Communitygithub.com

产品发布到HyperFrames

将产品URL、营销文案或创意简报转化为高质量的产品发布视频,适用于SaaS推广、功能发布、应用上线等多种场景。

产品发布到HyperFrames 是什么?

该技能是一个完整的工作流编排器,用于将任何产品营销材料(如网站URL、脚本或简报)转换为专业的产品发布视频。它支持多种平台,包括HyperFrames、HeyGen和OpenAI,并遵循严格的分步流程:从设置和资产捕获到设计系统构建、故事板与脚本编写、音频生成、视觉设计、帧构建,最终输出MP4视频。技能的核心优势在于其模块化和可扩展性——它使用预定义的帧预设和蓝图,同时允许根据品牌配色方案和字体进行自定义。此外,它还集成了HeyGen的音频(TTS和BGM)和资产(图片)目录,确保合法合规。用户需要在关键步骤(如步骤0、3和6)进行审批,并可以选择在步骤3和步骤6预览最终视频。该技能避免用于非产品发布场景,如网站导览、主题解说或运动图形。

兼容平台~Claude Code~Codex CLI~Cursor✓Gemini CLI
npx skills add https://github.com/1345AbhishekKumar/starter-supabase/tree/HEAD/.agents/skills/product-launch-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

媒体使用:在获取音频/图片之前,请先调用/media-use以从HeyGen目录中解析背景音乐/音效/图片。运行--adopt以注册现有资产。详情见/media-use技能。

产品发布到HyperFrames 是做什么的?

使用此技能来了解产品、理解其品牌、规划发布视频,并逐步在HyperFrames中构建视频。

在步骤0之前确认路径。 你是编排者。运行每一步,验证其关卡,然后才能继续下一步。此技能适用于正在营销、发布、推广或展示的产品,包括当目的是推广时的“我们网站的推广”等请求。将其他意图路由到别处:一般的非发布网站导览 -> /website-to-video;没有产品的主题解说 -> /faceless-explainer;GitHub PR -> /pr-to-video;在现有素材上加字幕 -> /embedded-captions;短的无旁白动态图形 -> /motion-graphics。如果用户只说了“制作视频”或路径不确定,请先阅读/hyperframes。

你是编排者。在videos/<project>/目录下工作。按顺序运行步骤,并通过每个关卡后再继续。用户把关的步骤是步骤0、步骤3和步骤6。除了步骤5(你需要为每个帧分派一个子代理)外,其他所有步骤都自己完成。不要在此处放置设计或运动规则;这些规则存在于帧工作子代理、本技能的本地../hyperframes-animation/rules/ + ../hyperframes-animation/blueprints/以及hyperframes-creative中。

工作流程:步骤0 设置 -> hyperframes.json;步骤1 捕获 -> capture/;步骤2 设计系统 -> frame.md;步骤3 故事板/脚本 -> STORYBOARD.md 和 SCRIPT.md;步骤3.1 音频 -> audio_meta.json;步骤4 视觉设计 -> 增强后的STORYBOARD.md;步骤5 帧 -> compositions/frames/NN-*.html 和 index.html;步骤6 最终渲染 -> renders/video.mp4。


步骤0:设置和简报

目标:锁定核心视频简报,并在需要时创建HyperFrames项目。

仅在hyperframes.json缺失时初始化。项目名称<project>使用kebab-case格式,来自品牌或域名,例如acme-promo;不要使用工作区名称或时间戳。

npx hyperframes init "videos/<project>" --non-interactive --example=blank — init会检查已安装的技能是否与GitHub上的最新版本一致,如果有任何过期,则更新全局技能集。

在简报之前显示登录状态 — 运行npx hyperframes auth status并逐字转述其输出(不要改写或重新表述)。 它会报告语音/背景音乐是使用HeyGen还是本地引擎,以及当未登录时如何登录。如果未登录,请停止并等待用户选择——登录,或说“go”/“offline”以继续使用本地引擎——然后再询问简报或其他任何事情。 将其视为一个真正的决策点,而不是一个过场提示;不要将选择折叠到简报问题中,也不要将密钥写入每个仓库的.env文件中。(在自主模式下,记录状态并继续离线工作。)参见../hyperframes-media → Preflight 以获取规范指导。

