Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add jeurtr/seedance-skill --skill zhgit clone --depth 1 https://github.com/jeurtr/seedance-skillWrote 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/jeurtr/seedance-skill/zh)<a href="https://agentmods.dev/skills/jeurtr/seedance-skill/zh"><img src="https://agentmods.dev/badge/skills/jeurtr/seedance-skill/zh.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00124 | $0.05966 |
| Opus 5 | $0.00062 | $0.02983 |
| Sonnet 5 | $0.00025 | $0.01193 |
| Haiku 4.5 | $0.00012 | $0.00597 |
Grade A, and why
seedance 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 8d 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 — 468 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Seedance 视频生成技能
字节跳动 Seedance 2.0/2.5 AI 视频生成模型综合技能指南。涵盖提示词工程、镜头语言、光影、多镜头叙事、API 集成及跨平台故障排除。
核心理念
三项原则贯穿所有交互：
- 听见意图背后的感受。 用户描述的是结果（"让它有家的感觉"），而非参数。将感受转化为制作语言；绝不把翻译工作推回给用户。
- 保持故事连贯。 在对话中维护状态：主体、模式、风格、引用素材、已确定的约束、之前失败的尝试。用户不应重复任何决定；新请求继承已构建的世界。
- 与用户共同成长。 对初学者说通俗语言，对专业人士用导演术语——并察觉同一用户在项目中从一者成长为另一者。表达方式可以调整，标准绝不降低。
快速入门
当用户想要创建 Seedance 视频时：
- 询问创建目标 — 视频类型、情绪、时长
- 询问已有素材 — 图片、视频、音频文件
- 按下方结构撰写提示词
- 简要说明你的选择理由
- 提供变体 — 更简或更野的版本
- 提醒约束条件 — 人脸限制和文件上限
对于简单的单片段请求，直接起草即可，无需对一次性片段运行完整分析流程。
平台接入
| 平台 | 接入方式 | 适用场景 |
|---|---|---|
| Dreamina（即梦） | 字节官方平台，每日免费积分 | 普通创作者，可视化界面 |
| 豆包 | VPN 连香港，约 10 积分/天 | 免费测试 |
| CapCut Pro | 部分集成 | 视频剪辑师 |
| Fal AI | fal.ai 获取 API key | 开发者，程序化调用 |
| 火山方舟 / Ark | 字节云 API | 生产环境，企业级 |
| Runway（Seedance 线路） | Runway API key | Runway 生态用户 |
| Replicate | Cog 模型 | 开发者 |
| MuAPI | 统一 API 网关 | 多供应商接入 |
API 端点
# Fal AI
图生视频: fal-ai/seedance-2.0/pro/image-to-video
参考生视频: fal-ai/seedance-2.0/pro/reference-to-video
文生视频: fal-ai/seedance-2.0/pro/text-to-video
# MuAPI
文生视频: POST https://api.muapi.ai/api/v1/seedance-2.5-t2v
图生视频: POST https://api.muapi.ai/api/v1/seedance-2.5-i2v
视频延长: POST https://api.muapi.ai/api/v1/seedance-2.5-extend
输入约束
| 输入类型 | 上限 | 格式 | 最大体积 |
|---|---|---|---|
| 图片 | ≤ 9（2.0）/ ≤ 30（2.5） | jpeg, png, webp, bmp, tiff, gif | 每张 30 MB |
| 视频 | ≤ 3（2.0）/ ≤ 10（2.5），总时长 ≤ 15s（2.0）/ 30s（2.5） | mp4, mov | 每个 50 MB |
| 音频 | ≤ 3（2.0）/ ≤ 10（2.5），总时长 ≤ 15s（2.0）/ 30s（2.5） | mp3, wav | 每个 15 MB |
| 文件总计 | ≤ 12（2.0）/ ≤ 50（2.5） | — | — |
输出规格
- 时长：4–15s（2.0），4–30s（2.5）
- 分辨率：480p、720p（1080p、4K 规划中）
- 画幅比：
21:916:94:31:13:49:16 - 格式：MP4（默认），MOV（2.5，高色彩保真度）
- 原生音视频同步，自动生成音效/背景音乐
关键限制
- 上传图片中不得出现逼真人脸（官方平台合规要求）
- 即梦/Dreamina 会自动拦截含逼真人脸的上传
- 引用视频素材时生成成本略高
- 优先上传对视觉效果或节奏影响最大的素材
生成模式
| 模式 | 说明 | 适用场景 |
|---|---|---|
| T2V（文生视频） | 仅通过文本生成 | 无参考素材 |
| I2V（图生视频） | 让静态图片动起来 | 有参考图，需要可控输出 |
| V2V（视频生视频） | 重新风格化/诠释一段视频 | 迁移运镜、节奏 |
| R2V（参考生视频） | 多模态：图片 + 视频 + 音频组合 | 最大控制力，最佳质量 |
| FLF2V（首尾帧） | 两个关键帧之间插值 | 精确控制起始与结束 |
| Edit（视频编辑） | 保留源视频，修改单一图层 | 换角色、换服装、改背景 |
| Extend（延长） | 从已确认素材继续生成 | 延长片段、无缝衔接 |
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.
- 8d ago First seen · 468 lines · 124 tokens per session scan A 3dfd8bb04a31
seedance is a skill published in the GitHub repository jeurtr/seedance-skill (2 stars, last pushed 1mo ago), licensed MIT. It adds 124 tokens to every session and 5,966 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
video-gen
Use when generate videos with AI models — Runway, Kling, Sora, Pika, Seedance 2.0, Grok Imagine, Veo. Text-to-video, image-to-video, video extension, multi-modal references. Use when generating video from text prompts, animating images, or creating AI video content.
seedance-20
This skill should be used when creating, improving, or troubleshooting Seedance 2.0 video on any surface — Dreamina, Jimeng, CapCut, Doubao, Volcengine/Ark, BytePlus, Runway's Seedance route, fal, or third-party provider/router surfaces such as EvoLink, OpenRouter, Kie.ai, PiAPI, LaoZhang, Runware, ModelsLab, AI/ML…
seedance-2-5-prompt-director
A skill for writing and improving prompts for Seedance 2.5, a video-generation system. It covers text-to-video, image-to-video, editing, video extension, references, camera movement, green-screen work, sound, and lip sync.
seedance-prompt
This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.0 video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt.
seedance-20
Generate and direct cinematic AI videos with Seedance 2.0 (ByteDance/Dreamina/Jimeng). Covers text-to-video, image-to-video, video-to-video, and reference-to-video workflows with @Tag asset references, multi-character scenes, audio design, and post-processing. Use when making AI video, writing Seedance prompts…
lanshu-create-ai-presenter-video
Turn a topic or finished script plus an authorized adult presenter image into a complete, publish-ready AI presenter video. Use for new presenter videos and for continuing, revising, captioning, lip-sync repairing, or re-exporting an existing presenter-video job. Keep model and provider selection capability-based and…