Communitygithub.com

NeverSight/learn-skills.dev

用于制作、执导或挽救产品发布视频、宣传片、预告片、演示集锦、功能公告影片或由代码构建的动画产品解说——并且当现有视频看起来粗糙、像幻灯片、揭示与画外音不同步、光标不可见、音效听不清、混音被剪切或过于安静、或者每个视频出来都千篇一律时使用。涵盖SaaS、应用、硬件、电子商务、开发工具、服务。关键词包括动态设计、故事板、画外音同步、动态文字、GSAP、HyperFrames、Remotion、胶片颗粒、LUFS、ffmpeg。

learn-skills.dev 是什么?

该技能将产品发布视频的制作从幻灯片式的简单组装提升为一种专业的电影制作工艺。它详细阐述了十条核心法则,涵盖从素材真实性、逐字同步、渲染确定性,到镜头语言、声音测量和配色策略等各个方面。该技能提供了一个完整的14步流水线,包括脚本编写、画外音录制、逐字时间码提取、基于GSAP的动画构建,以及通过HyperFrames或Remotion等可定位时间线的渲染器进行确定性渲染。此外,它还包含一套故障排查的“红旗”警示列表和一系列脚本,用于自动化组装、转场、音频挂载和调色,确保最终的MP4输出具有专业电影级质感,且不同作品之间风格鲜明。

兼容平台~Claude Code~Codex CLI✓Cursor
npx skills add https://github.com/NeverSight/learn-skills.dev/tree/HEAD/data/skills-md/abubakrchan/product-launch-motion/product-launch-motion

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

产品发布动态设计 (Product Launch Motion)

一种制作发布影片的专业工艺,使影片看起来像是专业动态设计师的作品——而不是带有画外音的幻灯片。

输出是一个渲染后的MP4文件。媒介是HTML、CSS和GSAP,由基于确定性查找的渲染器(默认是HyperFrames)逐帧渲染。这里的所有内容都可以移植到任何能够定位时间线的渲染器上;规则与渲染器无关,具体的流程示例基于HyperFrames。

此技能之所以存在,是因为好的工具不等于好的电影。 一个合成可能通过代码检查、无错渲染,但仍然是一个幻灯片。以下是区分这两者的工艺价值,以及那些需要花费大量时间才能发现的陷阱——每一个都附有证明其存在的测量数据,而非主观感受。

这是一套工艺,而不是一个模板。 以下法则是固定的;但外观不是固定的,决定外观是你作为导演的工作。使用此技能制作的两部影片应该截然不同——不同的配色、基底、镜头个性、字体、纹理、声音和结构——因为它们为不同的观众讲述不同的主张。在构建任何内容之前,先写下三种真正不同的视觉方向,然后淘汰两个:references/11-creative-direction.md。因为此处有文档记录就照搬参考影片的外观,这是唯一一种会使其他所有工作都变得毫无价值的失败模式。

何时使用此技能

适用于:产品发布或功能公告影片(20-90秒)、着陆页主视觉视频、演示集锦、会议宣传片、投资者更新影片,或对“看起来很基础”的视频进行挽救性修改。

不适用于:人物访谈剪辑、仅添加字幕的屏幕录制,或交付物是实时网页而非视频文件的任何内容。

十大法则

违反其中任何一条,影片都会显得业余,无论单个帧有多好。请注意它们未涉及的内容:没有一条会告诉你影片应该是什么样子。

1 · 真实至上。 屏幕上的每个数字、标志、面孔、截图和推荐都必须真实且来源可靠。在任何动画开始之前,写下已批准的数值——允许出现的精确数字列表——并拒绝所有其他数字。虚构的指标和库存面孔是让真实产品看起来虚假的最快方式。 → references/02-story-and-truth.md

2 · 逐字同步。 每一个揭示动画都与它所说明的那个词的实际开始时间精准同步。不是对准节拍网格,不是估计——而是基于实际画外音文件的逐字时间轴。t=0时刻的帧只能显示画外音在t=0时刻所说的内容。 → references/03-word-locked-sync.md