关卡: hyperframes.json已存在,并且角度、时长、宽高比和语言已锁定;登录状态已显示(已登录,或继续离线)。


步骤1:捕获资产

目标:收集视频的源材料、品牌信号和可用资产。

对输入进行分类并选择路径。显式URL -> 捕获它并使用网站作为旁白和资产。粘贴的脚本/简报 -> 原样保存为user_script.txt,询问一次“原样使用还是重新组织?”,将答案存储为VO_MODE,然后解析捕获目标:文本中的URL -> 使用它;仅有品牌名称 -> WebSearch,在一行中确认URL,然后爬取;无URL/网站 -> 无捕获路径。

使用以下命令运行捕获:npx hyperframes capture "<URL>" -o ./capture

如果存在GEMINI_API_KEY、GOOGLE_API_KEY或OpenRouter密钥,捕获会自动为资产添加字幕到capture/extracted/asset-descriptions.md中。这不是一个审查关卡。如果没有视觉密钥,则使用DOM上下文并继续。

无捕获路径:手动创建capture/extracted/tokens.json、capture/extracted/visible-text.txt、capture/extracted/asset-descriptions.md和capture/assets/。tokens.json应为{ "title": "", "description": "", "colors": [], "fonts": [] };尽可能从简报中填写标题/描述。visible-text.txt包含完整的简报或脚本。asset-descriptions.md应说明没有捕获任何资产,除非用户提供了资产说明。

关卡: capture/extracted/tokens.json、capture/extracted/visible-text.txt、capture/extracted/asset-descriptions.md和capture/assets/都存在;你能用一句清晰的话说明品牌。将asset-descriptions.md作为主要资产清单。如果在实际捕获后它缺失,请停止并报告捕获不完整。如果存在capture/BLOCKED.md,请遵循它。


步骤2:设计系统

目标:选择一个已交付的帧预设;脚本会将其转换为本视频的frame.md + 字幕皮肤。

你只做一个判断——选择哪个预设。阅读../hyperframes-creative/references/design-spec.md,选择外观最适合该品牌和简报的预设。然后运行:

node <SKILL_DIR>/scripts/build-frame.mjs --preset <name> --hyperframes .

脚本确定性地完成其余工作:将预设的FRAME.md复制为frame.md,并将其重新混合到capture/extracted/tokens.json中的品牌令牌上(品牌颜色按角色映射到预设的颜色键上——墨色、画布、强调色——保持键/结构/组件不变;预设的显示+正文字体替换为品牌的字体),将预设的字幕皮肤复制到.hyperframes/caption-skin.html,并进行自我验证(遇到映射错误时退出码1)。一旦脚本退出码为0,就继续下一步——无需手动编辑规范。

如果没有品牌颜色/字体的tokens.json(例如,无捕获),则脚本会保留预设自己的调色板,这是一个完整可交付的设计。如果简报中提到了捕获未包含的品牌颜色/字体,请在运行脚本之前将它们添加到capture/extracted/tokens.json中(或使用用户的design.md来填充);之后只有在映射确实需要时才手动调整frame.md。

关卡: build-frame.mjs退出码为0——frame.md来自一个命名预设,并且(当预设附带字幕皮肤时).hyperframes/caption-skin.html作为字幕皮肤源存在。


步骤3:故事板和脚本

目标:将简报和捕获材料转化为已批准的逐帧故事计划。

阅读references/story-design.md、../hyperframes-animation/blueprints-index.md、../hyperframes-core/references/storyboard-format.md和../hyperframes-core/references/script-format.md。使用它们编写STORYBOARD.md,以及在需要旁白时编写SCRIPT.md。

使用story-design.md获取故事蓝图、钩子、说服逻辑、节拍、VO_MODE和资产选择。作为一个软指南,查阅../hyperframes-animation/blueprints-index.md中的角色→蓝图菜单:对于每个节拍,如果合适,记录一个候选蓝图ID。故事的真实性仍然决定哪些节拍存在——永远不要为了适应蓝图而强制使用某个节拍,也不要仅仅因为有可用的经过验证的形状而发明节拍。从capture/extracted/asset-descriptions.md(规范清单)中选择每个视觉帧的asset_candidates——不要浏览原始的capture/assets/。除非该清单缺失或不可用,否则不要要求用户选择资产。使用故事板和脚本参考中要求的精确字段。

草拟完成后,显示逐帧摘要。在同一消息中询问用户两件事:(a) 批准或请求更改,以及 (b) 是否想要故事板脚手架的实时预览(npx hyperframes preview)——仅在用户同意时打开它。迭代直到获得批准,并将预览选择带到步骤6。

