video

Create marketing videos using AI generation models, AI avatars, and programmatic video frameworks.

Updated Jun 22, 2026
One-click install
npx skills add https://github.com/aashahin/ai-skills --skill video-aashahin
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: video
Source: https://github.com/aashahin/ai-skills/tree/main/video
Command: npx skills add https://github.com/aashahin/ai-skills --skill video-aashahin

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires hyperframes, and includes references (resource) components.

What problem does it solve? Producing marketing videos traditionally requires filming, editing skills, and expensive tooling. This Skill guides you through creating product demos, explainers, and social clips using AI video generation models, AI avatars, and code-based video frameworks, so you can produce video content without a production crew. ## Core Features & Use Cases - Programmatic Video: Build templated, data-driven videos with Hyperframes (HTML/CSS) or Remotion (React) for product announcements, changelogs, and batch social clips. - AI Video Generation: Generate B-roll and hero footage from text prompts using Veo, Runway, Kling, or Pika, with a detailed prompting reference guide. - AI Avatars: Create talking-head presenter videos with HeyGen (MCP server support) or Synthesia for explainers and multilingual content. - Use Case: You need a vertical product announcement video for TikTok. The Skill helps you script it, generate frames in Hyperframes, add AI-generated B-roll from Veo, and export at 1080x1920. ## Quick Start Ask the agent to create a 30-second vertical product demo video for TikTok using Hyperframes with your product's key features.

Frequently Asked Questions about video

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a video with code using Hyperframes or Remotion?▼

Hyperframes lets you define each frame as an HTML document and compose them into a timeline rendered to MP4, requiring no framework knowledge. Remotion uses React components as frames with props driving content, and supports batch rendering via Remotion Lambda on AWS.

Which AI video generation model should I use: Veo, Runway, Kling, or Pika?▼

Veo offers the highest quality with synced audio, Runway Gen-4 provides strong motion control and temporal consistency, Kling generates up to 2 minutes at the lowest cost per second, and Pika is fastest for short clips. Choose based on duration, quality, and budget needs.

How do I make a talking-head video without filming?▼

Use AI avatar tools like HeyGen or Synthesia to generate presenter videos from a text script with realistic lip-sync. HeyGen offers 230+ avatars in 140+ languages and has an MCP server so agents can generate videos directly.

Can AI video models render readable text in generated footage?▼

No, AI video models cannot reliably render readable text or logos. Generate the visual footage with AI, then add text overlays programmatically using Hyperframes, Remotion, or CapCut in post-production.

What aspect ratio should I use for TikTok versus YouTube videos?▼

Use 9:16 (1080x1920) for TikTok, Reels, and Shorts, and 16:9 (1920x1080) for YouTube and website embeds. Instagram feed posts work best at 1:1 or 4:5, and LinkedIn supports 16:9 or 1:1.

When should I use an AI avatar versus filming myself?▼

Use avatars for recurring content, multilingual versions, and personalized outreach at scale. Film yourself for authentic founder content, use screen recording for product UI walkthroughs, and use AI generation for creative or artistic visuals.