3 · 确定性。 不使用Math.random、Date.now、CSS过渡、repeat/yoyo。任何分散或带噪声的值都必须基于索引或播放头推导。在时间T进行定位必须产生字节一致的输出,否则你的渲染就是一场抽奖。 → references/01-renderer-contract.md

4 · 一个镜头,两个节点。 全景旋转和中景缩放必须位于不同的元素上。如果放在同一个元素上,它们会争夺同一个变换矩阵,导致动作抖动。外层节点 = 推拉(缩放),内层节点 = 3D旋转(旋转 + 透视)。 → references/05-camera-3d-cursor.md

5 · 光标是舞台道具。 一个真实大小的指针(1920分辨率下约32px)会在任何饱和度高的控件上消失。将其绘制成约44x54像素,带有粗描边和深阴影,将其放置在镜头移动的节点内部,并将缩放原点精确设置在其点击的控件上——这样该点就成为变换的固定点,瞄准在推动时得以保持,无需额外的数学补偿。 → references/05-camera-3d-cursor.md

6 · 声音是算术,不是感觉。 提示的音量无法挽救一个过轻的源文件。如果音频素材比叙述背景低20分贝,提高其音量只能使混音改变零点几分贝——这是测量出来的,不是猜的。先对素材进行电平调整,再验证提示是否在交付文件中达到预期效果。 → references/07-sound-and-master.md

7 · 任何结束都不要在运动中。 每个镜头都必须有结束状态。动作为意义服务;一个镜头在切换时仍在飘移,看起来像屏保;同样,一个镜头内所有元素独立飘移也是如此。范围: 这规定的是结束状态,而非静止状态。一个一镜到底的影片,只要在结束前减速至静止,就满足此法则;一个刻意保持缓慢移动而其内容已经稳定的镜头也满足。它所禁止的是,当镜头正在阐述的内容尚未完成时进行切换。 → references/04-motion-grammar.md

8 · 节制使用强调色。 两种基底(一种用于论点,一种用于产品),一种强调色或渐变,以及一个书面预算,说明允许使用的位置——通常是:每个标题的一个强调词、统计数字、活动步骤、状态切换、行动号召按钮。第三种色调几乎总是错误的。 → references/06-look-and-grade.md

9 · 绿闸(自动化检查)是必要条件,非充分条件。 代码检查、布局和对比度检查都无法捕捉到使电影变差的大部分问题。每次渲染后,从交付的文件中提取你修改过关键帧的帧,查看它们,并在其他人之前记录下问题所在。 → references/08-qa-and-direction.md

10 · 没有公司内部风格。 外观必须源于当前产品的卖点、品牌、受众和品类——决不能继承自上一步影片或本仓库中的示例。写出三种不同的方向,选择一个,并赋予影片一个其他任何影片都没有的标志性动作。一部只需替换logo就能成为竞争对手产品的影片,说明它没有方向。 → references/11-creative-direction.md

警示红旗

这些是跳过步骤前常有的想法。每一个都是停止并去做你正试图说服自己不做的事情的信号。

想法实际含义
“我先估计一下时间,稍后再精确调整”你不会的。每个提示都会错,重新推导所有时间点比现在做一次成本更高
“这个项目写三个方向有点多余”你只有一个想法,并且没有依据相信它是好的。三个方向中的两个本就是要被淘汰的
“品牌色是紫色,所以这个调色板没问题”检查一下你是从产品推导出来的,还是从此处的示例继承来的
“听起来没问题”你是在渲染它的机器上听的,音量是你选的,并且你知道要听什么。用数据测量它
“修改在源文件里,所以影片里也有了”此仓库历史中记录的两个bug正是这种情况。请从交付文件中采样验证
“自动化检查通过了”检查能发现错误,但发现不了平庸。它们从未发现过一部无聊的影片
“只是个小调整,不需要重新验证”小调整正是导致-14 LUFS母带变成被剪切状态的原因
“我直接覆盖上一次的渲染结果”这样你就无法证明修复有效,而且导演更喜欢的老版本也找不回来了
“他们说做成3D效果,那我加个旋转”把这个需求当作一个症状,而不是一个规格说明。“做成3D效果”意味着需要搭建摄像机支架、重建光标和重构坐标
“我最后再加摄像机运动”摄像机运动改变了每个坐标的含义。后期添加支架意味着要重新调整镜头中的每个位置
“已经差不多对得上词了”200毫秒的偏差对于一个说不上为什么的观众来说,感觉就是延迟

