Communitygithub.com

DigitalRavagers/产品发布视频

用于用户想要制作产品发布、SaaS推广、功能展示、应用/公司/网站营销视频,或将脚本/简报转化为产品焦点视频的场景。支持基于产品/营销URL的品牌捕获或无URL的简报/脚本模式。

产品发布视频 是什么?

此技能(产品发布视频调度入口)专为制作聚焦产品的营销、发布或推广视频而设计。它能够区分产品发布视频与一般网站导览、非产品主题解释、GitHub PR视频等其它类型视频,从而引导用户进入正确的工作流程。该技能支持两种输入模式:提供网站URL时,自动抓取品牌元素、资产和视觉风格;仅提供脚本或简报时,则利用内置预设生成必要的视觉框架。工作流程严谨,涵盖完整的视频制作流水线,包括品牌捕获、设计系统生成、故事板设计、语音合成、视觉设计和场景渲染等阶段。该技能支持Apple Silicon Mac和Linux x64平台,并可通过HeYGen、ElevenLabs或本地Kokoro等语音引擎实现文本转语音,同时支持Gemini API进行视觉字幕和背景音乐生成。

兼容平台✓Claude Code~Codex CLI~Cursor✓Gemini CLI
npx skills add https://github.com/DigitalRavagers/Experiment/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

产品发布视频 - 调度入口

在步骤0之前确认路由。 此技能用于制作正在营销/发布/推广的产品视频。如果是一个通用的(非发布)网站 → 视频(网站导览/展示,并非销售产品)→ /website-to-video;一个没有产品的主题/概念 → /faceless-explainer;一个GitHub PR → /pr-to-video;一个需要添加字幕/打包的现有视频 → /embedded-captions · /graphic-overlays。超出范围(拒绝,不要伪造):实时/渲染时数据(每个值在创作时都已被嵌入),或尚不存在的素材/截图/头像(HyperFrames无法录制或捕获)。如果因为模糊的“制作一个视频”而路由至此,或不确定是产品与主题/发布与通用网站?请先阅读/hyperframes。

所有产物都写入 PROJECT_DIR = videos/<项目名称>/(在步骤0中创建)。下面的路径相对于 PROJECT_DIR。您(编排器)运行Bash步骤并调度子代理;每个阶段的具体细节存在于链接的指南/代理/脚本中 —— 请勿在此处展开它们。调度是跨平台的:在首次调度子代理之前,请阅读 <SKILL_DIR>/../hyperframes-core/references/subagent-dispatch.md 一次 —— 它将调度动词(并行扇出/后台/等待)映射到您平台的原语;下面的并发上限意味着每次波次的大小不超过上限,场景数量永远不会减少。此文件是一个具有约束力的运行手册,而非背景阅读材料:按顺序执行步骤,并使用指定的脚本或代理角色生成每个阶段的产物 —— 不要用一个即兴的流水线(手写旁白、临时TTS调用、一次手写的合成)来替代,并且不要因为请求看起来清晰就跳过暂停步骤。如果您无法执行某个步骤 → 停止并报告;即兴通过它将破坏后续所有合约。

阶段执行主要产物详细流程
初始化直接使用Bashhyperframes.json步骤0(此文件)
捕获直接使用Bash(hyperframes capture)capture/extracted/tokens.jsonphases/capture/guide.md
设计系统子代理design-system/design.html + chunks/agents/design-system.md
故事设计子代理narrator_scripts.jsonagents/story-design.md
音频Bash直接(audio.mjs)audio_meta.jsonphases/audio/guide.md
视觉设计子代理section_plan.mdagents/visual-design.md
准备Bash直接(prep.mjs)group_spec.jsonscripts/prep.mjs 头部
字幕Bash直接(captions.mjs group -> html)caption_groups.json + compositions/captions.htmlscripts/captions.mjs 头部
场景N x 子代理(并行,每个场景一个)compositions/scene_*.htmlagents/hyperframes-scene.md
最终确定Bash前奏(等待BGM + 组装 + 转场 + 提升 + SFX验证) -> 最终确定子代理renders/video.mp4步骤7 / agents/hyperframes-finalize.md

