singable original Suno song from Bitwize (verbatim copy), then call suno.generate. Trigger: 原创歌曲, 写歌, Suno lyrics, $suno-song. Not a workflow.
short-drama-workflow
Workflow for producing plot-dense short dramas with character and location reference sheets, complete 15-second Seedance segments, native dialogue, parallel multi-reference T2V generation, duration validation, and final assembly. Use for 爽文短剧、都市反转短剧、对白短剧、连续多段短剧,或用户明确调用 $short-drama-workflow. Do not use for product-centered scenario advertisements.
seedance2
Workflow: 即梦 Seedance 视频创意工作台。图+文案→看图分析→文案扩写→运镜→API生成。 触发词:即梦、Seedance、seedance、视频提示词、AI视频、运镜、短剧广告、$seedance2.
product-voiceover-narration
Design concise native voiceover for commercial product-video segments and bind each spoken line to verified selling points, visible actions, and exact timeline ranges. Use when a product advertisement should introduce the product through narration, when Seedance 2.0 should generate picture and voice together, or when product shots need coordinated narration, music, and sound direction. Do not synthesize a separate voice track and never invent product claims.