Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/cclank/lanshu-awesome-ai-video-kitnpx agentmods add skills/cclank/lanshu-awesome-ai-video-kit/seedance-prompterWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cclank/lanshu-awesome-ai-video-kit/seedance-prompter)<a href="https://agentmods.dev/skills/cclank/lanshu-awesome-ai-video-kit/seedance-prompter"><img src="https://agentmods.dev/badge/skills/cclank/lanshu-awesome-ai-video-kit/seedance-prompter/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cclank/lanshu-awesome-ai-video-kit/seedance-prompter"><img src="https://agentmods.dev/badge/skills/cclank/lanshu-awesome-ai-video-kit/seedance-prompter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00142 | $0.01658 |
| Opus 5 | $0.00071 | $0.00829 |
| Sonnet 5 | $0.00028 | $0.00332 |
| Haiku 4.5 | $0.00014 | $0.00166 |
Grade A, and why
seedance-prompter scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
seedance-prompter
把用户的"我想要什么样的视频"转换成 Seedance 2.0 能理解的工程级指令。
何时不用此 skill
- 用户描述的是 5/10/15 秒紧凑短片 或 要原生带音频 → 用 happyhorse-prompter
- 用户已有提示词但效果不对 → 用 seedance-debugger
- 剧情复杂需要多镜头切换 → 用 seedance-storyboard
核心方法论：进阶公式
精准主体 + 动作细节 + 场景环境 + 光影色调 + 镜头运镜 + 视觉风格 + 画质 + 约束条件
工作流程
步骤 1：澄清需求（必要时）
如果用户只给了一两句话（"做个香水广告"），先问清楚以下要素中至少 3 项（不要问全部，挑最影响结果的）：
| 要素 | 示例问题 |
|---|---|
| 主体 | "香水瓶什么样？玻璃透明还是磨砂？" |
| 动作 | "瓶子是静止展示还是旋转/喷雾？" |
| 场景 | "实景还是纯色背景？什么色？" |
| 光影 | "硬光戏剧感还是柔光高级感？" |
| 镜头 | "特写质感优先还是中景展示整瓶？" |
| 风格 | "电影感 / 商业广告 / 极简 / 复古？" |
| 时长/比例 | "竖屏短视频 / 横屏 / 多长？" |
例外：如果用户说"随便""快"或给了参考图，直接生成一版给他改。
步骤 2：按 8 要素填充
写英文（Seedance 对英文响应更好），但用户的核心元素用原文保留（人物名字、品牌名、专有名词）。
模板骨架：
[Subject with 2-3 stable identifying features].
[Action with specific body parts + speed/intensity].
[Scene/environment].
[Light source + time of day + color tone].
[Camera size + movement + angle].
[Visual style + film grain/aesthetic anchor].
[Quality: cinematic / 4K / photorealistic].
[Negative: avoid ...; no watermark; no logo; preserve face stability].
步骤 3：检查避免错误
提交前自查：
- 提示词 50-200 词之间？
- 一个镜头只指定 1 种运镜方式（不要同时推+拉+摇）？
- 没有矛盾词（如
8mm+4K、slow motion+high speed）？ - 有约束条件（至少
no watermark, no logo）？ - 多主体场景已用标签区分（"警察"/"小偷"）？
步骤 4：输出格式
给用户一份完整的提示词，加 3 个说明：
## 生成的提示词
\`\`\`
[完整提示词]
\`\`\`
**推荐参数**：宽高比 [X:Y] · 时长 [N 秒] · 分辨率 1080p
**关键技巧**：[1-2 句说明这条提示词的设计思路]
**可调点**：[告诉用户可以怎么改 — 比如换光影/换风格/换镜头]
实战示例
用户输入："给我做个咖啡的广告"
澄清问题（一次性问，不超过 3 个）：
- 镜头视角偏好 — 极特写质感（油花/蒸汽）还是中景实景（咖啡馆桌面）？
- 情绪基调 — 温暖（晨间/木质） 还是 高端（黑底/聚光）？
- 投放渠道 — 竖屏抖音 / 横屏电视 / 正方形 IG？
用户答：极特写、温暖、竖屏。
输出：
Extreme close-up of rich cream being poured into a freshly brewed dark espresso in slow motion, creating a mesmerizing vortex pattern across the crema surface. Wisps of steam rise softly from the cup. Warm tungsten side-light highlights the contrast between cream and coffee, casting soft amber reflections on the ceramic edge. The camera slowly pulls back from macro to medium shot, revealing a styled wooden café table with a sprig of cinnamon and a folded linen napkin. Commercial quality, appetizing warm color grading, 4K, shallow depth of field, photorealistic liquid dynamics. No text overlays, no watermark, no logo.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 13d ago First seen · 123 lines · 142 tokens per session scan A d52c2d3ebe18
seedance-prompter is a skill published in the GitHub repository cclank/lanshu-awesome-ai-video-kit (392 stars, last pushed 3mo ago), licensed MIT. It adds 142 tokens to every session and 1,658 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
cost-aware-llm-pipeline
A planning guide for choosing language models and managing the amount of conversation context used by an AI coding workflow. It groups tasks by complexity and gives rules for avoiding context overflow during long sessions.
shortfilm-prompt
Generate cinematic AI shortfilm prompts (works with Seedance 2.0, Xiaoyunque, Sora, Kling, Jimeng, Veo) using the 5-stage structure from Mx-Shell's Zombie Scavenger. Trigger when the user wants transformation sequences, multi-shot narrative shorts, weapon-charge/combat segments, emotional family/pet/farewell…
universal-video-prompt-skill
Write one model-agnostic video prompt spec, then compile it to whichever video model you can actually call. Use for cross-model prompt work, model comparison matrices, reusing one brief across providers, or when the target model is not yet available and the work must proceed on another one.
optimize-prompts
Use this to improve a prompt systematically instead of hand-tweaking it by feel. Trigger on "optimize my prompt", "make this prompt better", "the prompt isn't working well", "auto-tune my prompt", "few-shot example selection", or when prompt quality has plateaued. Optimize against an eval set with a method, and let…
agent-orchestration-improve-agent
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
prompt-engineer
Expert-level Prompt Engineer skill. Transforms AI into a specialist who designs, evaluates, and optimizes prompts for LLMs, RAG pipelines, and agent workflows. Covers prompt patterns (zero-shot, few-shot, CoT, ReAct, Tree-of-Thought), RAG context injection and chunking strategies, agent tool-calling and multi-agent…