违反法则的字面意思就是违反法则。“大部分确定性”就是非确定性;“大致对得上词”就是不对词。

工作流

十四个步骤。不要跳过1、2、5或13——它们是人们经常跳过的,并且它们决定了影片的好坏。

步骤1-3是一个循环,而非顺序:方向取决于哪些真实资产可用,而真实性检查往往会直接否决某个方向(你无法为一个尚未生产的产品拍摄锐利光影的产品影片)。循环这几个步骤直到它们达成一致,然后继续。

#步骤输出参考
1信息收集 — 产品、受众、核心主张、角度(通常是产品自身的标题)BRIEF.mdassets/BRIEF.md
2方向设定 — 三种真正不同的视觉方向,评估并选定一个,加上标志性动作方向区块references/11-creative-direction.md
3真实性检查 — 收集真实资产、真实截图、真实客户,修正已批准的数值列表assets/, 数值列表references/02-story-and-truth.md
4脚本 — 40-60秒,为听觉而写;每个节拍一个子句;核心主张在头10秒内出现SCRIPT.mdreferences/02-story-and-truth.md
5画外音 — 在构建任何东西之前渲染或录制画外音;帧时长来自真实的画外音长度assets/voice/*.wavreferences/03-word-locked-sync.md
6逐词时间码 — 使用逐字时间戳转录并生成提示表audio_meta.jsonscripts/word-timings.mjs
7故事板 — 帧、时长、来自你方向设定中的映射表,以及每个节拍一个镜头STORYBOARD.mdreferences/09-shot-catalog.md
8构建帧 — 每帧一个HTML文件;基于骨架的摄像机支架和光标;每个补间动画都与一个词对应compositions/frames/*.htmlreferences/04-motion-grammar.md
9组装 — 索引、转场、音频、调色 — 按此顺序,每次不变index.htmlreferences/01-renderer-contract.md
10绿闸(自动化检查) — 代码检查/运行时/布局/运动,启用调色;禁用调色时对比检查0个错误references/08-qa-and-direction.md
11渲染 + 母带处理 — 两次动态标准化、限制器、重新编码renders/*.mp4scripts/master.sh
12在交付文件中验证 — 检查修改过关键帧的帧,测量提示电平证据scripts/verify-cue.sh
13导演审查 — 观看影片,自己列出缺陷,修复,作为新文件重新渲染v2, v3, …references/08-qa-and-direction.md
14交付套装 — 竖版剪辑、字幕、海报、循环、静帧、许可证deliverables/references/12-deliverables.md

构建顺序(步骤9)不容协商

索引是生成的,因此任何手动添加的内容在重新组装时都会被破坏,必须重新注入。此处的每个接线脚本都是幂等的(它会替换自己的标记块),因此安全的做法始终是重新运行整个链:

node scripts/assemble.mjs        # film.json + 测量后的VO → index.html
node scripts/transitions.mjs     # 帧之间的过渡
node scripts/wire-audio.mjs      # 背景音乐 + 与词同步的SFX提示
node scripts/wire-grade.mjs      # 胶片颗粒 + 暗角 + 高光扫掠

assemble.mjs读取film.json(assets/film.example.json是一个填充完成的示例),并使用ffprobe从其画外音中测量每一帧的长度,这样你就永远不需要手动输入时长。它应用了每个下游提示所依赖的算术:保持时间 = VO结束时间 + 填充时间——最后一个单词后的呼吸时间,因为若镜头在最后一个音节处切换会显得匆忙——以及持续时间 = 保持时间 + 出场转场时间。下一帧从保持时间开始,而非从持续时间开始;其差值即为转场所需的重叠时间。

