Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →cclank/prompt-translator
把一条 AI 视频提示词从源模型(如 Sora 2)的写法风格转换为目标模型(如 Kling 3.0 / Wan 2.7 / Veo 3.1 等)的最佳实践写法。基于 110 条 10 场景 × 11 模型对照基准数据(prompts/data/cross-model-matrix.json),不是凭直觉重写,而是查表式 in-context learning。10 场景:产品 / 双人对话 / 物理动作 / 图生视频 / 多人会议 / 恐怖 / 自然延时 / 抽象 / 武侠 / 萌宠。用于"Sora 已 EOL 帮我把这条提示词改成 Veo"、"我有 Kling 提示词想跑 Wan"、"跨模型 A/B 测试"、"把英文 prompt 优化成 Kling 中文版"等触发场景。
Passed 20 of 22 test cases with the skill, and 3 of 22 without it.
and 39 more in the full report
17 fixed3 passed either way2 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 17 test cases the skill fixed. Same model, same prompt, with and without the skill.
Translate this Wan 2.7 prompt into HappyHorse 1.0 format for a 5-second video clip: Entity: A red vintage sports car. Scene: Empty coastal highway at sunset. Motion: Car accelerates down the straight road, leaving tire smoke behind. Sound: Engine roar.
| Checked | Without skill | With skill |
|---|---|---|
| Begins the target HappyHorse 1.0 prompt text with 5s duration. | Missed | Passed |
| Formats the HappyHorse prompt as compact prose without section headers. | Missed | Passed |
The instructions your model reads when the skill loads.
跨模型提示词转换器。关键差异:不是凭 AI 直觉重写,而是查 110 条对照基准做 in-context learning。
seedance-prompter / kling-prompter / happyhorse-prompter 或 model-selectormodel-selectorseedance-debuggerprompts/data/cross-model-matrix.json — 这就是 translator 的"训练数据":
最少需要:
可选:
提取核心场景元素(与具体写法风格无关的):
test cases passed, vs 3 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.