videoagent-video-studio
๐ฏSkillfrom pexoai/pexo-skills
An AI creative skill for text-to-video, image-to-video, and reference-to-video generation supporting 7 models (Kling, Veo, Grok, Seedance, MiniMax, Hunyuan, PixVerse) with zero API key setup and a free tier included.
Overview
An AI creative skill for video generation from pexo-skills that supports text-to-video, image-to-video, and reference-to-video workflows. It connects to 7 video generation models through a single interface with zero API key setup and includes a free tier.
Key Features
- 7 video models โ Kling, Veo, Grok, Seedance, MiniMax, Hunyuan, and PixVerse accessible through one skill
- Zero setup โ No API keys required for core functionality; just install and go
- Multiple workflows โ Text-to-video, image-to-video, and reference-to-video generation
- Production-ready โ Rate limiting, error handling, and async polling built in
- Free tier included โ Start creating without payment
- Compatible โ Works with Claude Code, OpenClaw, and any agent supporting the Agent Skills standard
- Part of pexo-skills โ Alongside image-studio (Midjourney, Flux, Ideogram, Recraft, Gemini) and audio-studio (ElevenLabs)
Who is this for?
Developers and creators who want AI video generation directly from their coding agent without managing multiple API keys. Ideal for content creators, marketers, and developers building video-powered applications who want a single interface to multiple video models.
Same repository
pexoai/pexo-skills(12 items)
Installation
npx vibeindex add pexoai/pexo-skills --skill videoagent-video-studionpx skills add pexoai/pexo-skills --skill videoagent-video-studio~/.claude/skills/videoagent-video-studio/SKILL.mdSKILL.md
More from this repository10
Delegates short video production (5โ120 seconds) to the Pexo AI video agent โ scriptwriting, shot composition, transitions, and music for product ads, social clips, explainers, and brand videos in 16:9, 9:16, or 1:1.
Skill
Skill
Skill
Top-level Pexo AI creative partner skill โ turns a conversation into complete, publish-ready content by picking the best AI models (Midjourney / Flux / Ideogram / Recraft / Gemini for images, Kling / Veo / Grok / Seedance / MiniMax / Hunyuan / PixVerse for video, ElevenLabs / CassetteAI for audio) so the user writes no prompts and chooses no models.
Skill
Skill
Skill
Skill
Skill