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 anymouschina/TapCanvas --skill seedance-2-video-gengit clone --depth 1 https://github.com/anymouschina/TapCanvasWrote 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/anymouschina/tapcanvas/seedance-2-video-gen)<a href="https://agentmods.dev/skills/anymouschina/tapcanvas/seedance-2-video-gen"><img src="https://agentmods.dev/badge/skills/anymouschina/tapcanvas/seedance-2-video-gen/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/anymouschina/tapcanvas/seedance-2-video-gen"><img src="https://agentmods.dev/badge/skills/anymouschina/tapcanvas/seedance-2-video-gen.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 | $0.00101 | $0.03572 |
| Opus 5 | $0.00051 | $0.01786 |
| Sonnet 5 | $0.00020 | $0.00714 |
| Haiku 4.5 | $0.00010 | $0.00357 |
Grade A, and why
seedance-2-video-gen scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
> 需要真正出视频时，**用项目自有的生视频工具/节点**，把下面的方法论填进去；**不要**注册 EvoLink、不设任何 `*_API_KEY`、不 curl 外部端点。 How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Seedance 2.0 生视频方法论（本地版）
定位（重要）：本 skill 只给方法论，不执行、不调用外部 key。 本项目的视频生成统一走自己的链路：画布
video节点 /tapcanvas_video_generate_to_canvas工具 → new-api 的 doubao-seedance 官渠（如doubao-seedance-2-0-260128/-fast）。官渠已直接支持真人，项目不再有任何-face模型，禁止输出doubao-seedance-2.0-face等 -face 变体。 需要真正出视频时，用项目自有的生视频工具/节点，把下面的方法论填进去；不要注册 EvoLink、不设任何*_API_KEY、不 curl 外部端点。 边界：seedance-20 skill 教的是外部平台表面（EvoLink/OpenRouter/API key/外部定价），仅供咨询外部用法；本项目出片一律走自有链路，不采信其 API/key 指引。 TapCanvas 正式提示词边界：本 skill 的 Timeline、动作、运镜与模型知识只可作为领域方法输入，不能自行成为最终 prompt 标准。任何写入 TapCanvas 视频节点、提示词包或真实供应商请求的提示词，都由tapcanvas-video-workflow派video-prompt-writer，并在同一上下文按tapcanvas-video-reviewer修订；动态 generationContract 优先于本文件中的历史时长、分辨率、引用数量与示例@图N。
三种模式（方法论）
| 模式 | 用法 | 输入 |
|---|---|---|
| 文生视频 | 描述场景直接出视频 | prompt（可选 web 搜索增强时效性内容） |
| 图生视频 | 从图动起来 | 1 张图=首帧动画（首尾帧插值/续写/尾帧续接已于 2026-06-26/07-06 在本项目停用：镜间并发独立+exitState 文字承接；此段仅存档） |
| 参考生视频 | 多模态混合/编辑 | 图(0–9) + 视频(0–3) + 音频(0–3) + prompt，用自然语言按编号引用输入（续写用法已停用，同上注） |
当前口径：
storyboardImageNodeId是可选图片引用。单状态可用普通 image；确需表达连续变化时可用一张承载 2～3 个有序状态的故事板 image；无关键帧也合法。只有bridge_frames把它作为真起幅并要求lastFrameImageNodeId。仍禁运行时从已出视频抽帧续写，整章母板、通用设计板、四格以上分镜板和站位图禁止进入视频。
参数方法论
| 参数 | 说明 | 默认 |
|---|---|---|
| prompt | 运动意图描述。写运动方向与物理后果，把动作沿时间轴铺开（Timeline 分拍见下），禁止一句笼统带过。 | 必填 |
| duration | 4–15 秒。单段越短累积畸变越少（口径澄清：单拍 ≤3s（台词拍除外），单条 clip ≤15s）。 | 5s |
| resolution | 480p / 720p。 | 720p |
| audio | 可自动生成同步的人声/音效/BGM。 | 开 |
| aspect | 16:9 / 9:16 / 1:1 / 4:3 / 3:4 / 21:9 / adaptive。 | 16:9 |
| referenceImages | 图生视频 1–2 张；参考模式 0–9 张。 | 条件 |
| referenceVideos | 参考模式 0–3 个(.mp4/.mov，单段 2–15s，合计 ≤15s)。用于运镜/动作参考。（作为被编辑/续写源视频的用法已于 2026-06-26/07-06 在本项目停用：镜间并发独立+exitState 文字承接；此句仅存档） | 条件 |
| referenceAudio | 参考模式 0–3 个(.wav/.mp3，单段 2–15s，合计 ≤15s)。用于 BGM/音效/配音参考。 | 条件 |
一致性 / 喂图方法论（配合故事板）
- 按需关键帧 + 精选资产：每镜可不使用关键帧、使用普通单状态 image，或使用一张 2～3 状态故事板 image；再按剧情需要精选核心人物、群像、场景、武器/道具/VFX。整章母板、通用设计板、四格以上网格图和站位图绝不喂视频模型。
- 产品一致性：
keep the product appearance completely unchanged, camera movement only, no rotation；只动相机不动主体；单片段 ≤3s。 - 角色一致性：身份板派生单图（大头照+全身照）当锚点，每镜带固定外观描述；禁三视图整图直接喂视频（ID 漂移/双胞胎风险，与 sd2-pe 口径一致）。
What ships with it
2 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.
- 8d ago First seen · 93 lines · 101 tokens per session scan A 7ae390deb942
seedance-2-video-gen is a skill published in the GitHub repository anymouschina/TapCanvas (603 stars, last pushed 2d ago), licensed MIT. It adds 101 tokens to every session and 3,572 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
dramake
A production workflow for turning an idea, story, script, storyboard, or existing footage into a short AI drama or film. It covers planning, generation, voice, editing, and quality checks for formats such as vertical and horizontal video.
last30Days
Resolve "last30Days" to a concrete ISO date range relative to your run time — a rolling 30-day window ending today. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a "last 30 days" / trailing-month task…
thisWeek
Resolve "thisWeek" to a concrete ISO date range relative to your run time — this week so far (Monday → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a week-to-date task (this week's activity…
vchart-development-assistant
A coding assistant for VChart, a JavaScript chart library used to build visualizations such as bar, line, and pie charts.
short-drama-storyboard
A workflow for turning a Chinese short-drama script and its visual facts into a shot-by-shot storyboard with frozen starting-frame prompts.
md-fetch-summarize
Fetch a URL and return a concise markdown summary of its content. Read-only: no files are written; the summary is returned as output only. Use when asked to "fetch and summarize", "summarize this URL", "what does this page say", or "get the content of ". Proactively suggest when the user pastes a URL and asks what it…