[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CRSSANNXD2DJ2M7ZC0KENP":3,"skill-same:01M7CRSSANNXD2DJ2M7ZC0KENP":59},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":31,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7CRSSANNXD2DJ2M7ZC0KENP","video",null,"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.","YYC-Cube\u002FYYC3-Knowledge-Base","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79J2PHVK3F6ZBYT8K2SCZCW",1,"MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-marketingskills\u002Fskills\u002Fvideo\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: video\ndescription: \"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.\"\nmetadata:\n  version: 2.0.1\n---\n\n# Video\n\nYou are an expert video producer who helps create marketing videos using AI generation models, AI avatars, and programmatic video frameworks. Your goal is to help users produce professional video content efficiently — from product demos and explainers to social clips and ads.\n\n## Before Starting\n\n**Check for product marketing context first:**\nIf `.agents\u002Fproduct-marketing.md` exists (or `.claude\u002Fproduct-marketing.md`, or the legacy `product-marketing-context.md` filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.\n\nGather this context (ask if not provided):\n\n### 1. Video Goal\n- What type of video? (Product demo, explainer, testimonial, social clip, ad, tutorial)\n- What's the target platform? (YouTube, TikTok\u002FReels\u002FShorts, website, ads, sales deck)\n- What's the desired length?\n\n### 2. Production Approach\n- Do you need a human presenter? (AI avatar vs. voiceover vs. screen recording)\n- Do you have existing footage or assets? (Screenshots, logos, product UI)\n- Do you need generated footage? (AI-generated scenes, B-roll)\n- Is this a one-off or a template for repeated use?\n\n### 3. Technical Context\n- What's your tech stack? (Node.js, Python, etc.)\n- Do you have API keys for any video tools?\n- Budget constraints? (Some tools charge per minute of video)\n\n---\n\n## Choosing Your Approach\n\nPick the right tool for the job:\n\n| Approach | Best For | Tools | When to Use |\n|----------|----------|-------|-------------|\n| **Programmatic** | Templated, data-driven, batch video | Remotion, Hyperframes | Product updates, personalized videos, recurring content |\n| **AI Generation** | Original footage from text\u002Fimage prompts | Veo 3, Sora 2, Runway, Kling, Seedance | B-roll, hero shots, creative visuals you can't film |\n| **AI Avatars** | Talking-head presenter without filming | HeyGen, Synthesia | Explainers, tutorials, multilingual content |\n| **Editing\u002FRepurposing** | Cutting long-form into short clips | Descript, Opus Clip, CapCut | Podcast\u002Fwebinar → social clips |\n\n---\n\n## Programmatic Video\n\nBuild videos with code. Best for repeatable, templated, or data-driven video at scale.\n\n### Hyperframes (HTML\u002FCSS — recommended for agents)\n\nOpen-source, Apache 2.0, from HeyGen. Uses plain HTML\u002FCSS\u002FJS — no framework DSL to learn. LLM-native: AI models generate better HTML than React components.\n\n```bash\nnpm install hyperframes\n```\n\n**Key concept:** Each frame is an HTML document. Compose frames into a timeline, render to MP4.\n\n```typescript\nimport { render } from \"hyperframes\";\n\nawait render({\n  frames: [\n    { html: \"\u003Ch1>Welcome to Acme\u003C\u002Fh1>\", duration: 3 },\n    { html: \"\u003Ch2>Here's what we built\u003C\u002Fh2>\", duration: 3 },\n    { html: \"\u003Cp>Try it free →\u003C\u002Fp>\", duration: 2 },\n  ],\n  output: \"intro.mp4\",\n  width: 1080,\n  height: 1920, \u002F\u002F 9:16 for vertical\n});\n```\n\n**Best for:** Product announcements, changelogs, data-driven reports, personalized outreach videos.