seedance-examples-zh

seedance-examples-zh is a skill for Claude Code from anymouschina/TapCanvas. It costs 44 tokens per session (1,311 once invoked), scanned A, original, MIT.

A collection of Chinese examples and prompt patterns for Seedance video generation. It shows how to express production instructions in Chinese while distinguishing safe, reference-dependent, and rewrite-needed examples.

In plain words
What is it for?
Use it to study or create Chinese prompts for image-to-video work, reference assets, motion, lighting, and other video directions.
Why use it?
It helps Chinese-speaking users learn from concrete patterns instead of translating generic English templates. It also shows when a prompt involves protected material or a specific input format.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: built for openclaw.

Good fit Use it to study or create Chinese prompts for image-to-video work, reference assets, motion, lighting, and other video directions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anymouschina/tapcanvas/seedance-examples-zh
Install

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.

Any agent
npx skills add anymouschina/TapCanvas --skill seedance-examples-zh
Clone the repo
git clone --depth 1 https://github.com/anymouschina/TapCanvas

Made for: Claude Code.

Wrote 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.

agentmods badge for seedance-examples-zh

README.md
[![agentmods](https://agentmods.dev/badge/skills/anymouschina/tapcanvas/seedance-examples-zh/github.svg)](https://agentmods.dev/skills/anymouschina/tapcanvas/seedance-examples-zh)
Your own site
<a href="https://agentmods.dev/skills/anymouschina/tapcanvas/seedance-examples-zh"><img src="https://agentmods.dev/badge/skills/anymouschina/tapcanvas/seedance-examples-zh/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.

agentmods 80×15 button for seedance-examples-zh

Your own site · 80×15
<a href="https://agentmods.dev/skills/anymouschina/tapcanvas/seedance-examples-zh"><img src="https://agentmods.dev/badge/skills/anymouschina/tapcanvas/seedance-examples-zh.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,311 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.01311
Opus 5.5 $0.00018 $0.00524
Sonnet 5.5 $0.00009 $0.00262
Haiku 4.5 $0.00004 $0.00131

Measured 1mo ago against content hash 721298ddc3b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

seedance-examples-zh 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.

apps/agents-cli/skills/seedance-20/skills/seedance-examples-zh/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

seedance-examples-zh

Use examples as patterns, not as content to copy blindly. Chinese prompts should stay compact, concrete, and production-oriented. Literal @Image1, @Video1, @Audio1, @图片1, @视频1, and @音频1 strings below are Seedance 2.0 surface examples: preserve them only when the user or active surface supplied those exact tokens. For Seedance 2.5 without token mapping, substitute neutral asset-role names and bind execution through the structured reference fields.

Intent

Some users learn by rule, but the ones who come here learn by seeing. The purpose of these examples is recognition - a working prompt close enough to their idea that they can feel the gap and close it themselves. An example that teaches is worth ten instructions.

Example Labels

Label Meaning
safe Original concept, no protected identity.
needs-owned-reference Requires user-owned, licensed, public-domain, or authorized asset.
surface-specific Depends on the active web, API, or workflow surface.
rewrite-required Mentions protected identity, brand, celebrity, exact scene, song, or voice.

Safe Example Patterns

Product I2V: @Image1为产品参考,严格保持logo、标签、瓶身形状和颜色不变。镜头缓慢推进到标签特写;左侧暖光扫过玻璃,水珠沿瓶身下滑,背景保持暗色静止。声音:轻微环境声,结尾一声清脆玻璃音。

Character drama: 原创角色A站在狭窄走廊,缓慢放下信封,目光停在紧闭的门上。镜头为稳定中近景并轻微推进。暖色顶灯微微闪烁,墙面有冷色雨光反射。声音:远处雨声,无配乐。

Action: 原创快递员在雨夜屋顶奔跑,跃过一道狭窄缝隙,落地后单膝撑住并冲向即将关闭的铁门。低机位手持跟拍,冷色屋顶灯和湿滑地面反光。声音:急促呼吸、雨声、铁门提示音。

Safe animation: 原创二维动画沙漠信使,夸张围巾,驾驶小型风力木车穿过浅色沙丘。手绘背景质感,圆润角色造型,柔和粉彩色调,车轮带出细小沙尘。镜头侧向稳定跟拍。

First/last frame: @图片1为首帧,@图片2为尾帧。保持同一原创角色、服装和房间布局,角色从椅子上缓慢站起,走到窗边并停在尾帧姿势。动作连续自然,不跳切,不改变脸部、衣服或房间结构。镜头固定中景,仅轻微推镜。声音:安静室内环境声。

Sequence Clip 01: 原创角色A在清晨机场出口停下,手里握着一张折起的纸条。本段只建立“她在等待某人”的线索,不出现重逢或离开。镜头横向稳定跟拍到中景,A看向到达屏并停住。声音:机场环境声、远处广播、无配乐。

Continuation: 从上一段已接受视频的真实结尾继续:A站在到达屏前,纸条仍在右手。本段只让A打开纸条,看到名字后向画面左侧抬头,不重复走出机场的动作,不提前出现对方。镜头固定中近景,轻微推镜。

Camera-reference R2V: @图片1锁定原创角色造型和服装,@视频1仅参考运镜节奏和侧向跟拍方式,不复制人物、场景或品牌。角色在雨夜街道从画面左侧跑入,停在路灯下回头。镜头横向稳定跟拍,最后固定中景。冷色雨光,地面反射霓虹。声音:雨声、脚步声,无配乐。

Read the full file on GitHub · 65 lines

Changes

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.

  1. 1mo ago First seen · 65 lines · 44 tokens per session scan A 721298ddc3b7

Subscribe to this mod's changes

seedance-examples-zh is a skill published in the GitHub repository anymouschina/TapCanvas (686 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 1,311 once invoked, about $0.0002 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 2026-09-21.

Related

Other skills, from other repositories