参考文件索引

只加载当前步骤需要的文件。

文件内容
references/11-creative-direction.md请先阅读此文件。 什么是固定的,什么是自由的,方向设定拨盘,从产品推导外观,发散至三个方向,标志性动作,五个已制定方向的示例,以及避免雷同的检查方法
references/01-renderer-contract.mdHTML如何变成视频:时间轨道、可定位的时间线、确定性规则、构建顺序,以及如何在Remotion上操作
references/02-story-and-truth.md角度、情节弧线、映射表、已批准数值的纪律、真实性规则,以及如何为任何产品获取真实资产
references/03-word-locked-sync.md获取逐词时间码,编写提示表,节奏把控,停顿,以及为何画外音优先
references/04-motion-grammar.md缓动、入场、交错、预期动作、速度变化、动态文字,以及两种失败模式(幻灯片/屏保)
references/05-camera-3d-cursor.md双节点摄像机支架、转盘、推拉、缩放至细节、跟焦、Z轴视差,以及完整的假光标规格
references/06-look-and-grade.md调色板节制、无backdrop-filter的玻璃边框、胶片颗粒、暗角、高光扫掠,以及混合模式陷阱
references/07-sound-and-master.mdSFX设计、亚低频、主角节拍前的静默、音量算术定律、素材电平调整,以及母带处理链
references/08-qa-and-direction.md绿闸(自动化检查)、快照审查、验证交付文件,以及将v1转变为v7的导演循环
references/09-shot-catalog.md14种可供改编的镜头结构——提示/组合视图、结果列表、工作区、流水线追踪器、统计数据计数、推荐、对比、硬件主角、终端、地图、图表、结束卡片。绝不是一个可以照搬的执行顺序
references/10-traps.md我们遇到过的每一个陷阱,每个都附有证明其存在的测量数据。调试任何问题前请阅读此文件
references/12-deliverables.md实际交付的套装:竖版重新布局、平台安全区域、基于现有时间码的字幕、海报帧、循环、命名和交接事项

脚本

所有脚本都是依赖轻量的Node/bash,所有脚本都是幂等的,所有脚本都可以安全地重新运行。

脚本功能
scripts/assemble.mjs从film.json生成index.html,通过测量每帧画外音的长度来确定帧时长,而不是让你去猜测
scripts/transitions.mjs在每帧画外音结束的瞬间,注入帧间过渡——淡入淡出、缩放穿越、推动、剪切
scripts/wire-audio.mjs将背景音乐轨道和一个包含SFX的提示表挂载到已组装的索引中,根据实际帧开始时间解析帧相对提示时间
scripts/wire-grade.mjs注入影片调色:基于播放头位置生成的颗粒、暗角,以及在你指定的时间出现的高光扫掠(--sweeps 7.9:0.9,…;如果未传递参数,则无扫掠)

Individual skills in this repo

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

NeverSight/learn-skills.dev

Use when generating or modifying Remotion video code, creating demo videos, or working with the demo-video/ directory

NeverSight/learn-skills.dev

Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ languages, emotion steering for characters), ElevenLabs, Kokoro. Capabilities: audio-driven avatars, text-to-avatar, lipsync videos, talking head generation, virtual presenters, UGC content. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos, UGC ads, gaming avatars, NPC dialogue. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson, audio driven video, heygen alternative, synthesia alternative, talking avatar, lip sync, video avatar, ai presenter, digital human, ugc, ugc video, ugc ad, avatar ugc

NeverSight/learn-skills.dev

Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover. Types: product demos, testimonials, explainers, social ads, brand videos. Use for: Facebook ads, YouTube ads, product launches, brand awareness. Triggers: marketing video, ad video, promo video, commercial, brand video, product video, explainer video, ad creative, video ad, facebook ad video, youtube ad, instagram ad, tiktok ad, promotional video, launch video