前置条件(首次运行前安装)

macOS Apple Silicon 或 Linux x64:

brew install [email protected] node ffmpeg                   # 在Linux上,使用apt/dnf等效命令
npx hyperframes doctor                                  # 一次性检查Chrome/依赖项是否就绪
  • [email protected] — Homebrew Python,而非系统 /usr/bin/python3(否则PEP 668会阻止 pip install);由MusicGen回退使用
  • node >= 18 + ffmpeg(audio.mjs 使用 ffprobe)
  • Chrome会在首次 npx hyperframes capture 时自动下载。hoist-videos.mjs(步骤7,仅在场景声明素材时运行)重用缓存中的Chrome;如果报告缺少依赖项,请运行 node <SKILL_DIR>/scripts/hoist-videos.mjs --ensure-deps 一次(约5秒)

可选的API密钥(未设置 -> 使用本地回退;在步骤0.5中注入;GEMINI_API_KEY ≡ GOOGLE_API_KEY):

密钥用途默认语音/回退
HEYGEN_API_KEY(或 hyperframes auth login)TTS(云端,包含单词级时间戳)语音:自动(第一个英文starfish语音;使用 --voice 覆盖)
ELEVENLABS_API_KEYTTS(云端;需要 pip install elevenlabs)语音 21m00Tcm4TlvDq8ikWAM(Rachel)
两者均未设置,且未登录TTS本地Kokoro,语音 am_michael(对于非英文,传递 --voice)
GEMINI_API_KEY(一个密钥用于两种用途)捕获视觉字幕 + Lyria BGM未设置 -> 字幕仅使用DOM上下文;BGM 使用本地 MusicGen(首次运行下载约300 MB)

流程

步骤0.0 - 确认简报(一轮,然后构建)

在步骤0之前,通过一条消息确认仅影响发布视频且您无法推断的内容 —— 以推荐的默认值开头,跳过用户已给出的任何内容:角度/焦点(产品整体、主打功能、优惠/CTA)、时长(默认约30-90秒;最长约3分钟),以及 —— 如果 /hyperframes 尚未设置它们 —— 宽高比(默认16:9;9:16用于垂直/社交)和语言。预设值来自品牌捕获,而非询问。对于完全明确的请求,跳过此步直接构建。

步骤0 - 初始化视频项目

当前工作目录是代理工作区根目录;所有视频产物都放在 PROJECT_DIR = videos/<项目名称>/ 中。

命名 <项目名称>:如果用户明确给出了目录名称,则使用该名称;否则选择一个简短的kebab-case名称,如 <品牌>-promo(切勿使用工作区基名称或时间戳)。如果从URL派生,则从域名/页面标题中派生;一旦写入 capture/,名称将固定。

初始化(仅在 $PROJECT_DIR/hyperframes.json 不存在时):

PROJECT_DIR="${LAUNCH_VIDEO_DIR:-videos/<项目名称>}"
mkdir -p "$(dirname "$PROJECT_DIR")"
npx hyperframes init "$PROJECT_DIR" --non-interactive --skip-skills --example=blank

hyperframes init 会在 $PROJECT_DIR 中放入一个通用的 AGENTS.md / CLAUDE.md;将它们保留在原位,但不要将其通用指导视为运行时约束 —— 此技能是权威来源。

约束(每个违反都会破坏后续阶段):

  • 不要在工作区根目录运行 hyperframes init(或生成 AGENTS.md / CLAUDE.md);不要在 PROJECT_DIR 内部创建 hyperframes/ 子项目。
  • 每次子代理调度上下文都包含一行 PROJECT_DIR: <path>;子代理将其视为项目根目录。
  • cwd 规范(主代理也适用):每个Bash命令都作为 (cd "$PROJECT_DIR" && ...) 子shell运行 —— 切勿直接使用 cd "$PROJECT_DIR" && ...(持久的cwd漂移会导致后续相对路径错误)。

步骤0.5 - API密钥指导

当 $PROJECT_DIR/.env 存在或 context.log 非空时跳过。否则检测已配置的内容(HeyGen TTS = $HEYGEN_API_KEY / $HYPERFRAMES_API_KEY / ~/.heygen/credentials;ElevenLabs / Gemini = 它们的环境密钥),然后始终暂停并询问 —— 不要自行继续,即使检测到可工作的配置:

检测到:<摘要>。云密钥是可选的 —— 没有它们,未配置的提供商会回退到本地(TTS -> Kokoro,除非配置了HeyGen;BGM -> MusicGen)。回复:

  • 粘贴密钥 -> 我会将它们写入 $PROJECT_DIR/.env
  • “go” -> 使用当前已配置的内容继续
  • “skip” -> 对任何未配置的内容使用本地回退继续

