Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
This collection provides specialized skills for AI agents to automate the creation of multimedia content. It focuses on structured video production, offering specific frameworks for SaaS product explainers and founder-led videos.
Automation builders can use these skills to integrate generative media into content workflows, moving from raw prompts to formatted marketing assets.
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Create ~/.pexo/config manually. Set PEXO_BASE_URL to "https://pexo.ai" and replace "sk-..." with the Pexo API key obtained from https://pexo.ai.
Run this terminal verification command, replacing <skills-path> with the host's documented skills directory: ~/.claude/skills for Claude Code, ~/.openclaw/skills for OpenClaw, ~/.codex/skills for Codex, or ~/.cursor/skills for Cursor.
Installs: The complete documented pexo Claude Code plugin bundle, which includes the Pexo agent plus image, audio, director, and model-prompting skills. The listed skill paths are the seven paths explicitly mapped by the marketplace manifest. · Claude Code
Before you start
Claude Code.
A Pexo API key obtained from https://pexo.ai for the Pexo integration.
Enter these two commands in a Claude Code agent session, in order, to add the marketplace and install the plugin.
Create ~/.pexo/config manually. Set PEXO_BASE_URL to "https://pexo.ai" and replace "sk-<your-key>" with the Pexo API key obtained from https://pexo.ai.
Create ~/.pexo/config manually. Set PEXO_BASE_URL to "https://pexo.ai" and replace "sk-<your-key>" with the Pexo API key obtained from https://pexo.ai.
Design a Seedance 2.0 cinematic prompt from two images
Uses seedance-2.0-prompter
An uploaded subject image; [subject-image-path] is a placeholder for its path.
An uploaded product image; [product-image-path] is a placeholder for its path.
Any desired action or visual style.
Use the seedance-2.0-prompter skill to turn these two uploaded images into a structured Seedance 2.0 prompt: make the subject in [subject-image-path] drink from the product shown in [product-image-path]. Give it a cinematic close-up style and return the optimized JSON prompt with recommended parameters.
An uploaded product image; [product-image-path] is a placeholder for its path.
The desired product action and commercial style.
Use the veo-3.2-prompter skill to create a structured Veo 3.2 prompt for the product in [product-image-path], rotating on a dark reflective surface like a cinematic luxury commercial. Return the optimized JSON prompt, reference-image mapping, and recommended parameters.
A concise description of how the product works; [product-description] is a placeholder.
Make sure explainer-video is installed in your agent before trying this task.
Use the explainer-video skill to explain how [product-name] works in a 60-second video with narration and captions. Base the explanation on this description: [product-description].
Claude
Codex
Cursor
Gemini CLI
OpenClaw
Grok