NeverSight/learn-skills.dev

Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse

NeverSight/learn-skills.dev

ElevenLabs automatic dubbing - translate and dub audio/video into 29 languages while preserving speaker voice via inference.sh CLI. Capabilities: auto speaker detection, voice-preserving translation, video dubbing, audio localization. Use for: content localization, video translation, multilingual content, international distribution. Triggers: dubbing, dub video, translate audio, video translation, audio translation, localize content, elevenlabs dubbing, eleven labs dub, multilingual dub, voice translation, auto dub, language dub, content localization

NeverSight/learn-skills.dev

Explainer video production guide: scripting, voiceover, visuals, and assembly. Covers script formulas, pacing rules, scene planning, and multi-tool pipelines. Use for: product demos, how-it-works videos, onboarding videos, social explainers. Triggers: explainer video, how to make explainer, product video, demo video, video production, video script, animated explainer, product demo video, tutorial video, onboarding video, walkthrough video, video pipeline

NeverSight/learn-skills.dev

Still-to-video conversion guide: model selection, motion prompting, and camera movement. Covers Wan 2.5 i2v, Seedance, Fabric, Grok Video with when to use each. Use for: animating images, creating video from stills, adding motion, product animations. Triggers: image to video, i2v, animate image, still to video, add motion to image, image animation, photo to video, animate still, wan i2v, image2video, bring image to life, animate photo, motion from image

NeverSight/learn-skills.dev

Generate talking head avatar videos with Pruna P-Video-Avatar via inference.sh CLI. Turn a portrait image into a realistic speaking video with built-in TTS. 18x faster and 6x cheaper than competitors. Models: P-Video-Avatar, P-Image (for portrait generation). Capabilities: text-to-avatar, audio-driven avatars, 30 voices, 10 languages, 720p/1080p, built-in TTS, dynamic backgrounds, full-body control. Use for: AI presenters, product demos, explainer videos, virtual influencers, marketing, education, multilingual content, UGC, gaming avatars. Triggers: avatar video, talking head, ai avatar, p-video-avatar, pruna avatar, video avatar, ai presenter, digital human, virtual presenter, lipsync, talking avatar, ai spokesperson, heygen alternative, synthesia alternative, veed alternative, fabric alternative, omnihuman alternative

NeverSight/learn-skills.dev

Generate videos with Pruna P-Video and WAN models via inference.sh CLI. Models: P-Video, WAN-T2V, WAN-I2V. Capabilities: text-to-video, image-to-video, audio support, 720p/1080p, fast inference. Pruna optimizes models for speed without quality loss. Triggers: pruna video, p-video, pruna ai video, fast video generation, optimized video, wan t2v, wan i2v, economic video generation, cheap video generation, pruna text to video, pruna image to video

NeverSight/learn-skills.dev

Render videos from React/Remotion component code via inference.sh. Pass TSX code, get MP4. Supports all Remotion APIs: useCurrentFrame, useVideoConfig, spring, interpolate, AbsoluteFill, Sequence. Configurable resolution, FPS, duration, codec. Use for: programmatic video generation, animated graphics, motion design, data-driven videos, React animations to video. Triggers: remotion, render video from code, tsx to video, react video, programmatic video, remotion render, code to video, animated video, motion graphics code, react animation video

NeverSight/learn-skills.dev

Video ad creation with exact platform-specific specs for TikTok, Instagram, YouTube, Facebook, LinkedIn. Covers dimensions, duration limits, AIDA framework, and caption requirements. Use for: video ads, social media ads, paid media creative, video marketing, ad production. Triggers: video ad, social media ad, tiktok ad, instagram ad, youtube ad, facebook ad, linkedin ad, video creative, ad specs, paid media, video marketing, ad production, reels ad, stories ad, pre roll, bumper ad

