Communitygithub.com

NeverSight/learn-skills.dev

解說影片製作指南:涵蓋腳本撰寫、配音、視覺設計與影片剪輯。包含腳本公式、節奏規則、場景規劃與多工具工作流程。

learn-skills.dev 是什麼?

這是一個專為開發者與 AI 代理設計的解說影片製作指南,提供從腳本構思到最終剪輯的完整工作流程。使用者可以透過 inference.sh CLI(belt 指令)快速產生場景、配音與背景音樂。指南詳細介紹了三種實用的腳本公式(問題-激化-解決、前-後-橋接、功能聚焦),並根據影片類型(如產品示範、教學影片、社群解說)提供不同的節奏建議與字數規範。在視覺製作方面,支援透過 Veo 3.1、Seedance 2.0 等 AI 工具生成影片片段,也提供圖片轉影片的功能。此外,還包含配音腳本撰寫技巧(如短句、主動語態)、語速控制(標點符號調節)、背景音樂指引(音量、風格)以及完整的組裝流程。這個技能特別適合需要快速產出專業解說影片的團隊,支援多種平台並能與現有 AI 工具鏈整合,大幅降低影片製作門檻。

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

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

安裝 belt CLI 技巧: npx skills add belt-sh/cli

解說影片指南

透過 inference.sh CLI 創建從腳本到最終剪輯的解說影片。

快速開始

需要 inference.sh CLI (belt)。安裝說明

belt login

# 為解說影片生成一個場景
belt app run google/veo-3-1-fast --input '{
  "prompt": "Clean motion graphics style animation, abstract data flowing between connected nodes, blue and white color scheme, professional corporate aesthetic, smooth transitions"
}'

腳本公式

問題-激化-解決 (PAS) — 60 秒

部分時長內容字數
問題10s陳述觀眾的痛點~25 字
激化10s展示為何情況比他們想的更糟~25 字
解決方案15s介紹你的產品/想法~35 字
運作方式20s展示 3 個關鍵步驟或功能~50 字
行動呼籲5s一個明確的下一步行動~12 字

之前-之後-橋接 (BAB) — 90 秒

部分時長內容
之前15s展示當前令人沮喪的狀態
之後15s展示理想的結果
橋接40s解釋你的產品如何幫助他們達成目標
社會證明10s快速統計或見證
行動呼籲10s明確的下一步

功能聚焦 — 30 秒(社交媒體)

部分時長內容
鉤子3s驚人的事實或問題
功能15s展示一個功能解決一個問題
結果7s成果/好處
行動呼籲5s試試看 / 了解更多

節奏規則

內容類型每分鐘字數備註
標準旁白150 wpm對話式節奏
複雜/技術性120 wpm留出處理時間
充滿活力/社交170 wpm短形式更快
兒童內容100 wpm清晰且緩慢

關鍵規則: 每個關鍵訊息對應一個場景。不要在一個視覺中塞入多個想法。

場景時長指南

  • 建立鏡頭:3-5 秒
  • 功能展示:5-8 秒
  • 螢幕上的文字/統計:3-4 秒(必須可讀)
  • 轉場:0.5-1 秒
  • 行動呼籲畫面:3-5 秒

視覺製作

場景類型

# 產品在情境中
belt app run google/veo-3-1-fast --input '{
  "prompt": "Clean product demonstration video, hands typing on a laptop showing a dashboard interface, bright modern office, soft natural lighting, professional"
}'

# 抽象概念視覺化
belt app run bytedance/seedance-2-0 --input '{
  "prompt": "Abstract motion graphics, colorful data streams connecting floating geometric shapes, smooth fluid animation, dark background with glowing elements, tech aesthetic",
  "generate_audio": true
}'

# 生活方式/結果鏡頭
belt app run google/veo-3-1-fast --input '{
  "prompt": "Happy person relaxing on couch with laptop, smiling at screen, bright airy living room, warm afternoon light, satisfied customer feeling, lifestyle commercial style"
}'

# 之前/之後對比
belt app run falai/flux-dev-lora --input '{
  "prompt": "Split screen comparison, left side cluttered messy desk with papers and stress, right side clean organized minimalist workspace, dramatic difference, clean design"
}'