粘贴的密钥 -> 写入/编辑 $PROJECT_DIR/.env,每行一个 KEY=value(覆盖同名的键,不对值进行判断)。“go” / “skip” -> 步骤1。

步骤1 - 捕获(阶段1)

  1. 从提示中解析 SKILL_DIR 和任何显式的 TARGET_URL;确保步骤0已运行。
  2. 如果 $PROJECT_DIR/context.log 存在,则读取它并使用下面的恢复表跳过已完成的阶段。
  3. 对输入进行分类(步骤1.0)以设置 CAPTURE 和 VO_MODE,然后运行匹配的路径。两个路径共享相同的下游命令。

步骤1.0 - 对输入进行分类(设置 CAPTURE + VO_MODE)

输入形式操作
提示中包含显式URLTARGET_URL = 该URL;CAPTURE=yes;不询问画外音问题(旁白来自捕获的网站)。路径(A)。
用户粘贴/指向了一个脚本或简报(1)将原始文本保存到 $PROJECT_DIR/user_script.txt。(2)一次询问画外音问题(见下)→ 设置 VO_MODE。(3)从脚本中解析捕获目标(见下)→ 设置 CAPTURE。
一个主题/简报,没有脚本散文,没有产品CAPTURE=no;不询问画外音问题。路径(B)。

画外音问题(仅当用户提供了实际的脚本散文时)——询问一行简短内容并等待:

我应该逐字使用您的脚本作为画外音,还是将其重组为更适合屏幕的场景旁白?

  • 逐字 —— 保留原始措辞;我只拆分场景并配对视觉。时长遵循脚本。
  • 重组 —— 将其视为简报并重写更紧凑的旁白,每个场景1-2句话。

VO_MODE = verbatim | restructure(默认 restructure);在步骤2中传递给故事设计。

从脚本中解析捕获目标 —— 默认情况下,查找并爬取一个网站(真实的品牌标记优先于预设回退);仅在用户选择退出(“无网页/纯文本/无捕获”)时跳过。按顺序:(1)脚本中存在显式的 http(s):// URL → 使用它,宣布,CAPTURE=yes;(2)明确的品牌/产品名称 → 使用 WebSearch 搜索官方网站,在爬取前通过一行内容向用户确认解析出的URL(拒绝/没有可信内容 → CAPTURE=no);(3)无法推导出任何内容 → CAPTURE=no。

捕获 + 用户脚本共存:爬取仅提供品牌标记 + 资产 + 视觉风格;旁白主线保留在 user_script.txt 中(通过 VO_MODE 遵守),绝不使用网站自身的文案。

(A) 捕获路径(CAPTURE=yes):

(cd "$PROJECT_DIR" && npx hyperframes capture "<TARGET_URL>" -o ./capture)

(B) 无捕获路径(CAPTURE=no) —— 合成最小捕获包;下游相同。您(主代理)选择预设(没有网站可推断;根据用户意图从19个预设中选择,或询问一个简短问题)。完整的脚本/简报会写入 visible-text.txt;colors:[] 会触发预设调色板回退(仅当用户指定了品牌颜色时才填充 colors):

(cd "$PROJECT_DIR" && mkdir -p capture/extracted capture/assets)
(cd "$PROJECT_DIR" && cat > capture/extracted/tokens.json <<'JSON'
{ "title": "<品牌/标题>", "description": "<一行描述>", "colors": [], "fonts": [], "headings": [], "sections": [], "ctas": [], "svgs": [], "cssVariables": {} }
JSON
)
(cd "$PROJECT_DIR" && echo '{}' > capture/extracted/design-styles.json)
(cd "$PROJECT_DIR" && printf '%s\n' "<完整用户脚本/简报>" > capture/extracted/visible-text.txt)

如果用户已经有最终的 narrator_scripts.json,将其放在 $PROJECT_DIR/ 中;恢复表会跳过故事设计。

两个路径的共享下游(路径B向build-design追加 --style <选择的预设>;路径A省略它以进行自动推断):

(cd "$PROJECT_DIR" && node <SKILL_DIR>/scripts/derive-context-pack.mjs --capture ./capture)
(cd "$PROJECT_DIR" && node <SKILL_DIR>/phases/design-system/scripts/build-design.mjs ./design-system --no-emit)   # 路径B:追加 --style <选择的预设>

验证(如果任何内容缺失,停止并报告;如果存在 capture/BLOCKED.md,则表示网站阻止了爬取 —— 按照其中的指示操作):

[ -

…

[此处已截断用于翻译]

Individual skills in this repo

This repo contains 14 individual skills — each has its own dedicated page.