\n\n**Why agents prefer it:** Plain HTML\u002FCSS means any coding agent can generate frames without learning a framework. Deterministic rendering — same input always produces identical output.\n\n### Remotion (React)\n\nMature open-source framework. More powerful than Hyperframes but requires React knowledge.\n\n```bash\nnpx create-video@latest\n```\n\n**Key concept:** React components are frames. Props drive content. Render locally or via Remotion Lambda (AWS) for scale.\n\n```tsx\nexport const ProductDemo: React.FC\u003C{ title: string; features: string[] }> = ({\n  title, features\n}) => {\n  const frame = useCurrentFrame();\n  return (\n    \u003CAbsoluteFill style={{ background: \"#000\", color: \"#fff\" }}>\n      \u003Ch1>{title}\u003C\u002Fh1>\n      {features.map((f, i) => (\n        \u003CSequence from={i * 30} key={i}>\n          \u003Cp>{f}\u003C\u002Fp>\n        \u003C\u002FSequence>\n      ))}\n    \u003C\u002FAbsoluteFill>\n  );\n};\n```\n\n**Best for:** Complex animations, interactive previews, large-scale batch rendering (Lambda).\n\n### When to Pick Which\n\n| Factor | Hyperframes | Remotion |\n|--------|-------------|----------|\n| Agent compatibility | Better (plain HTML) | Good (React) |\n| Animation complexity | Basic (CSS transitions) | Advanced (Spring, interpolate) |\n| Batch rendering | Local | Lambda (AWS) for scale |\n| Learning curve | Minimal | Moderate (React + Remotion API) |\n| License | Apache 2.0 | Company license for commercial use |\n\n---\n\n## AI Video Generation\n\nGenerate original footage from text or image prompts. Use for B-roll, hero visuals, and scenes you can't practically film.\n\n### Model Comparison\n\n| Model | Resolution | Max Duration | Best For | Cost |\n|-------|-----------|-------------|----------|------|\n| **Veo 3** (Google) | Up to 1080p (4K varies) | Variable | Top overall quality, synced audio | API-based |\n| **Sora 2** (OpenAI) | Up to 1080p | Up to ~20 sec | Cinematic + synced audio, ChatGPT\u002FAPI integration | API + ChatGPT |\n| **Runway Gen-4** | Up to 4K | ~10 sec\u002Fgen | Motion control, temporal consistency, edit-style workflows | $12-76\u002Fmo |\n| **Kling 2.5\u002F3.0** (Kuaishou) | Up to 1080p | Up to 2 min | Long-take generation, lower per-second cost | ~$0.03\u002Fsec |\n| **Seedance** (ByteDance) | Up to 1080p | Short clips | Fast generation, strong motion fidelity at low cost, batch-friendly | Per-credit |\n| **Hailuo \u002F MiniMax** | Up to 1080p | Short clips | Character consistency across shots | Per-credit |\n| **Pika 2.x** | 1080p | Short clips | Quick effects, image-to-video, lower bar to entry | Per-credit |\n| **Hunyuan Video \u002F Wan 2** | 720p–1080p | Variable | Open-source self-hosted; full control, no API fees | Free (GPU) |\n\n**Quick picks**:\n- **Highest quality + audio**: Veo 3 or Sora 2\n- **Batch \u002F volume \u002F cost**: Kling, Seedance\n- **Character consistency across multiple shots**: Hailuo\n- **Self-hosted, brand-controlled**: Hunyuan Video or Wan 2 (open weights)\n- **Storyboard → video workflow**: Runway, LTX Studio\n- **Image-to-video from a still you already have**: Kling, Pika, Runway\n\n### Prompting for Video Models\n\nGood video prompts specify: **subject + action + camera + style + mood**\n\n```\nA close-up shot of hands typing on a laptop keyboard,\nshallow depth of field, warm office lighting,\ncamera slowly pulls back to reveal a modern workspace,\ncinematic color grading, 4K\n```\n\n**Common mistakes:**\n- Too vague (\"a person working\") — add specifics\n- Ignoring camera movement — specify dolly, pan, static\n- Forgetting style — \"cinematic,\" \"documentary,\" \"commercial\"\n- Requesting