uniqaiapp

Video Director — AI skill for Claude Code

AI community

AI video prompt director for Kling 3.0, Veo 3, Wan, Runway and Seedance: turns a one-line idea into a shot list with camera moves, lens, lighting, duration and model-specific syntax.

How to install Video Director

This entry records only its repository, not the path inside it, so there is no exact command to give. Open uniqaiapp/video-director and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Video Director does

AI video prompt director for Kling 3.0, Veo 3, Wan, Runway and Seedance: turns a one-line idea into a shot list with camera moves, lens, lighting, duration and model-specific syntax. Claude Code skill + Cursor/Codex rules + prompt templates. Text-to-video and image-to-video. By UniqAI.

Alternatives in AI

  • Humanize Ppt — AST-based outline director for human-centered AI presentation workflows 934 ★
  • Make Prompt Seedance2 — 一句话:试错成本越来越高,提示词的重要性从来没有像今天这样大 418 ★
  • Open AI Design Agent — Open-source AI design agent — alternative to Lovart AI, Runway Agent, Luma Labs Agent, Krea Agent, Pika Agent 356 ★

README

video-director: Turn a one-line idea into a shot-by-shot prompt for AI video models (Kling, Veo, Sora and others), with camera, lighting and motion vocabulary.

video-director: AI video prompts for Kling, Veo 3, Wan and Runway

[![License: MIT](https://img.shields.io/badge/license-MIT-d1fe17?style=flat-square&labelColor=0d0f12)](LICENSE) [![Claude Code skill](https://img.shields.io/badge/Claude_Code-skill-d1fe17?style=flat-square&labelColor=0d0f12)](#install) [![Cursor](https://img.shields.io/badge/Cursor-rules-d1fe17?style=flat-square&labelColor=0d0f12)](#install) [![Codex](https://img.shields.io/badge/Codex-AGENTS.md-d1fe17?style=flat-square&labelColor=0d0f12)](#install) [![Zero dependencies](https://img.shields.io/badge/dependencies-0-d1fe17?style=flat-square&labelColor=0d0f12)](#install)

**Idea in, second-by-second storyboard out, rendered as a prompt in each model's own shape.**

[Quickstart](#quickstart) · [How it works](#how-it-works) · [Examples](#examples) · [Install](#install) · [FAQ](#faq)

English · [Русский](README.ru.md) · [简体中文](README.zh-CN.md) · [Español](README.es.md) · [Português (BR)](README.pt-BR.md) · [日本語](README.ja.md) · [한국어](README.ko.md)

AI video prompts for Kling 3.0, Veo 3, Wan 2.5, Seedance and Runway, written the way the models read them: a timed storyboard (0-2 s, 2-4 s, ...) with one camera move per beat, a lens, a light setup, a sentence of motion physics, three layers of sound and a short negative list, then rendered per model with its length limit, negative-prompt handling and audio support applied. Works for text-to-video and image-to-video. It ships as a Claude Code skill, a Cursor rule and a Codex / `AGENTS.md` snippet, plus a stdlib Python script you can r