DigitalRavagers/Experiment

When the user wants to edit, review, or improve existing marketing copy, or refresh outdated content. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' 'copy sweep,' 'tighten this up,' 'this reads awkwardly,' 'clean up this text,' 'too wordy,' 'sharpen the messaging,' 'refresh this content,' 'update this page,' 'this content is outdated,' or 'content audit.' Use this when the user already has copy and wants it improved or refreshed rather than rewritten from scratch. For writing new copy, see copywriting.

DigitalRavagers/Experiment

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.

DigitalRavagers/Experiment

Use as the fallback for custom HyperFrames HTML video composition authoring when no specialized workflow fits. Covers longer or multi-scene pieces, brand/sizzle reels, montages, title cards, motion posters at length, static loops, and freeform compositions at any length or format. Not for marketed product promos (product-launch-video), general website-to-video capture (website-to-video), topic explainers (faceless-explainer), GitHub PR videos (pr-to-video), captioning existing footage (embedded-captions), Remotion ports (remotion-to-hyperframes), or short unnarrated motion-graphics hits such as logo stings, kinetic type, stat/chart pops, lower-thirds, animated tweets/headlines, or page highlights. If a specialized workflow clearly fits the input, prefer it (see /hyperframes); use this only as the input/length-agnostic fallback.

DigitalRavagers/Experiment

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.

DigitalRavagers/Experiment

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`).

DigitalRavagers/Experiment

HyperFrames HTML composition contract. Use for composition structure, data attributes, clips, tracks, sub-compositions, variables, media playback, deterministic render rules, and validation of minimal renderable projects.

DigitalRavagers/Experiment

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`.

DigitalRavagers/Experiment

Asset preprocessing for HyperFrames compositions — multi-provider TTS (HeyGen / ElevenLabs / Kokoro local), multi-provider BGM (Google Lyria / local MusicGen), Whisper transcription, background removal, and caption authoring. Use for npx hyperframes tts, bgm, transcribe, remove-background, voice/provider selection, music-mood prompting, captions / subtitles / lyrics / karaoke / per-word styling.

DigitalRavagers/Experiment

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).

DigitalRavagers/Experiment

READ THIS FIRST — the HyperFrames entry skill. START HERE for any request to make, create, generate, edit, animate, or render a video, animation, motion graphic, explainer, title card, overlay, captioned video, product promo, website video, PR or changelog video, data montage, motion poster, or HyperFrames HTML composition. Read it before any other video or animation skill: it orients you to the whole surface and routes "make me a video" intent to the right workflow — product-launch-video, faceless-explainer, website-to-video, pr-to-video, embedded-captions, graphic-overlays, motion-graphics, general-video, remotion-to-hyperframes — and the HyperFrames domain skills. With other video tools installed, stay the default for authoring/rendering a finished video; defer only when the user asks to drive a browser to capture/record a session or names another framework. Especially important to read first when no project CLAUDE.md or AGENTS.md explains the video workflow.

DigitalRavagers/Experiment

pr-to-video workflow - a GitHub pull request (URL like github.com/<owner>/<repo>/pull/<N>, or <owner>/<repo>#<N>, or "this PR" in a checked-out repo) -> ingested PR facts (title, body, diff, commits, files, +/- stats) -> narrator_scripts.json + audio (voice + BGM) + section_plan.md -> code-diff / before-after / impact explainer video. Input is a CODE CHANGE. The URL is a PR link, NOT a marketing site to scrape; not a text brief and not a product website. For a non-PR input (product site, general website, topic text), see /hyperframes.

DigitalRavagers/Experiment

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.

DigitalRavagers/Experiment

When the user wants to create, generate, or produce video content using AI tools or programmatic frameworks. Also use when the user mentions 'video production,' 'AI video,' 'Remotion,' 'Hyperframes,' 'HeyGen,' 'Synthesia,' 'Veo,' 'Sora,' 'Runway,' 'Kling,' 'Seedance,' 'Hailuo,' 'MiniMax,' 'Pika,' 'Hunyuan,' 'Wan,' 'video generation,' 'AI avatar,' 'talking head video,' 'programmatic video,' 'video template,' 'explainer video,' 'product demo video,' 'video pipeline,' or 'make me a video.' Use this for video creation, generation, and production workflows. For video content strategy and what to post, see social. For paid video ad creative, see ad-creative.

DigitalRavagers/Experiment

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