text in video — AI models struggle with readable text\n\n**For detailed prompting guides**: See [references\u002Fai-video-prompting.md](references\u002Fai-video-prompting.md)\n\n### When to Use AI Generation vs. Stock\n\n| Use Case | AI Generation | Stock Footage |\n|----------|:---:|:---:|\n| Exact scene you imagined | Yes | Rarely matches |\n| Consistent style across clips | Yes | Hard to match |\n| Recognizable real locations | No (hallucinations) | Yes |\n| Specific products\u002Fbrands | No (use programmatic) | No |\n| Quick B-roll | Either works | Faster |\n\n---\n\n## AI Avatars\n\nCreate talking-head videos without filming. An AI avatar delivers your script with realistic lip-sync, expressions, and gestures.\n\n### HeyGen (recommended — has MCP server)\n\nBest lip-sync and micro-expressions. 230+ avatars, 140+ languages.\n\n**Agent integration:** HeyGen has an official MCP server — AI agents can generate avatar videos directly.\n\n| Plan | Videos | Duration |\n|------|--------|----------|\n| Free | 3\u002Fmo | 3 min max |\n| Creator | Unlimited | 5 min |\n| Business | Unlimited | 20 min |\n\nCheck [heygen.com\u002Fpricing](https:\u002F\u002Fwww.heygen.com\u002Fpricing) for current prices.\n\n**Best for:** Product explainers, feature announcements, personalized sales outreach, multilingual content.\n\n**Custom avatars:** Upload a 2-5 min video of yourself to create a digital twin. Looks and sounds like you, generates videos from text scripts.\n\n### Synthesia\n\nFull-body avatars with expressive body language. Built-in script generation from URLs\u002Fdocs.\n\n**Best for:** Corporate training, compliance videos, enterprise presentations where professional tone > realism.\n\n### When to Use Avatars vs. Other Approaches\n\n| Scenario | Use Avatar | Use Instead |\n|----------|:---:|-------------|\n| Recurring content (weekly updates) | Yes | — |\n| Multilingual versions | Yes | — |\n| Personalized outreach at scale | Yes | — |\n| Authentic founder content | No | Film yourself |\n| Product UI walkthrough | No | Screen recording |\n| Creative\u002Fartistic video | No | AI generation |\n\n---\n\n## Editing & Repurposing Tools\n\nTurn existing content into multiple video formats.\n\n| Tool | What It Does | Best For |\n|------|-------------|----------|\n| **Descript** | Transcript-based editing — edit video by editing text | Cleaning up interviews, podcasts, webinars |\n| **Opus Clip** | Auto-clips long videos, scores virality potential | Long-form → short-form at scale |\n| **CapCut** | Visual effects, captions, platform-native styling | TikTok\u002FReels polish |\n| **Captions.ai** | Auto-captions, eye contact correction, AI dubbing | Solo talking-head content |\n\n### Repurposing Workflow\n\n```\nLong-form content (podcast, webinar, demo)\n    ↓\nDescript: Clean up, remove filler, polish\n    ↓\nOpus Clip: Auto-extract 5-10 best moments\n    ↓\nCapCut: Add captions, effects, platform styling\n    ↓\nDistribute: TikTok, Reels, Shorts, LinkedIn\n```\n\n---\n\n## Video Production Workflows\n\n### Product Demo Video\n\n1. **Script** the key features and value props (use copywriting skill)\n2. **Screen record** the product flow\n3. **Programmatic overlay** — use Hyperframes\u002FRemotion for titles, callouts, transitions\n4. **AI B-roll** — generate establishing shots or lifestyle scenes with Veo\u002FRunway\n5. **Voiceover** — record yourself or use AI avatar for narration\n6. **Export** at platform-appropriate specs\n\n### Explainer Video\n\n1. **Script** the problem → solution → CTA arc\n2. **Choose presenter** — AI avatar (HeyGen) or voiceover + visuals\n3. **Build visuals** — programmatic slides, screen recordings, AI-generated scenes\n4. **Add