关卡: STORYBOARD.md存在,每个视觉帧都有asset_candidates,在需要旁白时SCRIPT.md存在,并且用户已批准逐帧计划。


步骤3.1:音频

目标:根据已批准的脚本生成旁白、单词时间码、音乐和音频元数据。

在步骤3批准后开始音频处理。在后台运行它,然后继续步骤4。

node <SKILL_DIR>/scripts/audio.mjs --script ./SCRIPT.md --storyboard ./STORYBOARD.md --hyperframes . --out ./audio_meta.json &

音频脚本处理旁白、单词时间码、从HeyGen音乐库查找背景音乐以及时间元数据。背景音乐情绪来自故事板的music:字段。这使用HeyGen Audio API进行检索,而不是生成,并使用与TTS相同的~/.heygen凭据。有关提供商详细信息,请阅读../hyperframes-media/references/tts.md。

如果没有旁白且没有SCRIPT.md,则跳过语音生成。如果故事板有音乐情绪,背景音乐仍可能运行。

关卡: 音频任务已启动,或项目被标记为静音。


步骤4:帧视觉设计

目标:为每个故事板帧添加视觉方向、布局意图和运动选择。

直接编辑STORYBOARD.md。不要创建另一个故事板。使用frame.md作为颜色、字体、布局感觉和风格的真实来源。

阅读references/visual-design.md、../hyperframes-animation/blueprints-index.md、references/motion-language.md和../hyperframes-animation/rules-index.md。使用visual-design.md获取方法(带时间码的镜头序列、内联布局词汇和必需的## Video direction块)。使用../hyperframes-animation/blueprints-index.md选择每个帧的镜头形状。使用motion-language.md(运动词汇 + 运动原则)和../hyperframes-animation/rules-index.md(有效的规则名称)来指定运动——不要发明运动名称。

对于每个视觉帧,按照visual-design.md的方法在STORYBOARD.md中编写带时间码的镜头序列:选择该帧的蓝图(或组合),用当前产品的实例化它,并调整每个场景的展示节奏以适应画外音,使得帧在其整个持续时间内展开,而不是提前加载然后冻结。根据每个场景内联说明布局和运动(词汇见visual-design.md和motion-language.md)。添加一个全视频范围的## Video direction块。

不要更改故事、脚本、资产选择、asset_candidates、transition_in或捕获的源材料。在此步骤中不要编写HTML。

在视觉设计锁定后暂存命名的资产:

node <SKILL_DIR>/scripts/stage-assets.mjs --storyboard ./STORYBOARD.md --hyperframes .

关卡: 每个视觉帧都有一个带时间码的镜头序列,其展示节奏与画外音同步(没有提前加载);## Video direction存在;assets/包含命名的资产。


步骤5:构建帧

目标:将每个故事板帧构建为HTML组合,并组装可播放的视频。

如果音频已启动,请等待步骤3.1的音频完成。然后同步时长并获取音效;如果项目静音,则跳过两者。

node <SKILL_DIR>/scripts/audio.mjs sync-durations --audio-meta ./audio_meta.json --storyboard ./STORYBOARD.md

node <SKILL_DIR>/scripts/audio.mjs fetch-sfx --storyboard ./STORYBOARD.md --hyperframes .

时长同步是机械性的:真实语音时长优先;静音帧保留估计值;永远不要手动编辑同步后的时长。

在分派之前,阅读sub-agents/frame-worker.md和../hyperframes-core/references/subagent-dispatch.md。为每个帧分派一个子代理,如果可能则并行;否则,按批次运行工作器。每个工作器只负责一个帧。

每个工作器上下文必须包含PROJECT_DIR、frame_id、画布大小、字幕状态和如果启用字幕时的禁区带,以及RULES_DIR作为本技能../hyperframes-animation/rules/目录的绝对路径。每个工作器读取frame.md、来自STORYBOARD.md的其自己的## Frame N块、每个引用运动的本地规则配方(../hyperframes-animation/rules/<id>.md)以及该帧的蓝图模板(../hyperframes-animation/blueprints/<id>.md)。每个工作器只写入compositions/frames/NN-*.html。工作器绝不能编辑STORYBOARD.md。

当每个工作器返回时,编排器在STORYBOARD.md中将该帧标记为animated。

在音频时间码存在后,在后台构建字幕并组装索引:

node <SKILL_DIR>/scripts/captions.mjs build --storyboard ./STORYBOARD.md --audio-meta ./audio_meta.json --hyperframes . --out ./caption_groups.json &

node <SKILL_DIR>/scripts/assemble-index.mjs --storyboard ./STORYBOARD.md --hyperframes .

