seedance-examples-ja

seedance-examples-ja is a skill for Claude Code from 1370998960-del/https-github.com-Emily2040-seedance-2.0. It costs 43 tokens per session (1,027 once invoked), scanned A, original, MIT.

A collection of Japanese examples and patterns for writing Seedance 2.0 video-generation prompts. Seedance is a tool that creates video from written instructions and reference media.

In plain words
What is it for?
Use it to write or rewrite Japanese Seedance prompts, including safer versions and prompts that use image, video, or audio references.
Why use it?
It helps Japanese-speaking creators describe emotion as concrete camera, lighting, movement, sound, and editing directions.

Skill for Claude Code

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

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.

agentmods
npx agentmods add skills/1370998960-del/https-github.com-emily2040-seedance-2.0/seedance-examples-ja
Any agent
npx skills add 1370998960-del/https-github.com-Emily2040-seedance-2.0 --skill seedance-examples-ja
Clone the repo
git clone --depth 1 https://github.com/1370998960-del/https-github.com-Emily2040-seedance-2.0

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-ja

README.md
[![agentmods](https://agentmods.dev/badge/skills/1370998960-del/https-github.com-emily2040-seedance-2.0/seedance-examples-ja.svg)](https://agentmods.dev/skills/1370998960-del/https-github.com-emily2040-seedance-2.0/seedance-examples-ja)
Your own site
<a href="https://agentmods.dev/skills/1370998960-del/https-github.com-emily2040-seedance-2.0/seedance-examples-ja"><img src="https://agentmods.dev/badge/skills/1370998960-del/https-github.com-emily2040-seedance-2.0/seedance-examples-ja.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,027 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00043 $0.01027
Opus 5 $0.00022 $0.00513
Sonnet 5 $0.00009 $0.00205
Haiku 4.5 $0.00004 $0.00103

Measured 6d ago against content hash 023792e9969a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

seedance-examples-ja 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 6d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/seedance-examples-ja/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

seedance-examples-ja

Use Japanese examples as native prompt patterns, not translated English templates. Preserve reference tags exactly: [Image1], [Image2], [Video1], and [Audio1] remain unchanged inside Japanese sentences.

Intent

Japanese examples should feel like production notes a Japanese creator could actually use: polite where helpful, compact where the model needs clarity, and concrete enough that every emotion becomes framing, light, motion, sound, or post-production handling.

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]を商品参照として使い、ロゴ、ラベル、形状、色を正確に維持する。変化は小さな水滴が表面を下へ流れる動きと、左から横切る柔らかい暖色光だけ。Camera: locked product close-up, slow push-in. Sound: quiet room tone, one small glass tick at the end.

Portrait micro-performance: [Image1]の人物の顔、髪型、衣装、背景構図を保持。動きは小さく、一度まばたきし、視線を少し下げ、最後に控えめに微笑む。Camera: locked medium close-up, no reframing. Lighting: soft window light from frame right. Sound: quiet room tone.

Sequence clip 01: オリジナル人物Aが夜明けの駅ホームに入ってくる。目的は「誰かを待つ」と分かる最初の手がかりだけを見せる。Aは濡れた床を二歩歩き、折りたたまれた切符を見つけて拾わずに止まる。Camera: stable lateral tracking, medium-wide. このクリップでは列車到着や再会は見せない。

Continuation: 前の採用済みクリップの終点から続ける。Aは切符の二歩手前で止まっている状態から開始し、ゆっくりしゃがんで切符を拾い、遠くのアナウンスに反応して顔を上げる。前の入場動作を繰り返さない。Camera: locked medium shot, slight push-in.

Dialogue: Character A sits at a cafe table in a locked medium close-up and softly says, "もう一度だけ。" セリフ中は頭を大きく動かさず、小さな口の動きだけ。Lighting: warm interior practical, cool rain reflection on wall. Sound: clear short dialogue, no music under the line.

Textless localization: 9:16の日本向けSNSカット。商品は中央、端に重要な動きなし。画面内に生成文字、字幕、広告コピーを入れない。Post note: 日本語字幕、法務文言、CTAは編集で追加する。

Read the full file on GitHub · 59 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. 6d ago First seen · 59 lines · 43 tokens per session scan A 023792e9969a

Subscribe to this mod's changes

seedance-examples-ja is a skill published in the GitHub repository 1370998960-del/https-github.com-Emily2040-seedance-2.0 (235 stars, last pushed 2mo ago), licensed MIT. It adds 43 tokens to every session and 1,027 once invoked, about $0.0002 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.

Related

Other skills, from other repositories