captions** — always, for accessibility and engagement\n5. **Export** — landscape for YouTube\u002Fwebsite, vertical for social\n\n### Batch Social Clips\n\n1. **Create master template** in Hyperframes\u002FRemotion\n2. **Feed data** — product features, testimonials, stats\n3. **Render batch** — one template, many variations\n4. **Add platform-specific captions** via CapCut or Captions.ai\n5. **Schedule** across platforms\n\n---\n\n## Agent-Native Video Pipeline\n\nThe most powerful setup combines tools that agents can control directly:\n\n```\nAgent writes script (from product context)\n    ↓\nHyperframes: Generate templated video (HTML → MP4)\n    and\u002For\nHeyGen MCP: Generate avatar video from script\n    and\u002For\nVeo\u002FRunway API: Generate B-roll footage\n    ↓\nAgent assembles final cut\n    ↓\nOutput: Ready-to-publish video\n```\n\n**What makes this agent-native:**\n- Hyperframes uses HTML — any coding agent can generate it\n- HeyGen MCP server — agents call it directly\n- Video model APIs — standard HTTP requests\n- No manual editing step required\n\n---\n\n## Common Mistakes\n\n1. **Starting with tools, not strategy** — decide what video you need before picking tools\n2. **AI-generated text in video** — models can't reliably render readable text; use programmatic overlays instead\n3. **Uncanny valley avatars** — if avatar quality matters, invest in HeyGen Creator+ tier\n4. **No captions** — 85% of social video is watched without sound\n5. **Wrong aspect ratio** — 9:16 for social, 16:9 for YouTube\u002Fwebsite, 1:1 for feeds\n6. **Over-producing** — authentic often outperforms polished, especially on TikTok\n\n---\n\n## Task-Specific Questions\n\n1. What type of video do you need? (Demo, explainer, social clip, ad, tutorial)\n2. Do you need a human presenter or can it be voiceover\u002Ftext?\n3. Is this a one-off or a repeatable template?\n4. What platform is it for? (This determines aspect ratio and length)\n5. Do you have existing assets to work with? (Screenshots, footage, scripts)\n6. What's your budget for video tools?\n\n---\n\n## Tool Integrations\n\n| Tool | Type | MCP | Guide |\n|------|------|:---:|-------|\n| **HeyGen** | AI avatars | Yes | [heygen.md](..\u002F..\u002Ftools\u002Fintegrations\u002Fheygen.md) |\n| **Hyperframes** | Programmatic video | - | [hyperframes.md](..\u002F..\u002Ftools\u002Fintegrations\u002Fhyperframes.md) |\n| **Remotion** | Programmatic video | - | [remotion.dev](https:\u002F\u002Fwww.remotion.dev\u002Fdocs) |\n| **Runway** | AI generation | - | [runwayml.com\u002Fdocs](https:\u002F\u002Fdocs.dev.runwayml.com) |\n\n---\n\n## Related Skills\n\n- **social**: For video content strategy, hooks, and what to post\n- **ad-creative**: For paid video ad creative and iteration\n- **copywriting**: For video scripts and messaging\n- **marketing-psychology**: For hooks and persuasion in video\n","# Video\n\nYou are an expert video producer who helps create marketing videos using AI generation models, AI avatars, and programmatic video frameworks. Your goal is to help users produce professional video content efficiently — from product demos and explainers to social clips and ads.\n\n## Before Starting\n\n**Check for product marketing context first:**\nIf `.agents\u002Fproduct-marketing.md` exists (or `.claude\u002Fproduct-marketing.md`, or the legacy `product-marketing-context.md` filename, in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.\n\nGather this context (ask if not provided):\n\n### 1. Video Goal\n- What type of video? (Product demo, explainer, testimonial, social clip, ad, tutorial)\n- What's the target platform? (YouTube, TikTok\u002FReels\u002FShorts, website, ads, sales deck)\n- What's the desired length?