captions.mjs使用项目的.hyperframes/caption-skin.html(在步骤2中复制)作为字幕外观,注入来自frame.md的品牌令牌;如果没有皮肤存在,则渲染内置的默认药丸形状。captions: skipped (<reason>)是有效的。当明确跳过时,继续不生成字幕。

关卡: 每个帧都被标记为animated,index.html存在,并且字幕已构建或明确跳过。


步骤6:最终确定

目标:验证组装的视频,获得用户批准,并渲染最终的MP4。

注入过渡效果,运行检查,暂停以供审查,然后渲染。

node <SKILL_DIR>/scripts/transitions.mjs inject --storyboard ./STORYBOARD.md --hyperframes .

node <SKILL_DIR>/scripts/transitions.mjs verify --storyboard ./STORYBOARD.md --index ./index.html

npx hyperframes lint

npx hyperframes validate

npx hyperframes inspect

npx hyperframes snapshot --at <frame-midpoints>

snapshot将捕获的帧拼接成一张联系表(snapshots/contact-sheet.jpg)。快速浏览一下;如果没有明显问题,就继续——不要在此停留。

如果某个命令失败,输出stderr并停止——不要堆积恢复命令。自己修复它:对compositions/frames/NN-*.html进行最安全的编辑,然后重新运行失败的检查。

检查通过后,暂停以供用户审查。视频已组装完成,可在Studio中查看和编辑。在步骤3和步骤6之间只管理一次预览:如果用户之前要求过,则打开它;如果他们之前拒绝了,则提供它;如果他们已经在Studio中审查,则不要再询问。

预览:npx hyperframes preview

渲染

…

[为了翻译而截断]

Individual skills in this repo

This repo contains 13 individual skills — each has its own dedicated page.

1345AbhishekKumar/starter-supabase

Add captions to a talking-head video. ONE catalog (CATALOG.md) of 32 visual identities behind two engines: column-flow (captions composited INTO the scene — matte occlusion + mix-blend; cream/ink/editorial/keynote/documentary/loud/neon/glitch/chrome/velocity) and themed constitutions (anchor/ordnance/terminal/neonsign/stardust/stomp/scoreboard/transit/vhs/arcade/dossier/laser/thunder/hologram/biolume/aurora/spectrum/papercut/popup/chalkboard/graffiti/brush/inkwater/ransom/lastpage/nightcity — e.g. a glyph-decode climax, a neon sign WRITTEN stroke by stroke, or the quiet `anchor` rail default). Route by identity, never by mode. Trigger on "captions/subtitles", "embed/cinematic captions", "VFX captions", "炸/特效/酷炫字幕", a named identity, or top-tier motion-graphics asks. Embedding every word is wrong for most talking-head content — `anchor` is the verbatim default. Pipeline: transcription → hyperframes remove-background matting → HTML render → ffmpeg overlay. Requires hyperframes and a single-subject clip.

1345AbhishekKumar/starter-supabase

The fallback workflow for authoring custom HyperFrames video compositions at any length or format — longer or multi-scene pieces, brand / sizzle reels, montages, title cards, static loops, and freeform compositions. Input- and length-agnostic. If a specialized workflow clearly fits the input — a marketed product, a website, a topic explainer, a GitHub PR, existing footage, a short motion graphic, or a Remotion port — prefer it (see /hyperframes); use this only as the general fallback when none fit.

1345AbhishekKumar/starter-supabase

All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4 rules and compose, or load a blueprint, or look up runtime-specific API (e.g. GSAP eases / Lottie player / Three.js mixer). HyperFrames-native: single paused timeline, seek-safe, deterministic.

1345AbhishekKumar/starter-supabase

HyperFrames CLI dev loop. Use when running npx hyperframes init, add, catalog, capture, lint, validate, inspect, layout, snapshot, preview, play, render, publish, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, tts, or remove-background, or when troubleshooting the HyperFrames build/render environment. Entry point for AWS Lambda cloud rendering (`hyperframes lambda deploy / render / progress / destroy / policies`).

1345AbhishekKumar/starter-supabase

The HyperFrames composition contract — build one renderable project. Use for composition structure, the `data-*` timing attributes, `class="clip"`, tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Read before writing composition HTML.

1345AbhishekKumar/starter-supabase

Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use `hyperframes-animation`.

