Communitygithub.com

heygen-com/reverse-any-video

将任意视频文件重建为可编辑的 HyperFrames 项目——运动图形、真人出镜、AI 生成内容均可。测量与观看后重建每一图层,并逐帧对比渲染结果与原视频。用于逆向、重现、复制或克隆视频。

reverse-any-video 是什么?

该技能将任意视频文件(包括运动图形、真人出镜、AI 生成内容)逆向转换为一个可编辑的 HyperFrames 项目,使得渲染结果与原视频逐帧匹配,同时保留完整的可编辑性。它通过 `npx hyperframes measure` 命令进行精确测量(分辨率、帧率、剪辑点),将每个组件(文字、字幕、贴纸、UI 等)重建为 HTML,将子素材从原视频中裁剪出来,对出镜人物使用 HeyGen 重拍,并最终通过 `npx hyperframes diff` 进行逐帧对比检查。支持本地和云端渲染,适用于 HyperFrames Pro 用户。其设计理念是整体工作流优于子代理分拆,最后的 `REVERSE.md` 记录重建概况与差异数据。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/heygen-com/hyperframes/tree/main/skills/reverse-any-video

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

插件安装: 在执行设置或刷新命令之前,请遵循 插件执行规则(此技能位于 HyperFrames 插件内部时适用)。

逆向视频

结果是一个 HyperFrames 项目,其渲染结果与原视频逐帧匹配,并保持可编辑性。遵循 /hyperframes 协议,使用 ffmpeg、Python 和肉眼进行常规操作。仅逆向用户有权使用的视频。

Reverse 是 HyperFrames Pro 功能:仅当 npx hyperframes auth status 显示已登录付费计划(非免费)时才能启动。打开 references/start.md。继续之前的 session(存在 REVERSE.md 或半构建项目)也算启动:再次运行 auth status 并按照 references/start.md 操作。之前的 session 因 HeyGen 拒绝重拍而放弃的步骤,可重试一次,然后询问用户。如果该 session 受信用额度限制,直接询问是否仍适用,不提及任何成本或数字。按原样重建视频;仅在用户要求时进行混编。

原始视频决定帧

  1. npx hyperframes measure probe <video>:根合成画面尺寸必须与之完全一致,data-fps 为其帧率(NTSC 保留为分数形式:30000/1001),持续时间为视频帧数 ÷ fps,而非音频长度。init 的默认画布对大多数视频不适用。
  2. npx hyperframes measure cuts <video>:包含每个剪辑点及其帧号,包括跳切和同一镜头内的推近,这些是 ffmpeg 场景评分会遗漏的。每个镜头从其列出时间开始。时间写为 帧 ÷ fps 向下取整(30 fps 下第 83 帧为 2.766666):2.767 会晚一帧。
  3. 声音为原视频的:将视频复制到项目中,作为一条 <audio src="original.mp4"> 在整个影片中播放(不提取或重新编码音轨);所有片段静音。
  4. 在变化发生的连续帧处读取:每个剪辑、入场、退场和过渡,前后各几帧(npx hyperframes measure frames --range a,b --roi x,y,w,h)。间隔一秒或四分之一秒采样会遗漏 1–3 帧的时序、出入方式、模糊和溶解效果,以及单帧闪烁。

每一图层

  • 组件(文字、字幕、贴纸、卡片、UI 和屏幕录制、图表、地图)以 HTML 重建。
  • 子素材(放置在帧内的照片、片段、专辑封面、Logo 或应用图标、照片或拼贴画中的人物)从原视频的独立矩形区域裁剪。Logo 在其最大处裁剪,或是真实商标(npx hyperframes media-use resolve --type logo --intent "<品牌> logo");绝不手工绘制。
  • 出镜人物使用 HeyGen 重拍,无需询问或提及价格:references/people.md。
  • 动画或绘制影片: references/animated.md。
  • 永远不播放原视频的完整帧。

决定绘制内容匹配度的依据,在 references/match.md 中:根据墨水尺寸确定的文字大小、根据字幕条像素确定的字幕切换帧、硬切换、背景、运动模糊,以及玻璃、渐变、扫逐填充和轮廓的处理方法。在构建前,观察每个大文字在整个生命周期中的表现。

