Communitygithub.com

NeverSight/learn-skills.dev

为 TikTok、Instagram、YouTube、Facebook、LinkedIn 创建符合精确平台规格的视频广告。涵盖尺寸、时长限制、AIDA 框架和字幕要求。

learn-skills.dev 是什么?

该技能《Video Ad Specs》是一个专注于视频广告制作的专项工具,旨在帮助 AI 代理(如 Claude Code、Cursor 等)根据目标平台的精确技术规格生成广告素材。它详细列出了 TikTok(9:16 竖屏,5-60 秒)、Instagram Reels/Stories、YouTube(包括 Bumper 广告和 Shorts)、Facebook Feed(静音播放是关键)和 LinkedIn 的分辨率、宽高比、时长限制和安全区域等参数。技能还集成了 AIDA(注意力、兴趣、欲望、行动)广告框架,提供了每种钩子技巧和分阶段时间线,并包含了通过 inference.sh CLI 生成视频、添加画外音和字幕的命令。这对于需要在不同社交媒体渠道上快速制作符合规格的广告片、避免因格式错误而被平台拒绝或降低效果的开发者、营销人员和内容创作者来说非常实用。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/NeverSight/learn-skills.dev/tree/HEAD/data/skills-md/101-skills/skills/video-ad-specs

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

安装 belt CLI 技能: npx skills add belt-sh/cli

视频广告规格

通过 inference.sh CLI 创建符合平台规格的视频广告。

快速开始

需要 inference.sh CLI (belt)。安装说明

belt login

# 生成一个竖屏视频广告场景
belt app run bytedance/seedance-2-0 --input '{
  "prompt": "vertical video, person excitedly unboxing a product, clean modern room, bright natural lighting, social media ad style, authentic feeling",
  "ratio": "9:16",
  "generate_audio": true
}'

平台规格

TikTok

规格值
宽高比9:16 (竖屏)
分辨率1080 x 1920 px
时长5-60 秒 (建议 15-30 秒)
文件大小最大 500 MB
格式MP4, MOV
声音默认开启 (设计时需考虑声音)
文本安全区距各边缘 150px
吸引窗口1 秒 — 第一帧必须抓住注意力

Instagram Reels

规格值
宽高比9:16 (竖屏)
分辨率1080 x 1920 px
时长最长 90 秒 (广告建议 15-30 秒)
封面图片单独上传,显示在网格中
声音默认开启
字幕区域底部 20% 保留给文字叠加

Instagram Stories

规格值
宽高比9:16
分辨率1080 x 1920 px
时长每段最长 15 秒
向上滑动/链接广告可用
顶部/底部顶部 14% 和底部 20% = 关键内容不安全区域

YouTube

格式宽高比时长可跳过
Bumper16:9正好 6 秒不可跳过
不可跳过16:915 秒不可跳过
可跳过 (TrueView)16:9任意长度5 秒后可跳过
Shorts9:16最长 60 秒不适用

分辨率:1920 x 1080 (16:9) 或 1080 x 1920 (Shorts)

Facebook Feed

规格值
宽高比1:1 (方形) 或 4:5 (推荐用于移动端)
分辨率1080 x 1080 或 1080 x 1350
时长最长 240 分钟 (建议 15-30 秒)
自动播放静音 — 字幕至关重要
声音85% 的 Facebook 视频在 无声 状态下观看

LinkedIn

规格值
宽高比1:1 或 16:9
分辨率1080 x 1080 或 1920 x 1080
时长3 秒到 10 分钟 (广告建议 15-30 秒)
风格专业
自动播放信息流中静音

AIDA 视频广告框架

阶段时间目标技巧
注意力0-3秒停止滚动模式中断、大胆视觉、提问
兴趣3-10秒保持观看陈述问题、展示相关性
欲望10-20秒想要解决方案展示产品/结果、社会证明
行动最后 3-5秒点击/购买/注册清晰的 CTA、紧迫感、优惠

钩子技巧 (前 3 秒)

技巧示例
大胆陈述"这个工具取代了我整个营销团队"
提问"为什么你还在手动做这个?"
惊喜视觉意想不到的转变、之前/之后揭示
模式中断从动作中间开始、不寻常的角度、鲜艳的颜色
社会证明"200 万人已改用这个"
痛点"如果你讨厌[常见的烦恼],请看这个"

创建视频广告

竖屏 (TikTok, Reels, Stories, Shorts)

# 钩子场景 (0-3s)
belt app run google/veo-3-1-fast --input '{
  "prompt": "vertical 9:16 video, close-up of hands struggling with tangled cables and messy desk, frustrated energy, shaky handheld camera, authentic social media style, bright lighting"
}'

