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 ShuaiMXu/mv-skills-bundle --skill seedance-2-guidegit clone --depth 1 https://github.com/ShuaiMXu/mv-skills-bundleWrote 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/shuaimxu/mv-skills-bundle/seedance-2-guide)<a href="https://agentmods.dev/skills/shuaimxu/mv-skills-bundle/seedance-2-guide"><img src="https://agentmods.dev/badge/skills/shuaimxu/mv-skills-bundle/seedance-2-guide/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/shuaimxu/mv-skills-bundle/seedance-2-guide"><img src="https://agentmods.dev/badge/skills/shuaimxu/mv-skills-bundle/seedance-2-guide.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00219 | $0.02787 |
| Opus 5.5 | $0.00088 | $0.01115 |
| Sonnet 5.5 | $0.00044 | $0.00557 |
| Haiku 4.5 | $0.00022 | $0.00279 |
Grade A, and why
seedance-2-guide 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 1mo 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 — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Seedance 2.0 · 参考手册
本技能是知识型 Skill，不调接口，不写代码。当你需要判断 Seedance 2.0 的能力边界、选择工作模式、理解提示词结构时查阅本文档。真正的生成调用走
libtv-skill。
⚠️ 与 LibTV Skill 的协作原则（重要）
libtv-skill 的核心原则是：用户侧不改写 prompt，只做传话。后端 Agent 会自行处理 prompt 工程、模型选择、参数配置。
本手册的正确用法：
- ✅ 帮你/用户判断当前需求是否适合 Seedance 2.0（vs 需要改用 Kling O3）
- ✅ 帮你回答用户关于模型能力、参数范围、@符号、工作模式的问题
- ✅ 在用户主动索要模板时，展示提示词模板供用户挑选和二次创作
- ✅ 帮你诊断生成失败时的可能原因（如人物换脸 → 提示用户提供更清晰的参考图）
绝对不要：
- ❌ 拿本手册里的提示词模板偷偷嫁接到用户请求中再发给 libtv-skill（违反传话原则）
- ❌ 替用户扩写为「@character1, cinematic, 8K, 24fps...」之类的技术参数
- ❌ 擅自判断用户应该用哪个模板并直接执行
本手册是给人类创作者和模型选型决策用的，不是给 Agent 用来注入 prompt 的。
一、Seedance 2.0 定位
基于扩散模型的 AI 视频生成工具，主打「参考视频 + 文本提示词」的可控生成。
核心优势：
- 角色一致性：解决 AI 视频"换脸""换衣"的痛点，同一角色可贯穿多镜头
- 镜头语言可控：精准控制运镜、转场、节奏，媲美专业剪辑
- 成本门槛低：相比传统影视制作，时间和资金成本大幅降低
- 商业场景成熟：电商广告、短剧、MV、品牌营销等领域已有大量成功案例
适合的场景：
- 电商 TVC、产品广告、探店 / 测评短视频
- 短剧、漫剧、微电影、品牌故事片
- 音乐 MV（支持音乐卡点）
- 旅游探险、生活方式类内容
- 多镜头叙事、同角色贯穿全片
不擅长的场景：
- 超长篇叙事（剧情复杂度 > 3 分钟的故事）
- 极端抽象 / 超现实实验艺术（Sora 更合适）
- 纯速度优先的 UGC 短视频（Veo 更便宜更快）
二、两种工作模式
模式 1：首尾帧模式（新手必选）
- 适用场景：快速生成简单转场、测试创意、验证提示词效果
- 操作流程：
- 上传首帧（起始画面）+ 尾帧（目标画面）
- 输入提示词描述中间过渡过程
- 调整时长（推荐 2-5 秒）和运动强度
- 优势：上手快，适合验证创意，无需复杂参考视频
模式 2：全能参考模式（进阶必选）
- 适用场景：多镜头叙事、角色一致性控制、复杂运镜
- 操作流程：
- 上传 1-3 段参考视频（建议 10-30 秒，清晰稳定）
- 为每段视频绑定提示词，定义镜头内容和风格
- 开启「角色一致性」开关，锁定核心人物
- 优势：高度可控，支持多场景无缝衔接，是商业创作的核心模式
三、@ 符号 · 核心控制符
@ 是 Seedance 2.0 的核心控制符，用于精确绑定参考视频中的元素（角色、物体、场景），让模型理解「这是什么」「要做什么」，避免生成混乱。
常见用法
| 用法 | 示例 | 作用 |
|---|---|---|
| 锁定角色 | @character1 |
绑定参考视频中的主角，确保多镜头一致性 |
| 指定物体 | @product |
绑定商品，保证电商广告中产品细节不变 |
| 定义场景 | @cityscape |
绑定城市背景，维持场景连贯性 |
| 控制动作 | @character1 walks forward |
让角色执行特定动作 |
实战案例
电商广告：
@product is a sleek wireless earbud, rotating slowly on a marble countertop,
soft studio lighting, 8K, product photography
短剧转场：
@character1 opens a door, revealing a neon-lit cyberpunk alley,
rain falling, cinematic dolly shot
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 200 lines · 219 tokens per session scan A c1873dc5f159
seedance-2-guide is a skill published in the GitHub repository ShuaiMXu/mv-skills-bundle (14 stars, last pushed 5mo ago), licensed MIT. It adds 219 tokens to every session and 2,787 once invoked, about $0.0009 per session on Opus 5.5. 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
sketch-correction-worker
Use when doing single-beat sketch quality control and preparing correction labels from a SuperTale project path and episode number. This skill turns one episode's selected sketches plus local script beat data into selectresult.jsonl, selectsummary.json, tasks.jsonl, and labels.jsonl for edit execution. Prefer using…
freezone
Use when the active chat surface is 虾画/Freezone/canvas, or when the user asks about canvas nodes, visual boards, selections, graph edits, canvas actions, layout, or Freezone short-video workflow work.
dramaclaw-workflows
Create, revise, confirm, run, or resume multi-node DramaClaw Freezone canvas workflows. Use for requests involving a workflow, several connected nodes, grouped production stages, storyboards, or text/image/video/audio pipelines; do not use for one standalone canvas operation.
workflows
Use in Freezone/虾画 chat when the user selects a Skill or asks to create, plan, analyze, or expand a dynamic canvas workflow for short drama, ads, ecommerce, product video, MV, text, image, video, or audio production.
dramaclaw
Use for explicit DramaClaw/虾导 production work: ingesting a screenplay; checking or resuming a bound pipeline; generating or displaying portraits, identity images, sketches, first frames, audio, beat videos or final episodes; and reading or updating project artifacts. Also use for identity questions. Generic…
sketch-storyboard-director
Use when doing a separate post-QC storyboard-directing pass on SuperTale sketches. This skill focuses on shot scale, camera angle, staging, composition, and beat-to-beat visual rhythm after basic sketch correctness has already passed QC.