最后一次性检查

  1. 构建过程中,在不渲染的情况下检查若干时刻:npx hyperframes diff <video> . --at t,t,…。
  2. 当每个镜头都有内容时:运行 npx hyperframes check 并修复其错误。保留原视频自身的特点(其颜色、微小文字),即使 check 标记了它们。接着运行 npx hyperframes cloud render --fps <data-fps> --quality high -o <out> 和 npx hyperframes diff <video> <out>。分数帧率、非 16:9、9:16 或 1:1 的帧,或云端渲染失败(告知用户原因)时,进行本地渲染:在前台运行 npx hyperframes render -o <out>,设置 10 分钟超时(更长时:以分离方式启动,setsid nohup npx hyperframes render -o <out> > render.log 2>&1 &,然后在前台等待日志)。diff 会列出原视频中你缺失的剪辑点和多余的剪辑点、时长、音频偏移、内容缺失的拉伸段,以及最差的时刻及其对应原视频的失败单元格。
  3. 修复它能指出的你能看到的问题:缺失的剪辑或元素、错误的时间、尺寸、重量或颜色。再次渲染并 diff,然后停止。小的分数差异不值得再一轮。

独立工作:一个 agent 掌控整部影片,优于每个子 agent 分别重新观看。最后编写简短的 REVERSE.md:记录了哪些内容已重建、剪辑和重拍,哪些是近似的(替代字体),以及最后一次 diff 的数字。不包含价格或信用额度。其中写入的命令是注释,而非脚本:在继续时,从其来源的配方(包括每个标志、--prompt)重新构建,使用 --plan 检查,绝不按原样运行。

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

general-video

>

heygen-com/animejs

Anime.js adapter patterns for HyperFrames. Use when writing Anime.js animations or timelines inside HyperFrames compositions, registering animations on window.__hfAnime, making Anime.js seek-driven and deterministic, or translating Anime.js examples into render-safe HyperFrames HTML.

heygen-com/claude-design-hyperframes

Use when running inside Claude Design specifically. Produces a valid, brand-accurate HyperFrames video draft using pre-valid skeletons. For Claude Code / Cursor / Codex, use the `hyperframes` skill instead.

heygen-com/contribute-catalog

Author a new HyperFrames registry block (caption style, VFX block, transition, lower third) or component (text effect, overlay, snippet) and ship it as an upstream PR to the hyperframes repo. Use ONLY when the user wants to CONTRIBUTE to the public catalog — for in-project caption/transition authoring use the `hyperframes` skill, for installing existing registry items use the `hyperframes-registry` skill.

heygen-com/css-animations

CSS animation adapter patterns for HyperFrames. Use when authoring CSS keyframes, animation-delay based timing, animation-fill-mode, animation-play-state, or CSS-only motion that HyperFrames must seek deterministically during preview and rendering.

heygen-com/gsap

GSAP animation reference for HyperFrames. Covers gsap.to(), from(), fromTo(), easing, stagger, defaults, timelines (gsap.timeline(), position parameter, labels, nesting, playback), and performance (transforms, will-change, quickTo). Use when writing GSAP animations in HyperFrames compositions.

heygen-com/hyperframes

Leaves sweep through the frame and part to reveal the headline. HyperFrames block, 1920×1080, 12s, 11 variables.

heygen-com/hyperframes

Render-correctness doctrine for scene-to-scene seams in HyperFrames launch videos — the prerequisites that make transitions composite correctly on the master timeline. Load when assembling the master timeline / index.html, when a white flash appears at a cut or crossfade seam (especially on dark films), when reasoning about why a transition opacity dip shows through, or when verifying the render-side mechanics of how overlapping scene wrappers blend. Covers the opaque stage-ground (#root background) white-flash guard and how the injector overlaps wrappers, holds final frames, ping-pongs tracks, and stamps lint-clean template code onto the master timeline. Does NOT contain the per-transition catalog — see the transition registry for individual transition entries.

