donghaozhangdonghaozhangCommunityยท1 Agent Skills Included

video-agent-skill

Generate images, videos, avatars, and speech from text

Generates images, videos, talking avatars, and speech from text prompts using 73 models across 12 categories. Chains multi-step workflows through YAML pipelines with parallel execution for faster rendering. Transcribes audio, analyzes videos, and processes media with FFmpeg commands. Removes manual model selection, API wiring, and repetitive media conversion work.
npx skills add donghaozhang/video-agent-skill --all -g -y
Available:

Gives your AI agent the project structure, CLI commands, environment setup, and coding rules needed to run and extend this content generation pipeline correctly.

All Skills in This Repository (1)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install video-agent-skill?โ–ผ

Run `npx skills add donghaozhang/video-agent-skill --all -g -y` in your terminal to install all skills in this suite globally.

How to generate videos from text prompts?โ–ผ

Use the `aicp create-video --text "your prompt"` command, which generates an image and animates it into a video using models like Veo 3, Sora 2, or Kling.

Can it create talking avatars with lip-sync?โ–ผ

Yes. Run `aicp generate-avatar` with an image and audio file to produce lip-synced talking avatars using models like OmniHuman and MultiTalk.

Does it work with Claude Code and Cursor?โ–ผ

Yes. The skills follow the standard SKILL.md format and run in Claude Code, Cursor, and other compatible coding environments.

What API keys do I need?โ–ผ

You need a FAL API key for most models, plus optional Gemini, ElevenLabs, and OpenRouter keys for video analysis, speech, and prompt generation.

Related Repositories in Design & Creative

View All in Design & Creativeโ†’