Tuzi Video Gen

This is a video generation backend that hits the Tuzi API with support for Veo, Sora, Kling, and Seedance models. The interesting bit is the long video mode, which chains multiple segments together by feeding each segment's last frame as a reference image to the next one, then stitches everything with ffmpeg. It handles the usual CLI options for prompts, durations, and aspect ratios, plus it has a preferences system through EXTEND.md files so you're not constantly passing the same flags. Default model is veo3.1. You'll need an API key from tu-zi.com and ffmpeg installed if you want the multi-segment concatenation to work.

skills.sh installs: 189
GitHub stars: 39
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add tuziapi/tuzi-skills --skill tuzi-video-gen --agent claude-code

Installs into .claude/skills of the current project.

Files

Video Generation (AI SDK)

Tuzi API video generation backend. Default model: veo3.1.

Script Directory

Agent Execution:

SKILL_DIR = this SKILL.md file's directory
Script path = ${SKILL_DIR}/scripts/main.ts

Step 0: Load Preferences ⛔ BLOCKING

CRITICAL: This step MUST complete BEFORE any video generation. Do NOT skip or defer.

0.1 Check API Key

echo "${TUZI_API_KEY:-not_set}"
grep -s TUZI_API_KEY .tuzi-skills/.env "$HOME/.tuzi-skills/.env"

Result	Action
Key found	Continue to Step 0.2
Key NOT found	⛔ Run API key setup (see references/config/first-time-setup.md) → Store key → Then continue

0.2 Check EXTEND.md

test -f .tuzi-skills/tuzi-video-gen/EXTEND.md && echo "project"
test -f "$HOME/.tuzi-skills/tuzi-video-gen/EXTEND.md" && echo "user"

Result	Action
Found	Load, parse, apply settings
Not found	⛔ Run first-time setup (references/config/first-time-setup.md) → Save EXTEND.md → Then continue

SKILL.md on GitHub

Details

Repository: github.com/tuziapi/tuzi-skills
Categories: Backend & APIs, Generative Media
First seen: Jun 3, 2026