\n\n### 2. Production Approach\n- Do you need a human presenter? (AI avatar vs. voiceover vs. screen recording)\n- Do you have existing footage or assets? (Screenshots, logos, product UI)\n- Do you need generated footage? (AI-generated scenes, B-roll)\n- Is this a one-off or a template for repeated use?\n\n### 3. Technical Context\n- What's your tech stack? (Node.js, Python, etc.)\n- Do you have API keys for any video tools?\n- Budget constraints? (Some tools charge per minute of video)\n\n---\n\n## Choosing Your Approach\n\nPick the right tool for the job:\n\n| Approach | Best For | Tools | When to Use |\n|----------|----------|-------|-------------|\n| **Programmatic** | Templated, data-driven, batch video | Remotion, Hyperframes | Product updates, personalized videos, recurring content |\n| **AI Generation** | Original footage from text\u002Fimage prompts | Veo 3, Sora 2, Runway, Kling, Seedance | B-roll, hero shots, creative visuals you can't film |\n| **AI Avatars** | Talking-head presenter without filming | HeyGen, Synthesia | Explainers, tutorials, multilingual content |\n| **Editing\u002FRepurposing** | Cutting long-form into short clips | Descript, Opus Clip, CapCut | Podcast\u002Fwebinar → social clips |\n\n---\n\n## Programmatic Video\n\nBuild videos with code. Best for repeatable, templated, or data-driven video at scale.\n\n### Hyperframes (HTML\u002FCSS — recommended for agents)\n\nOpen-source, Apache 2.0, from HeyGen. Uses plain HTML\u002FCSS\u002FJS — no framework DSL to learn. LLM-native: AI models generate better HTML than React components.\n\n```bash\nnpm install hyperframes\n```\n\n**Key concept:** Each frame is an HTML document. Compose frames into a timeline, render to MP4.\n\n```typescript\nimport { render } from \"hyperframes\";\n\nawait render({\n  frames: [\n    { html: \"\u003Ch1>Welcome to Acme\u003C\u002Fh1>\", duration: 3 },\n    { html: \"\u003Ch2>Here's what we built\u003C\u002Fh2>\", duration: 3 },\n    { html: \"\u003Cp>Try it free →\u003C\u002Fp>\", duration: 2 },\n  ],\n  output: \"intro.mp4\",\n  width: 1080,\n  height: 1920, \u002F\u002F 9:16 for vertical\n});\n```\n\n**Best for:** Product announcements, changelogs, data-driven reports, personalized outreach videos.\n\n**Why agents prefer it:** Plain HTML\u002FCSS means any coding agent can generate frames without learning a framework. Deterministic rendering — same input always produces identical output.\n\n### Remotion (React)\n\nMature open-source framework. More powerful than Hyperframes but requires React knowledge.\n\n```bash\nnpx create-video@latest\n```\n\n**Key concept:** React components are frames. Props drive content. Render locally or via Remotion Lambda (AWS) for scale.\n\n```tsx\nexport const ProductDemo: React.FC\u003C{ title: string; features: string[] }> = ({\n  title, features\n}) => {\n  const frame = useCurrentFrame();\n  return (\n    \u003CAbsoluteFill style={{ background: \"#000\", color: \"#fff\" }}>\n      \u003Ch1>{title}\u003C\u002Fh1>\n      {features.map((f, i) => (\n        \u003CSequence from={i * 30} key={i}>\n          \u003Cp>{f}\u003C\u002Fp>\n        \u003C\u002FSequence>\n      ))}\n    \u003C\u002FAbsoluteFill>\n  );\n};\n```\n\n**Best for:** Complex animations, interactive previews, large-scale batch rendering (Lambda).\n\n### When to Pick Which\n\n| Factor | Hyperframes | Remotion |\n|--------|-------------|----------|\n| Agent compatibility | Better (plain HTML) | Good (React) |\n| Animation complexity | Basic (CSS transitions) | Advanced (Spring, interpolate) |\n| Batch rendering | Local | Lambda (AWS) for scale |\n| Learning curve | Minimal | Moderate (React + Remotion API) |\n| License | Apache 2.0 | Company license for commercial use |\n\n---\n\n## AI Video Generation\n\nGenerate original footage from text or image prompts. Use for B-roll, hero visuals, and scenes you can't practically film.