Communitygithub.com

SingleGrain-Team/video-skills

在演示者背后渲染一个5-6秒的运动图形,超大字重标题(2-4个单词)从背后进入,去除背景的演示者剪影叠加在文字之上。随后通过硬切换移除演示者,同时标题保持完全相同的大小和位置,并显示一行简短的支撑文字供阅读。适用于人物讲话开场、章节开篇、发布公告和社交媒体引流。基于 HyperFrames 构建,输出 1920x1080 H.264 MP4 及可编辑项目。

video-skills 是什么?

该技能主要用于快速生成演示者出镜的视频开篇或章节过渡动画。核心创意是:前段演示者位于标题文字前方,形成深度层次感;后段通过硬切换瞬间移除演示者,标题保持不变,并补充一行支撑文字,实现从“人物引导”到“信息强调”的流畅过渡。 适用场景包括:人物访谈开场、课程章节开篇、产品发布、社交媒体短视频引流等。支持平台为 HyperFrames,输出两个文件:`final.mp4`(1920x1080 H.264 MP4)和可编辑的 HTML/CSS 项目文件夹。 使用流程简洁:准备一段人物出镜视频(切割6秒、去除背景)、选择2-4个单词的大写标题、一行支撑文字、一组调色板(深色背景+奶油色文字+强调色)。技能从模板自动生成时间轴动画,包括标题缩放淡入、演示者与标题共存、硬切换、支撑文字出现、最终完全静态定格。内置验证规则确保切换前后标题位置、大小完全一致,且剪影无残影。对于需要快速产出高质量、风格统一的出镜视频内容的团队或个人非常实用。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/SingleGrain-Team/video-skills/tree/HEAD/skills/title-takeover

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

title-takeover

一个想法,两个节拍。节拍1:标题从演讲者背后猛冲进来(深度)。节拍2:硬切换瞬间移除演讲者,同样的文字保持不变,同时一行支撑文字读出(清晰度)。切换前后是同一个元素;切换是唯一的变化。

输入

输入规则
演讲者视频一人,面对镜头,头部和肩部大致居中,1920x1080横屏,至少4秒可用素材。无声也可以。仅限自有或授权素材。
标题2-4个单词,大写,每行最多约16个字符。双行效果最佳(例如 ADOPT AI / SKILLS)。可选一个重音词。
支撑文字一句话,理想4-9个单词,绝不超过约50个字符(必须能在60像素字号下一行显示)。
调色板背景色、油墨色、强调色。深色背景+奶油色油墨+一个强调色效果最佳;保持对比度达到 WCAG AA 或更高。
字体一个作为本地文件提供的浓缩粗体展示字体(默认 Anton,OFL 许可证)加上一个用于支撑文字的干净无衬线字体(Inter)。

工作流程

  1. 准备视频。 剪辑一段6秒的窗口,演讲者面向镜头且不离开画面。去除音频,标准化为30 fps, 1920x1080: ffmpeg -ss <in> -i src.mp4 -t 6 -an -r 30 -c:v libx264 -crf 14 -pix_fmt yuv420p assets/presenter.mp4
  2. 去除背景。 npx --yes hyperframes remove-background assets/presenter.mp4 -o assets/presenter-cutout.webm(透明的 VP9 WebM,帧数和分辨率与源文件相同;在 Apple Silicon 上处理180帧约需25秒)。如果模型下载超时,重新运行;模型缓存在 ~/.cache/hyperframes 下。
  3. 合成。 将 template/ 复制到项目中,将 presenter.mp4、presenter-cutout.webm、字体和 logo 放入 assets/,然后仅编辑标记的调色板变量、两行标题和支撑文字。图层顺序,从底层到顶层:
    1. 背景(纯色 + 柔和的强调色辉光)
    2. 演讲者视频 + 暗色遮罩(使繁忙的背景变暗,让文字更突出)
    3. 标题
    4. 演讲者剪影(与视频相同的 data-start / data-media-start / data-duration)
    5. 支撑文字、品牌标志
  4. 检查并渲染。 npx --yes hyperframes check,然后 npx --yes hyperframes render --workers 2 --quality delivery --output final.mp4。

时间规则(6.0秒视频,30 fps)

时刻时间规则
进入0.30秒(第一行),0.45秒(第二行)缩放1.4到1.0,不透明度0到1,0.45秒,expo.out。各行交错0.15秒。先显示0.3秒的演讲者,让标题落在实时画面上。
演讲者背后保持0.75秒至切换至少2.4秒,演讲者可见并位于文字之上。
硬切换3.4秒(第102帧)视频、遮罩和剪影在同一帧结束。无淡入淡出、无过渡、无缩放。
支撑文字3.75秒,0.55秒上升28像素,强调色线条擦入切换后留约0.35秒的标题独自存在,以体现“保持”感。
阅读保持4.3秒至6.0秒至少1.5秒完全静止。以完整锁定画面结束;切勿淡出到黑色。

不变规则:

  • 标题是一个元素。进入动画稳定后(约第24帧),永远不要再调整其缩放、位置、大小或字间距。切换不能移动任何一个字形。
  • 切勿在第二个场景中重新创建标题。
  • 剪影和视频必须帧锁定;两者都设置 muted playsinline,不带 crossorigin。
  • 仅对标题行进行变换和不透明度动画(它们位于静态包装器内)。不要对 .clip 元素进行补间。
  • 演讲者的脸部会遮挡部分字母。这是故意的;保持词间距和每侧可见的独特字母对,并将标题字号保持在380-440像素,使单词保持可读。
  • 在第一行上方保留140像素的头部空间,确保字形永远不会超出画布。

