Happyhorse Prompter
This generates tight 30-55 word prompts for HappyHorse 1.0, Alibaba's video model that does native audio-video generation. The core discipline is subject-first grammar, explicit camera specs, and audio activation phrases like "with rain on leaves audible" or "speaking English at natural pace". It includes an 8-second temporal beat structure for sequenced shots. The hard rule on duration placement is useful: either put it at the very front as a timing anchor or omit it entirely from the prompt and note it in metadata. If you need multi-shot sequences or 10-15 second complexity, the docs point you to the Seedance skills instead. Good for coffee shop ambience, ASMR prompts, or any 3-8 second clip where you want the model to generate matching sound without post work.
- GitHub stars
- 269
- last updated
- Jun 1, 2026
Install
$ npx -y skills add cclank/lanshu-awesome-ai-video-kit --skill happyhorse-prompter --agent claude-codeInstalls into .claude/skills of the current project.
Files
happyhorse-prompter
HappyHorse 1.0（阿里巴巴 Kling 团队）的核心差异：原生音视频联合生成 + 严格按字数执行。这个 skill 帮你产出符合它脾气的紧凑提示词。
何时不用此 skill
- 需要 10-15 秒长视频 / 多镜头切换 → 用 seedance-prompter 或 seedance-storyboard
- 复杂叙事 / 多主体 → 用 Seedance
- 已有提示词调不出来 → 还在 HappyHorse 范围内的话可以让我帮看，否则用 seedance-debugger
五大黄金规则
规则 1：主体先行，动作其后
- ❌
Walking through a forest, a woman... - ✅
A woman in hiking gear walking through a forest...
规则 2：明确指定镜头技术
HappyHorse 对"特写""广角"的理解非常精确，不要留给模型猜测。
规则 3：提示词长度控制在 30-55 词
- 过短（<30 词） → 输出模糊
- 过长（>60 词） → 模型忽略后半段
写完数一下英文单词数。
规则 4：物理效果加运动描述词
头发、水、布料、烟雾、火焰：加 slow motion、motion blur 或 fluid dynamics
规则 5：明确指定音频内容
音频激活路径（这是 HappyHorse 区别于 Seedance 的核心能力）：
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/cclank/lanshu-awesome-ai-video-kit
- Category
- AI & Agent Building
- License
- MIT
- First seen
- Jun 11, 2026
More from cclank/lanshu-awesome-ai-video-kit
All 7Recommended
More AI & Agent Building
seedance-debuggercclank/lanshu-awesome-ai-video-kit诊断 Seedance 2.0 生成视频时出现的常见问题（人物 ID 漂移/双胞胎/字幕/Logo/风格漂移/延长跳变/画质劣化/特效不对/中文发音/音色不准/结尾噪音 等 12 类），定位根因并给出修复后的提示词。用于"我的提示词生成出来不对"、"视频里出现奇怪的字幕"、"人脸不像参考图"、"出现两个一样的人物"、"0skills.sh installsseedance-storyboardcclank/lanshu-awesome-ai-video-kit把复杂剧情/故事大纲拆分为 Seedance 2.0 的"镜头1/镜头2/镜头3"多分镜结构。每个分镜按 4 维度组织（运镜 + 主体动作与表情 + 位置/空间变化 + 音频）。用于"帮我把这个故事写成 Seedance 提示词"、"分镜脚本"、"多镜头视频"、"剧情复杂的视频"、"剧本转分镜"等触发场景。0skills.sh installs
cherry-assistant-guidecherryhq/cherry-studioCherry Studio 产品知识库、源码路径索引、故障排查和页面导航。当用户询问 Cherry Studio 的功能、配置、报错、使用方法时触发。也适用于用户提到 provider、模型、知识库、Agent、MCP、OpenClaw、PDF、快捷短语等关键词的场景。0skills.sh installsgh-pr-reviewcherryhq/cherry-studioAutomated Cherry Studio code review for local branches, PRs, commits, and files. Use for reviewing code, docs, or pull requests with project-specific checks for0skills.sh installs
API Designerdaffy0208/ai-dev-standardsDesign REST and GraphQL APIs. Use when creating backend APIs, defining API contracts, or integrating third-party services. Covers endpoint design, authenticatio0skills.sh installsFrontend Builderdaffy0208/ai-dev-standardsBuild modern React/Next.js frontends. Use when creating web applications, choosing frontend stack, structuring components, or implementing UI/UX designs. Covers0skills.sh installs