# 解决方案揭示 (3-15s)
belt app run bytedance/seedance-2-0 --input '{
  "prompt": "vertical video, smooth product reveal, clean wireless charging station on minimalist desk, satisfying organization transformation, bright modern room, social media ad aesthetic",
  "ratio": "9:16",
  "generate_audio": true
}'

# 添加旁白
belt app run falai/dia-tts --input '{
  "prompt": "[S1] Stop wasting time with this mess. This one product changed my entire setup. Everything charges. Everything is organized. Link in bio."
}'

# 合并视频 + 音频
belt app run infsh/video-audio-merger --input '{
  "video": "solution-reveal.mp4",
  "audio": "voiceover.mp3"
}'

# 添加字幕 (对于静音自动播放至关重要)
belt app run infsh/caption-videos --input '{
  "video": "ad-with-audio.mp4",
  "caption_file": "captions.srt"
}'

方形 (Facebook, LinkedIn Feed)

belt app run google/veo-3-1-fast --input '{
  "prompt": "square 1:1 video, professional person at desk discovering a new software tool, laptop screen showing clean dashboard, natural office lighting, corporate commercial style, satisfied expression"
}'

YouTube Bumper (6 秒)

# 6 秒 Bumper:一个信息,一个视觉,一个 CTA
belt app run google/veo-3-1-fast --input '{
  "prompt": "6 second product ad, quick montage of a sleek app being used on phone, fast cuts, modern, energetic, brand logo reveal at end, punchy and dynamic, wide 16:9"
}'

# 保持紧凑
belt app run falai/dia-tts --input '{
  "prompt": "[S1] Your reports. Automated. Try DataFlow free."
}'

字幕是必需的

85% 的 Facebook 和 40% 以上的 Instagram 视频在静音状态下观看。

字幕最佳实践

规则原因
总是添加字幕大多数平台上静音观看是默认设置
大号、易读字体小字在移动设备上不可见
高对比度白色文字配深色轮廓/背景
居中或底部三分之一标准观看位置
一次最多 2 行更多文字 = 来不及阅读
关键词加粗/着色吸引眼睛到重要词汇
# 从音频生成字幕
# (从脚本创建 SRT 文件,然后烧录)
belt app run infsh/caption-videos --input '{
  "video": "ad-video.mp4",
  "caption_file": "ad-captions.srt"
}'

广告结构模板

推荐广告 (15-30s)

时间内容
0-3s客户陈述他们遇到的问题
3-15s他们如何发现并尝试产品
15-25s他们实现的具体成果
25-30s产品名称 + CTA

演示广告 (15-30s)

时间内容
0-3s问题 (文字或视觉)
3-20s产品演示显示解决方案
20-25s关键成果/好处
25-30sCTA + 优惠

之前/之后广告 (15s)

时间内容
0-3s"之前" 状态 (杂乱、缓慢、令人沮丧)
3-5s过渡 / 产品介绍
5-12s"之后" 状态 (干净、快速、令人满意)
12-15sCTA

常见错误

错误问题修复
前 1-3 秒没有钩子观看者会划走以模式中断开头
在 TikTok/Reels 上使用横屏视频出现黑边,显得业余为竖屏平台使用 9:16
没有字幕大多数观看者静音观看总是添加字幕
CTA 太晚观看者已经离开在最后 5 秒内给出清晰的 CTA
时长超过平台限制强制跳过或流失符合平台时长规范
所有平台使用同一个广告规格错误,风格错误创建平台特定版本
前 3 秒出现 Logo感觉像商业广告,被跳过将品牌信息保留到结尾
文本处于不安全区域被平台 UI 截断检查每个平台的安全区域

检查清单

  • 为目标平台使用正确的宽高比
  • 在前 1-3 秒内设置钩子
  • 添加字幕 (可读、高对比度)
  • CTA 清晰并在最后 5 秒内
  • 时长符合平台规范
  • 文本不在平台不安全区域
  • 音频为有声和无声两种场景设计
  • 平台特定版本 (非一刀切)

相关技能

npx skills add inference-sh/skills@ai-video-generation
npx skills add inference-sh/skills@video-prompting-guide
npx skills add inference-sh/skills@text-to-speech
npx skills add inference-sh/skills@prompt-engineering

浏览所有应用:belt app store

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

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

Download YouTube videos, extract/proofread/translate subtitles, and render them onto video. Use whenever the user asks to download a YouTube video with subtitles, translate video subtitles to Chinese, add subtitles/burn subtitles to a video, or do ASR transcription on video audio. Covers the full pipeline: video download → subtitle extraction → proofreading → translation → SRT generation → subtitle rendering. Also use for "下载视频加字幕", "视频翻译字幕", "把字幕烧录到视频中". For pure subtitle file creation without rendering (just SRT output), this skill handles that too — stop before Phase 5.

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