Open-source AI video creation workspace with an infinite canvas, where a natural-language assistant builds workflows linking text, image and video nodes.
1.7K+6 this week253PythonApache-2.0Updated 2 months ago
pexoai/pexo-skills
Open-source Agent Skills that let coding agents like Claude Code and Cursor turn text, images, URLs, scripts, or audio into finished AI videos.
- Stars
- 822
- Forks
- 49
- Open issues
- 10
- Last commit
- 3 months ago
What is it?
pexo-skills is a collection of MIT-licensed Agent Skills for AI content creation, covering images, audio, and video. Installed into a coding agent such as Claude Code, Cursor, or OpenClaw, the skills take a natural-language brief and handle the production steps: choosing a video model, writing prompts, generating each shot, and assembling a multi-shot video with music and subtitles.
The main entry point is the pexo-agent skill, which covers the full pipeline and supports 5 to 120 second videos in 16:9, 9:16, or 1:1. The repository also includes scenario skills such as product video, TikTok ad, and explainer video, along with lower-level studio skills for choosing a specific image, video, or audio model directly. Supported models include Seedance 2, Kling 3.0, Veo, Midjourney, Flux, and ElevenLabs, all accessed through a single Pexo API key.
Key features
- 01Auto model selection routes each shot to a suitable video model based on its content.
- 02Turns text, product images, URLs, scripts, or audio into a finished video.
- 03Builds multi-shot sequences with storyboarding, transitions, music, and subtitles.
- 04Includes TTS narration, voice cloning, and lip sync.
- 05Offers scenario skills for ads, product videos, and explainers, plus studio skills for direct model control.
- 06Works with Claude Code, Cursor, OpenClaw, and any agent that follows the Agent Skills standard.
Use cases
- Producing short product ads for TikTok, Instagram Reels, or YouTube from a product photo or store URL.
- Generating several ad variants from one brief for A/B testing.
- Turning a written script with scene descriptions into a narrated explainer video.
- Creating brand or launch videos with a storyboard and background music.
Quick start
- 1
Install the pexo-agent skill with skills.sh
npx skills add https://github.com/pexoai/pexo-skills --skill pexo-agent - 2
Or install the pexo-video-agent skill from ClawHub
openclaw skills install pexo-video-agent
Things to know
- Requires a Pexo API key, so generation depends on a paid or account-based service.
In collections
Topics
FAQ
- What is pexo-skills?
- Open-source Agent Skills that let coding agents like Claude Code and Cursor turn text, images, URLs, scripts, or audio into finished AI videos. pexo-skills is a collection of MIT-licensed Agent Skills for AI content creation, covering images, audio, and video. Installed into a coding agent such as Claude Code, Cursor, or OpenClaw, the skills take a natural-language brief and handle the production steps: choosing a video model, writing prompts, generating each shot, and assembling a multi-shot video with music and subtitles.
- Is pexo-skills free to use? What license does it have?
- pexo-skills is open source under the MIT license. Check the license terms before using it in commercial products.
- Is pexo-skills still maintained?
- Updated within 6 months. The last commit to pexo-skills was on Aug 20, 2026.
- What can I use pexo-skills for?
- Producing short product ads for TikTok, Instagram Reels, or YouTube from a product photo or store URL. Generating several ad variants from one brief for A/B testing. Turning a written script with scene descriptions into a narrated explainer video. Creating brand or launch videos with a storyboard and background music.
- How do I install pexo-skills?
- Install the pexo-agent skill with skills.sh: npx skills add https://github.com/pexoai/pexo-skills --skill pexo-agent Or install the pexo-video-agent skill from ClawHub: openclaw skills install pexo-video-agent
- Where can I get pexo-skills?
- The source code and installation instructions are on GitHub: https://github.com/pexoai/pexo-skills
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
An agent skill that turns one topic into a finished Vox-style paper-collage explainer video, automating script, images, motion, voice-over, music and captions.
2.7K+147 this week373PythonMITUpdated last month
A curated prompt library, methodology guides and Claude Skills for writing prompts across about 15 AI video generation models.
445+7 this week105HTMLMITUpdated last month
Open-source large-scale video generative models for text-to-video, image-to-video, speech-to-video and character animation.
AI & Machine Learning#video-generation#text-to-video#image-to-video#diffusion-model#mixture-of-experts
18.5K+161 this week2.4KPythonApache-2.0Updated 2 months ago
A ComfyUI custom node that adds a multi-segment storyboard director for MiniMax H3 video generation with native stereo audio.
2.7K+53 this week324JavaScriptApache-2.0Updated 25 days ago
A video generation framework for Diffusion Transformer models that creates videos at flexible resolutions and from images, with training support for baseline and LoRA models.
2.3K+7 this week199PythonApache-2.0Updated 2 days ago