验证

  1. npx --yes hyperframes check 必须报告0错误。故意的标题位于演讲者身后的重叠情况通过在剪影和标题行上声明 data-layout-allow-occlusion 来处理(模板中已包含)。
  2. 从渲染的 MP4 中提取并查看(而不仅仅是计数)以下帧:
    for n in 90 101 102 103 179; do ffmpeg -y -i final.mp4 -vf "select=eq(n\,$n)" -frames:v 1 qc_$n.png; done
    
    • 90:标题在演讲者身后可见,剪影边缘干净(无光晕,无缺失的头发或肩膀)。
    • 101(演讲者最后一帧)和102(切换后的第一帧):102上演讲者消失,标题在两者中的大小和位置完全相同。
    • 103:仍无支撑文字或刚刚开始;标题不变。
    • 179(最终帧):标题加上完整的支撑文字,完全清晰可见,无任何内容被裁剪。
  3. 如果剪影出现边缘闪烁或抖动,使用 --quality best 重新运行 remove-background 或选择更干净的源素材窗口。如果标题在切换时跳动,说明有补间动画仍在运行;请移除它。
  4. ffprobe 必须显示 h264, 1920x1080, 30 fps, 6.0 秒。

交付

交付 final.mp4 以及项目文件夹(index.html、assets/)。在 NOTES.md 中记录素材来源 URL 和许可证。切勿使用可识别创作者或名人的素材,或第三方标志。

Individual skills in this repo

This repo contains 7 individual skills — each has its own dedicated page.

SingleGrain-Team/video-skills

Make a 30-45 second launch film for a product by staging it inside one persistent, neutral chat window. A user types a request, the assistant answers and calls the product as a connected tool, a progress card runs, a follow-up triggers a second tool action, and the result lands as a count-up headline number before closing on the logo, tagline and call to action. Use when you need a launch, feature or integration announcement video for something that plugs into AI assistants (a skill, MCP server, plugin, connector, CLI). Delivers a rendered 1920x1080 MP4 plus an editable single-file HyperFrames project.

SingleGrain-Team/video-skills

Build a motion graphic where a screen recording plays in a large frame beside a checklist, and each checklist item ticks off at the exact moment that step happens in the recording, ending with every item checked and a short hold. Use when someone has a screen recording (product walkthrough, tutorial, onboarding, install demo) plus a list of steps with timestamps and wants a "watch the steps get done" film. Input is a recording, step labels with timestamps, a title and an optional palette; output is a 1920x1080 H.264 MP4 and the editable HyperFrames project.

SingleGrain-Team/video-skills

Build a 15-20 second product launch film that shows the product's real screen on a laptop built from plain CSS (no 3D model, no generation model) in a dark studio, scrolls the page, zooms into the interface for one key action such as typing a search, and resolves to the logo lockup. Use when someone has a full-page screenshot or screen recording of their product, one action worth showing, and a logo, and wants a short silent-friendly launch teaser rendered as a 1920x1080 MP4 with an editable HyperFrames project.

SingleGrain-Team/video-skills

Builds a 6-8 second logo sting in which the brand mark rides inside a refracting liquid bead (distorted past legibility), the bead swells, holds still for a beat, then ruptures into droplets and leaves the logo lockup (mark plus wordmark) crisp and upright on screen. Delivered as a 1920x1080 H.264 MP4 plus the editable HyperFrames project, with no 3D model, stock footage or generation model. Use it for brand intros and outros, product-launch openers, channel stings and any "reveal our logo" moment, from an SVG or PNG logo (including raster-only logos), a wordmark string and a palette.

SingleGrain-Team/video-skills

Make a 20-30 second launch film for a product that is not tied to one interface, such as a CLI, package, plugin or agent skill. The identical prompt or command is typed into four visually different surfaces in turn (a wide terminal, a tall chat card, a floating palette, an editor cell), the film then hard-cuts into a fast reel of real outputs on a beat or fixed tempo grid, and it closes on the command in a large pill. Delivered as a rendered 1920x1080 MP4 plus the editable HyperFrames project. Music is optional - with a track the cuts land on detected beats, without one they land on a 120 bpm grid.

SingleGrain-Team/video-skills

Make a roughly 30-second film that explains a code change (a pull request, release or uncommitted diff) to people who will never read the diff. It opens by showing the real diff scrolling past too fast to follow, cuts to a plain-language summary, fires four capability beats each pinned to a real code snippet, and closes on how to get it (install command and URL). Delivered as a 1920x1080 H.264 MP4 plus the editable HyperFrames project. Use when asked to turn a PR, changelog or release into a launch or explainer video.

SingleGrain-Team/video-skills

Builds a 10-14 second product sting out of a short run of UI moments (an entry screen, a single counting metric, a navigation list, one click that opens a menu, then an endcard) cut together so every cut carries the previous motion forward and the piece reads as one continuous camera move. Delivered as a 1920x1080 H.264 MP4 plus an editable single-file HyperFrames project. Use it for app launches, feature teasers, social bumpers and site intros when you have a product's logo, a couple of screenshots, one headline number and its real nav labels, and want polished UI motion without narration.

相关技能