NeverSight/learn-skills.dev

Best practices and techniques for writing effective AI video generation prompts. Covers: Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora prompting strategies. Learn: shot types, camera movements, lighting, pacing, style keywords, negative prompts. Use for: improving video quality, getting consistent results, professional video prompts. Triggers: video prompt, how to prompt video, veo prompts, video generation tips, better ai video, video prompt engineering, video prompt guide, video prompt template, ai video tips, video prompt best practices, video prompt examples, cinematography prompts

NeverSight/learn-skills.dev

YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression psychology, and A/B testing. Use for: YouTube thumbnails, video cover images, click-through optimization. Triggers: youtube thumbnail, thumbnail design, video thumbnail, click through rate, ctr optimization, youtube cover, video cover image, thumbnail maker, thumbnail tips, youtube design, video preview image

NeverSight/learn-skills.dev

Landing page conversion optimization with layout rules, hero section design, and CTA psychology. Covers above-the-fold formula, social proof placement, mobile design, and F-pattern reading. Use for: startup landing pages, product pages, SaaS marketing, conversion optimization. Triggers: landing page, hero section, above the fold, conversion optimization, landing page design, cta button, hero image, landing page layout, saas landing page, product page design, conversion rate, landing page best practices

NeverSight/learn-skills.dev

Configure and use the hosted YouTube Data MCP end-to-end with minimal user input. Use when users want the agent to verify Node.js and `npx`, configure MCP server config (Windows/macOS, Cursor/Codex/OpenClaw/OpenCode), request API key at setup time, run post-install capability discovery (`tools/list` and `get_patch_notes`), and then strongly recommend helper skill and Python setup for full local document and spreadsheet workflows.

NeverSight/learn-skills.dev

Creates 120fps GPU-accelerated animations with Motion.dev (Framer Motion successor) for React, Next.js, Svelte, and Astro projects. Use when user requests animation, motion, scroll effects, parallax, hero animations, gestures, drag interactions, spring physics, whileHover effects, whileInView animations, animated UI, micro-interactions, page transitions, or layout animations. Generates production TypeScript/JSX code with accessibility (prefers-reduced-motion) and performance validation (≥60fps). Supports entrance animations, gesture interactions (hover/tap/drag), scroll-based reveals, and layout transitions using spring physics and natural timing. Do NOT use for CSS-only transitions (use native CSS), static sites without JavaScript, Vue animations (use motion-v variant instead), or SVG/Canvas complex animations (GSAP better suited).

NeverSight/learn-skills.dev

Static artifact craft skill for self-contained HTML/CSS/JS documents: docs, sheets, dashboards, explainers, slides, tools, and landing pages. Use when the user asks for a durable, openable, shareable web deliverable they'll keep or hand off — a report, a dashboard, a slide deck, a data table, a page. Local folder first, temporary public link via tunnel (localhost.run), optional durable publish to Surge, GitHub Pages, or Cloudflare. Not for quick look renders, inline snippets, or throwaway scratch. Not for SPA frameworks, backend APIs, database apps, or production product UI.

NeverSight/learn-skills.dev

FFmpeg commands for video/audio conversion, trimming, compression, and processing. Use when user mentions "ffmpeg", "convert video", "compress video", "extract audio", "trim video", "gif from video", "video codec", "transcode", "screen recording", "merge videos", "video to mp4", "reduce file size", or any media processing task.

NeverSight/learn-skills.dev

Vim keybindings, motions, text objects, and operators for efficient text editing. Use when user asks about "vim commands", "vim motions", "text objects", "vim keybindings", "vim cheat sheet", "learn vim", "vim in VS Code", or any Vim editing tasks.

NeverSight/learn-skills.dev

Grok Build ONLY. Turn a 2D character still into smooth animation sprites via image_gen/image_edit base → image_to_video (6s/10s run-in-place) → ffmpeg frames → magenta chroma-key → dense sampled sprites (strip/grid/GIF). Use when the user wants video-to-sprite, motion capture from generated video, smoother run/walk cycles from dense frames, or runs /video2dsprite. Do NOT use on Codex/Claude — only Grok Build has image_to_video. Prefer generate2dsprite for crisp pixel sheets without video.

相关技能