video

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

Updated May 6, 2026
One-click install
npx skills add https://github.com/UnionStreetAI/unionstreet --skill video-unionstreetai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: video
Source: https://github.com/UnionStreetAI/unionstreet/tree/main/plugins/gtm/skills/video
Command: npx skills add https://github.com/UnionStreetAI/unionstreet --skill video-unionstreetai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? Producing marketing videos normally requires filming, editing skills, and expensive tooling. This Skill guides you through creating product demos, explainers, social clips, and ads using AI video generation models, AI avatar platforms, and code-based video frameworks, so you can produce professional 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 guide covering camera movement, style keywords, and model-specific tips. - AI Avatars: Create talking-head presenter videos with HeyGen (which offers an MCP server for direct agent integration) or Synthesia for explainers and multilingual content. - Use Case: You need a vertical product demo for TikTok. The Skill helps you script the value props, screen-record the product, add programmatic title overlays via Hyperframes, generate B-roll with Veo, and export at 1080x1920. ## Quick Start Ask the agent to create a 30-second vertical product explainer video using an AI avatar and programmatic title overlays for TikTok.

Frequently Asked Questions about video

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

FAQPage Schema
How do I create a product demo video with AI tools?▼

Script the key features, screen-record the product flow, add programmatic titles and transitions with Hyperframes or Remotion, generate B-roll with Veo or Runway, and add a voiceover or AI avatar narration. Export at platform-appropriate specs such as 9:16 for social or 16:9 for YouTube.

Hyperframes vs Remotion for programmatic video?▼

Hyperframes uses plain HTML/CSS/JS, making it easier for coding agents to generate frames with deterministic rendering, and it is Apache 2.0 licensed. Remotion is React-based with more advanced animation and AWS Lambda batch rendering, but has a steeper learning curve and a commercial license.

What AI video generation model should I use?▼

Veo 3 offers the highest quality with synced audio, Runway Gen-4 provides strong motion control and temporal consistency, Kling 3.0 supports up to 2-minute clips at the lowest cost per second, and Pika is fastest for short clips and quick iterations.

Can AI agents generate avatar videos directly?▼

Yes. HeyGen provides an official MCP server, so AI agents can generate talking-head avatar videos directly from text scripts. HeyGen offers 230+ avatars and 140+ languages, with a free tier of 3 videos per month.

Why does AI-generated video have unreadable text?▼

AI video models cannot reliably render readable text or logos. Instead, generate the footage without text and add titles, captions, and overlays in post-production using programmatic tools like Hyperframes or editors like CapCut.

When should I not use an AI avatar for video?▼

Avoid avatars for authentic founder content, product UI walkthroughs, and creative or artistic videos. Film yourself for founder content, use screen recording for UI demos, and use AI generation models for creative visuals instead.