1345AbhishekKumar/starter-supabase

Audio and media assets for HyperFrames compositions, produced by one shared audio engine (`scripts/audio.mjs`) — multi-provider TTS (HeyGen / ElevenLabs / Kokoro local), background music + sound effects (HeyGen audio-library retrieval by default, with local Lyria / MusicGen BGM generation and a bundled SFX library as the no-credential fallback), Whisper transcription, background removal, and caption authoring. Use for voiceover / TTS, BGM, SFX / sound effects, transcription, captions / subtitles / lyrics / karaoke / per-word styling, voice + provider selection, and music-mood prompting.

1345AbhishekKumar/starter-supabase

Install and wire registry blocks and components into HyperFrames compositions. Use when running hyperframes add, installing a block or component, wiring an installed item into index.html, or working with hyperframes.json. Covers the add command, install locations, block sub-composition wiring, component snippet merging, registry discovery, and authoring a new block or component to contribute upstream (idea → scaffold → validate → PR).

1345AbhishekKumar/starter-supabase

Use when the user wants a short, design-led motion graphic where motion is the message: kinetic typography, stat or number count-up, chart/data-viz hit, logo sting, brand lockup, lower-third, callout, social overlay, animated headline/tweet/news item, motion poster, or quick captured-page highlight. Usually under 10s and up to ~30s, with no narration arc, voice-over, or live-action subject. Can render to MP4 or transparent overlay. Not for longer, multi-scene, narrated, or brand-reel pieces (use general-video), narrated website videos (website-to-video), topic explainers (faceless-explainer), product promos (product-launch-video), PR videos (pr-to-video), or captions on existing footage (embedded-captions). When unsure whether it's a quick motion-first piece or a longer / narrated treatment, see /hyperframes.

1345AbhishekKumar/starter-supabase

Use when the user has a music track (an audio file, or a video to pull audio from) and wants a beat-synced HyperFrames video, calm to hard-hitting. The music drives everything: one analyzer reads it once, the orchestrator lays out the frames and fills a per-frame plan, and one sub-agent builds each frame. Typography and templates are the floor — a complete video needs zero assets — but any images or videos the user supplies are cut into the frames on the same beat grid (beat-cut / ken-burns). The genre (lyric video, slideshow, kinetic promo) falls out of the per-frame choices; the pipeline never branches on it.

1345AbhishekKumar/starter-supabase

turn a GitHub pull request (a PR URL like github.com/<owner>/<repo>/pull/<N>, an <owner>/<repo>#<N> ref, or 'this PR' in a checked-out repo) into a code-change explainer video, up to ~3 min (sweet spot 30-90s) — changelog, feature reveal, fix, or refactor walkthrough, rendered from the diff / commits / files. The input is a CODE CHANGE read via the gh CLI; there is no website capture. Use this skill for a GitHub PR. Do not use it for a product launch/promo (use /product-launch-video), a tour of a real website (use /website-to-video), a topic explainer with no PR (use /faceless-explainer), captions on existing footage (use /embedded-captions), or a short unnarrated motion graphic (use /motion-graphics). If the intent is unclear, route through /hyperframes first.

1345AbhishekKumar/starter-supabase

Port an existing Remotion (React) composition to HyperFrames HTML. Use ONLY when the user explicitly asks to port/convert/migrate/translate a Remotion source. Do NOT use: (a) authoring a new HyperFrames composition; (b) Remotion mentioned in passing; (c) Remotion code shared as reference only; (d) "same video as my Remotion one" without explicit migrate request — treat as fresh build. Doubt → `/general-video`. One-way, Remotion-only: no reverse export (HyperFrames→Remotion or any framework), no non-Remotion source (After Effects, Framer Motion, plain React/CSS) → out of scope, re-create via `/general-video`. Flags unsupported patterns (useState, useEffect, async calculateMetadata, third-party React libs, `@remotion/lambda`) and recommends runtime interop over lossy translation. Unsure whether to port vs. build fresh, or only a passing Remotion mention? → /hyperframes.

1345AbhishekKumar/starter-supabase

Capture a general website/URL and turn it into a HyperFrames video (site tour, showcase, or social clip from the site's own visuals). Uses headless Chrome screenshots + brand assets. Use when intent is general — portfolio/blog/landing-page showcase or social clip from the site. NOT for: product/SaaS launch or promo (→ /product-launch-video, even from a URL); topic explainer with no site (→ /faceless-explainer); GitHub PR (→ /pr-to-video); adding captions to existing video (→ /embedded-captions); short unnarrated page-highlight motion graphic (→ /motion-graphics). Unclear launch-vs-general-site? Ask one question or start at /hyperframes.

相关技能