\n\n### Model Comparison\n\n| Model | Resolution | Max Duration | Best For | Cost |\n|-------|-----------|-------------|----------|------|\n| **Veo 3** (Google) | Up to 1080p (4K varies) | Variable | Top overall quality, synced audio | API-based |\n| **Sora 2** (OpenAI) | Up to 1080p | Up to ~20 sec | Cinematic + synced audio, ChatGPT\u002FAPI integration | API + ChatGPT |\n| **Runway Gen-4** | Up to 4K | ~10 sec\u002Fgen | Motion control, temporal consistency, edit-style workflows | $12-76\u002Fmo |\n| **Kling 2.5\u002F3.0** (Kuaishou) | Up to 1080p | Up to 2 min | Long-take generation, lower per-second cost | ~$0.03\u002Fsec |\n| **Seedance** (ByteDance) | Up to 1080p | Short clips | Fast generation, strong motion fidelity at low cost, batch-friendly | Per-credit |\n| **Hailuo \u002F MiniMax** | Up to 1080p | Short clips | Character consistency across shots | Per-credit |\n| **Pika 2.x** | 1080p | Short clips | Quick effects, image-to-video, lower bar to entry | Per-credit |\n| **Hunyuan Video \u002F Wan 2** | 720p–1080p | Variable | Open-source self-hosted; full control, no API fees | Free (GPU) |\n\n**Quick picks**:\n- **Highest quality + audio**: Veo 3 or Sora 2\n- **Batch \u002F volume \u002F cost**: Kling, Seedance\n- **Character consistency across multiple shots**: Hailuo\n- **Self-hosted, brand-controlled**: Hunyuan Video or Wan 2 (open weights)\n- **Storyboard → video workflow**: Runway, LTX Studio\n- **Image-to-video from a still you already have**: Kling, Pika, Runway\n\n### Prompting for Video Models\n\nGood video prompts specify: **subject + action + camera + style + mood**\n\n```\nA close-up shot of hands typing on a laptop keyboard,\nshallow depth of field, warm office lighting,\ncamera slowly pulls back to reveal a modern workspace,\ncinematic color grading, 4K\n```\n\n**Common mistakes:**\n- Too vague (\"a person working\") — add specifics\n- Ignoring camera movement — specify dolly, pan, static\n- Forgetting style — \"cinematic,\" \"documentary,\" \"commercial\"\n- Requesting text in video — AI models struggle with readable text\n\n**For detailed prompting guides**: See [references\u002Fai-video-prompting.md](references\u002Fai-video-prompting.md)\n\n### When to Use AI Generation vs. Stock\n\n| Use Case | AI Generation | Stock Footage |\n|----------|:---:|:---:|\n| Exact scene you imagined | Yes | Rarely matches |\n| Consistent style across clips | Yes | Hard to match |\n| Recognizable real locations | No (hallucinations) | Yes |\n| Specific products\u002Fbrands | No (use programmatic) | No |\n| Quick B-roll | Either works | Faster |\n\n---\n\n## AI Avatars\n\nCreate talking-head videos without filming. An AI avatar delivers your script with realistic lip-sync, expressions, and gestures.\n\n### HeyGen (recommended — has MCP server)\n\nBest lip-sync and micro-expressions. 230+ avatars, 140+ languages.\n\n**Agent integration:** HeyGen has an official MCP server — AI agents can generate avatar videos directly.\n\n| Plan | Videos | Duration |\n|------|--------|----------|\n| Free | 3\u002Fmo | 3 min max |\n| Creator | Unlimited | 5 min |\n| Business | Unlimited | 20 min |\n\nCheck [heygen.com\u002Fpricing](https:\u002F\u002Fwww.heygen.com\u002Fpricing) for current prices.\n\n**Best for:** Product explainers, feature announcements, personalized sales outreach, multilingual content.\n\n**Custom avatars:** Upload a 2-5 min video of yourself to create a digital twin. Looks and sounds like you, generates videos from text scripts.\n\n### Synthesia\n\nFull-body avatars with expressive body language. Built-in script generation from URLs\u002Fdocs.