video-init

video-init - Initialize project

Overview

Initialize a new video project and create the directory structure.Interactive confirmation is implemented at the skill layer via AskUserQuestion。

Trigger conditions

Triggered when the user says "create a new project", "initialize project", or similar expressions.

Interaction flow

Step 1: Ask for the project name

Use AskUserQuestion to ask:

"Please give the project a name?"

Step 2: Ask for the image generation provider

选项:
1) volcengine (火山引擎 Seedream)
2) dashscope (阿里云)
3) gemini (Google)
4) mock (测试用)

Step 3: Ask for the video generation provider

选项:
1) volcengine (火山引擎 Seedance)
2) dashscope (阿里云 Wan2.6)
3) mock (测试用)

Step 4: Ask for the storage method

选项:
1) local (本地存储)
2) google_drive (上传到 Google Drive)

Execution flow

1. Use AskUserQuestion to collect the configuration in sequence (project name, image provider, video provider, storage method)
2. Call videoclaw init <project-name> to create the project
3. Use videoclaw config --project <name> --set to set the project configuration (using the new backend field is recommended; if a Codex / ChatGPT login environment already exists, it is recommended to prioritize the Codex-first path)

# 示例执行
videoclaw init my-video
videoclaw config --project my-video --set models.image.backend=codex-host-image
videoclaw config --project my-video --set models.image.model=gpt-image-2-medium
videoclaw config --project my-video --set models.image.auth=chatgpt_login
videoclaw config --project my-video --set models.image.transport=codex_oauth
videoclaw config --project my-video --set models.video.provider=volcengine
videoclaw config --project my-video --set storage.provider=google_drive

Created directories

• assets/ - Shared characters, scenes, props, cover
• videos/ - Multiple video units (each video is managed independently)
• exports/ - Final delivery artifacts

Parameters

• project_name: Project name (required)
• --dir: Project directory path (optional, defaults to ~/videoclaw-projects)

Global configuration (optional)

Users can also set the global configuration first, and new projects will automatically use it:

# 设置全局默认提供商
videoclaw config --set models.image.backend=volcengine
videoclaw config --set models.video.provider=volcengine
videoclaw config --set storage.provider=google_drive

Example

用户: 帮我创建一个新项目

Claude Code:
  - 询问项目名称
  - 询问图像提供商（volcengine/dashscope/gemini/mock）
  - 询问视频提供商（volcengine/dashscope/mock）
  - 询问存储方式（local/google_drive）
  - 执行: videoclaw init my-video
  - 执行: videoclaw config --project my-video --set models.image.backend=xxx
  - 执行: videoclaw config --project my-video --set models.video.provider=xxx
  - 执行: videoclaw config --project my-video --set storage.provider=xxx