
Model Selector
You're staring at 16 AI video models wondering which one actually fits your use case. This asks you 3-4 pointed questions about duration, audio needs, Chinese vs English, editing vs generation, then recommends 1-3 models with reasons. It covers the commercial heavy hitters (Kling, Sora, Runway, Veo) plus Chinese options (即梦, Wan, Hailuo) and four open source models including Hunyuan for local deployment. The decision tree is practical: editing existing footage goes straight to Runway Aleph, lip sync to Wan 2.7, extreme physics to Hailuo or Sora. Good for "which model should I use" questions before you dive into model-specific prompter skills. Saves you from reading 16 different docs when you just need one answer.
- GitHub stars
- 269
- last updated
- Jun 1, 2026
Install
$ npx -y skills add cclank/lanshu-awesome-ai-video-kit --skill model-selector --agent claude-codeInstalls into .claude/skills of the current project.
Files
model-selector
15 个主流 AI 视频模型(11 商业 + 4 开源)的"购物顾问"。问用户 3-4 个关键问题,给出推荐 + 理由。
何时不用此 skill
- 用户已经确定要用某个模型 → 用对应的
<model>-prompterskill - 用户问"提示词怎么写" → 用
seedance-prompter/kling-prompter/happyhorse-prompter - 用户的提示词不工作 → 用
seedance-debugger
11 模型能力速查矩阵
Sponsors
Details
- Repository
- github.com/cclank/lanshu-awesome-ai-video-kit
- Category
- AI & Agent Building
- License
- MIT
- First seen
- Jun 11, 2026