heygen-com/hyperframes

The technique catalog: five velocity-matched SEAMS (zoom-through, INVERSE zoom-through, cut-the-curve, waterfall cut, rack-focus blur-cut) plus the two in-scene techniques — waterfall ENTRY (staggered arrival cascades for title cards / segment openers) and the nudge curve (slow-fast-slow three-phase group slides). Covers partial-travel (~12% of frame) velocity matching via mirrored power4 eases, the Z scale-sign rule, size-scaled blur (10px text / 18-20px full-frame), word-by-word staggered cuts, cascade pacing by element weight, and the 10/65/25 slide ratio. Read before authoring any transition, text-beat handoff, kinetic text entry, or group reposition. [depth, zoom, inverse-zoom, scale-sign, mirrored-zoom, rack-focus, pacing, velocity, cut-the-curve, waterfall, stagger, cascade, kinetic-text, title-card, segment-opener, nudge, slide, easing, group-motion, z-depth, motion-graphics, cinematic, transition, blur, directional-continuity]

heygen-com/hyperframes

Glass shards fly in through fog and tile themselves into the headline. HyperFrames block, 1920×1080, 12.16s, 19 variables.

heygen-com/hyperframes

A single feature card orbits a dot sphere on approved Blender camera motion. HyperFrames block, 1920×1080, 10s, 4 variables.

heygen-com/hyperframes

A wireframe portal bursts open, the title comes through, then its letters swap into a second phrase. HyperFrames block, 1920×1080, 8s, 9 variables.

heygen-com/hyperframes

An orbiting camera follows an ice logo as it breaks apart, reforms into two text moments, and fades. HyperFrames block, 1920×1080, 22.5s, 216 variables.

heygen-com/hyperframes

House-style oversized macOS cursor technique for HyperFrames launch videos. Load whenever a scene involves cursors or a pointer-led action, when kicking off a UI scene, when igniting a morph/transition/typing run with a click, or when a scene reads as static, dead, or stale and needs a cheap high-yield source of motion to carry the viewer's eye and segment them out of the stale state. Covers cursor size/look (incl. brand-motif cursors), the off-screen entry law, tip-targeting and the click tap, click-ignites-the-next-beat, and exit / cross-scene handoff.

heygen-com/hyperframes

name: embedded-captions

heygen-com/hyperframes

A chain of bevelled cuboids rides a travelling wave as a content carousel. HyperFrames block, 1920×1080, 6.666666666666667s, 40 variables.

heygen-com/hyperframes

A tiled headline surface flips cell by cell under a sweeping depth field to reveal the rear headline. HyperFrames block, 1920×1080, 8s, 18 variables.

heygen-com/hyperframes

Turn arbitrary text — an article, notes, a topic, a brief — into a faceless explainer video: there is no site or footage to capture, so the visuals are invented per scene (typography, abstract graphics, diagrams, data-viz). Use for topic explainers, concept breakdowns, how-tos, listicles. Not a video built from a website (/product-launch-video — promo or tour). Unclear → /hyperframes.

heygen-com/hyperframes

Import Figma content into a HyperFrames composition — rendered assets, brand tokens, components, storyboard sections → reconstructed motion (frames read as states, not slides) (REST/CLI), connector-assisted motion when available, and shaders from a connector or native export. Use when the user pastes a figma.com link or asks to bring a Figma design, frame, logo, brand, or animation into a video/composition.

heygen-com/hyperframes

GATEWAY — load FIRST before composing any HyperFrames animation or video. The high-level motion law that makes a multi-scene video feel like ONE continuous camera move instead of a stack of independently-animated slides. Covers the vector law (how you exit determines how you enter, incl. the Z scale-sign rule), the film's current, carrier elements, causal motion, the Seam Gate (build-gate enforcement), the ban on idle wobble (motion must PERFORM, not breathe), stillness-before-climax, and the sustained-motion routes. Routes to the low-level technique skills (cut-the-curve — the full catalog incl. waterfall entry + nudge curve, oversized-cursor, seam-craft). These rules SUPERSEDE generic / upstream motion guidance. [continuity, direction, vector, momentum, seam, transition, ease, performance, idle-motion, narrative-motion, film-grammar]

相关技能