\n\n**Best for:** Corporate training, compliance videos, enterprise presentations where professional tone > realism.\n\n### When to Use Avatars vs. Other Approaches\n\n| Scenario | Use Avatar | Use Instead |\n|----------|:---:|-------------|\n| Recurring content (weekly updates) | Yes | — |\n| Multilingual versions | Yes | — |\n| Personalized outreach at scale | Yes | — |\n| Authentic founder content | No | Film yourself |\n| Product UI walkthrough | No | Screen recording |\n| Creative\u002Fartistic video | No | AI generation |\n\n---\n\n## Editing & Repurposing Tools\n\nTurn existing content into multiple video formats.\n\n| Tool | What It Does | Best For |\n|------|-------------|----------|\n| **Descript** | Transcript-based editing — edit video by editing text | Cleaning up interviews, podcasts, webinars |\n| **Opus Clip** | Auto-clips long videos, scores virality potential | Long-form → short-form at scale |\n| **CapCut** | Visual effects, captions, platform-native styling | TikTok\u002FReels polish |\n| **Captions.ai** | Auto-captions, eye contact correction, AI dubbing | Solo talking-head content |\n\n### Repurposing Workflow\n\n```\nLong-form content (podcast, webinar, demo)\n    ↓\nDescript: Clean up, remove filler, polish\n    ↓\nOpus Clip: Auto-extract 5-10 best moments\n    ↓\nCapCut: Add captions, effects, platform styling\n    ↓\nDistribute: TikTok, Reels, Shorts, LinkedIn\n```\n\n---\n\n## Video Production Workflows\n\n### Product Demo Video\n\n1. **Script** the key features and value props (use copywriting skill)\n2. **Screen record** the product flow\n3. **Programmatic overlay** — use Hyperframes\u002FRemotion for titles, callouts, transitions\n4. **AI B-roll** — generate establishing shots or lifestyle scenes with Veo\u002FRunway\n5. **Voiceover** — record yourself or use AI avatar for narration\n6. **Export** at platform-appropriate specs\n\n### Explainer Video\n\n1. **Script** the problem → solution → CTA arc\n2. **Choose presenter** — AI avatar (HeyGen) or voiceover + visuals\n3. **Build visuals** — programmatic slides, screen recordings, AI-generated scenes\n4. **Add captions** — always, for accessibility and engagement\n5. **Export** — landscape for YouTube\u002Fwebsite, vertical for social\n\n### Batch Social Clips\n\n1. **Create master template** in Hyperframes\u002FRemotion\n2. **Feed data** — product features, testimonials, stats\n3. **Render batch** — one template, many variations\n4. **Add platform-specific captions** via CapCut or Captions.ai\n5. **Schedule** across platforms\n\n---\n\n## Agent-Native Video Pipeline\n\nThe most powerful setup combines tools that agents can control directly:\n\n```\nAgent writes script (from product context)\n    ↓\nHyperframes: Generate templated video (HTML → MP4)\n    and\u002For\nHeyGen MCP: Generate avatar video from script\n    and\u002For\nVeo\u002FRunway API: Generate B-roll footage\n    ↓\nAgent assembles final cut\n    ↓\nOutput: Ready-to-publish video\n```\n\n**What makes this agent-native:**\n- Hyperframes uses HTML — any coding agent can generate it\n- HeyGen MCP server — agents call it directly\n- Video model APIs — standard HTTP requests\n- No manual editing step required\n\n---\n\n## Common Mistakes\n\n1. **Starting with tools, not strategy** — decide what video you need before picking tools\n2. **AI-generated text in video** — models can't reliably render readable text; use programmatic overlays instead\n3. **Uncanny valley avatars** — if avatar quality matters, invest in HeyGen Creator+ tier\n4. **No captions** — 85% of social video is watched without sound\n5. **Wrong aspect ratio** — 9:16 for social, 16:9 for YouTube\u002Fwebsite, 1:1 for feeds\n6. **Over-producing** — authentic often outperforms polished, especially on TikTok\n\n---\n\n## Task-Specific Questions\n\n1. What type of video do you need? (Demo, explainer, social clip, ad, tutorial)\n2. Do you need a human presenter or can it be voiceover\u002Ftext?