Initializes a new video project with directory structure and prompts for project name, image provider, video provider, and storage method using the videoclaw CLI.
How this skill is triggered — by the user, by Claude, or both
Slash command
/videoclaw-claude-adapter:video-initThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
初始化新的视频项目,创建目录结构。**交互确认在 skill 层通过 AskUserQuestion 实现**。
初始化新的视频项目,创建目录结构。交互确认在 skill 层通过 AskUserQuestion 实现。
用户说"创建一个新项目"、"初始化项目"或类似表达时触发。
用 AskUserQuestion 询问:
"请给项目起个名字?"
选项:
1) volcengine (火山引擎 Seedream)
2) dashscope (阿里云)
3) gemini (Google)
4) mock (测试用)
选项:
1) volcengine (火山引擎 Seedance)
2) dashscope (阿里云 Wan2.6)
3) mock (测试用)
选项:
1) local (本地存储)
2) google_drive (上传到 Google Drive)
videoclaw init <project-name> 创建项目videoclaw config --project <name> --set 设置项目配置(推荐使用新的 backend 字段)# 示例执行
videoclaw init my-video
videoclaw config --project my-video --set models.image.backend=gemini
videoclaw config --project my-video --set models.video.provider=volcengine
videoclaw config --project my-video --set storage.provider=google_drive
assets/ - 共享角色、场景、道具、封面videos/ - 多个视频单元(每个 video 独立管理)exports/ - 最终交付产物project_name: 项目名称(必填)--dir: 项目目录路径(可选,默认 ~/videoclaw-projects)用户也可以先设置全局配置,新项目会自动使用:
# 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
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
npx claudepluginhub t0ugh/videoclawOrchestrates AI video production workflow: gathers specs interactively, generates scripts/storyboards, Gemini TTS voiceovers, Lyria music, Veo 3.1 clips or image animations, assembles with FFmpeg.
Integrates generative video into applications: text-to-video, image-to-video, avatar video. Covers async architecture, cost optimization, cinematographic prompting, provider selection (FAL.ai, Veo, Sora, Runway).
Generates finished multi-shot videos (5–120s) from text, images, URLs, scripts, or audio with auto model selection across 10+ video generation models. Includes AI music, lip sync, and subtitles.