場景的圖像轉影片

# 先生成靜態幀
belt app run falai/flux-dev-lora --input '{
  "prompt": "Professional workspace with glowing holographic interface, futuristic but clean, blue accent lighting"
}'

# 讓它動起來
belt app run falai/wan-2-5-i2v --input '{
  "prompt": "Gentle camera push in, holographic elements subtly floating and rotating, soft ambient light shifts",
  "image": "path/to/workspace-still.png"
}'

旁白製作

腳本撰寫技巧

  • 短句。每句最多 15 個字。
  • 主動語態。「你可以追蹤你的數據」而不是「你的數據可以被追蹤。」
  • 對話式語氣。大聲朗讀——如果聽起來僵硬,就重寫。
  • 每句一個想法。每個視覺節拍一個句子。

生成旁白

# 使用 Dia TTS 的專業旁白
belt app run falai/dia-tts --input '{
  "prompt": "[S1] Tired of spending hours on reports that nobody reads? There is a better way. Meet DataFlow. It turns your raw data into visual stories... in seconds. Just connect your source, pick a template, and share. Try DataFlow free today."
}'

TTS 中的節奏控制

技巧效果示例
句號 .中等停頓"This changes everything. Here's how."
省略號 ...長停頓(戲劇性)"And the result... was incredible."
逗號 ,短停頓"Fast, simple, powerful."
驚嘆號 !強調/活力"Start building today!"
問號 ?上升語調"What if there was a better way?"

音樂與音頻

背景音樂指南

  • 音量: 旁白下 20-30%(語音播放時降低 6-12dB)
  • 風格: 符合品牌調性(企業 = 環境電子,初創公司 = 樂觀獨立)
  • 結構: 前奏漸強(前 3 秒)-> 旁白下輕柔循環 -> 行動呼籲處漸強
  • 無歌詞: 旁白下僅用器樂
# 生成背景音樂
belt app run <music-gen-app> --input '{
  "prompt": "upbeat corporate background music, modern electronic, 90 BPM, positive and professional, no vocals, suitable for product explainer video"
}'

組裝管道

完整製作流程

# 1. 生成旁白
belt app run falai/dia-tts --input '{
  "prompt": "[S1] Your script here..."
}'

# 2. 生成場景視覺(並行)
belt app run google/veo-3-1-fast --input '{"prompt": "scene 1 description"}' --no-wait
belt app run google/veo-3-1-fast --input '{"prompt": "scene 2 description"}' --no-wait
belt app run google/veo-3-1-fast --input '{"prompt": "scene 3 description"}' --no-wait

# 3. 將場景合併為序列
belt app run infsh/media-merger --input '{
  "media": ["scene1.mp4", "scene2.mp4", "scene3.mp4"]
}'

# 4. 將旁白添加到影片
belt app run infsh/video-audio-merger --input '{
  "video": "merged-scenes.mp4",
  "audio": "voiceover.mp3"
}'

# 5. 添加字幕
belt app run infsh/caption-videos --input '{
  "video": "final-with-audio.mp4",
  "caption_file": "captions.srt"
}'

各格式影片時長

格式時長平台
社交預告15-30sTikTok, Instagram Reels, YouTube Shorts
產品展示60-90s網站,登陸頁面
功能解說90-120sYouTube,電子郵件
教程/逐步指導2-5minYouTube,幫助中心
投資者推介影片2-3min簡報補充

轉場類型

轉場使用時機效果
切換相關場景間默認乾淨,專業
淡入淡出/交叉溶解時間流逝,情緒轉變柔和,沉思
擦拭新話題或章節明確分離
縮放/推進深入細節聚焦注意力
匹配剪輯場景間視覺相似巧妙,令人難忘

常見錯誤

錯誤問題修正
腳本過於冗長旁白急促,觀眾不知所措削減至最多 150 wpm
前 3 秒無鉤子觀眾立即離開以問題或驚人統計開始
視覺落後於旁白造成混淆的脫節視覺應匹配或稍微領先於文字
背景音樂過大聽不見旁白將音樂降低 6-12dB 在語音之下
無字幕85% 的社交影片在靜音下觀看始終添加字幕
想法過多觀眾什麼也記不住每個影片一個核心訊息

相關技巧

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

瀏覽所有應用: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

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

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.

相關技能