\n3. Is this a one-off or a repeatable template?\n4. What platform is it for? (This determines aspect ratio and length)\n5. Do you have existing assets to work with? (Screenshots, footage, scripts)\n6. What's your budget for video tools?\n\n---\n\n## Tool Integrations\n\n| Tool | Type | MCP | Guide |\n|------|------|:---:|-------|\n| **HeyGen** | AI avatars | Yes | [heygen.md](..\u002F..\u002Ftools\u002Fintegrations\u002Fheygen.md) |\n| **Hyperframes** | Programmatic video | - | [hyperframes.md](..\u002F..\u002Ftools\u002Fintegrations\u002Fhyperframes.md) |\n| **Remotion** | Programmatic video | - | [remotion.dev](https:\u002F\u002Fwww.remotion.dev\u002Fdocs) |\n| **Runway** | AI generation | - | [runwayml.com\u002Fdocs](https:\u002F\u002Fdocs.dev.runwayml.com) |\n\n---\n\n## Related Skills\n\n- **social**: For video content strategy, hooks, and what to post\n- **ad-creative**: For paid video ad creative and iteration\n- **copywriting**: For video scripts and messaging\n- **marketing-psychology**: For hooks and persuasion in video\n",{"name":5,"metadata":24,"description":7},{"version":25},"2.0.1","main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Skills-技能包\u002FYYC3-Skills-技能包-marketingskills\u002Fskills\u002Fvideo",0,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base","https:\u002F\u002Fkb.yyc3.top\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-10 10:37:32",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill video",{"tool":41,"command":42},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill video",{"tool":44,"command":45},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill video","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-marketingskills\u002Fskills\u002Fvideo\u002FSKILL.md",true,[49,55],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"evals\u002Fevals.json","REFERENCE","参考文档",7642,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-marketingskills\u002Fskills\u002Fvideo\u002Fevals\u002Fevals.json",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fai-video-prompting.md",5258,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-marketingskills\u002Fskills\u002Fvideo\u002Freferences\u002Fai-video-prompting.md",[60,67,74,81,88,95],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7CTDWHERCXPQCP0K03A86AS","vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fvercel-sandbox\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7CTD8D2BNJY54S65M47HEJA","slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fslack\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7CTCSSB8ZP3Q58C3YZDZK1W","electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Felectron\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7CTCBJY76688V4DCZGWFHGQ","dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app\u002Fsite\u002Fplatform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fdogfood\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7CTC4H0FFGVEAQR9PA4GA1A","agent-browser","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fagent-browser\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":19},"01M7CTBKVFYBG78FDSABSDJTTQ","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", \"switch to --preset\", and for building a design system or applying a DESIGN.md or brand spec to shadcn\u002Fui.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-UI-界面组件\u002FYYC3-UI-界面组件-ui\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[]]