This skill should be used when the user asks for Korean Seedance 2.0 prompt wording, Korean cinematic vocabulary, or translation of camera, lighting, action, VF
复制下面这句话,粘贴给 Claude Code、Codex、Cursor 等 AI 编程工具,它会读取安装说明并在你确认后完成安装。
请阅读 https://ai.atlankj.com/install/asset/gh-seedance-vocab-ko-be2f2986a6dc ,按照其中的说明把「seedance-vocab-ko」安装到你(当前 AI 工具)中。执行前先告诉我将运行的命令和写入的位置,等我确认。
查看 AI 将读取的安装说明正在读取 GitHub 原文…
内容来自 GitHub 原始文件,由原作者维护。在 GitHub 查看
Before producing prompt text, a prompt-ready block, a rewrite, an example, or a compiled clip, load the Director's Read, classify the brief, and complete its canonical narrative or non-narrative record. Translate that record into visible or audible carriers and keep its internal labels out of final generation prose.
Use Korean cinematic vocabulary when the user asks for Korean prompt wording, bilingual delivery, compact translation, or production vocabulary for camera, lighting, action, VFX, audio, and constraints. Preserve actual reference tags exactly; their spelling is independent of the prompt language.
Before adapting a reference example below, load Using Reference Examples. Bind its placeholders to real assets by the requested role, then preserve the actual token, including its script, case, spacing and punctuation. A written example token does not attach a file.
Korean prompt direction should preserve useful mood or style terms and clarify ambiguous intent through observable light, framing, blocking, or timing. Keep the relationship and speech level explicit whenever dialogue is added. The shipped independent review artifact is empty, so treat these choices as working production wording pending locale-specialist review.
Translate the production intention rather than every English word. Keep the Korean prompt compact and concrete: subject, action, camera, light, sound, and preservation constraint.
| Function | Korean wording |
|---|---|
| Camera | 느린 돌리 인, 측면 트래킹 샷, 고정된 미디엄 샷, 로우 앵글, 클로즈업 |
| Lighting | 역광, 부드러운 창문 빛, 따뜻한 프랙티컬 조명, 차가운 달빛, 림 라이트 |
| Motion | 천천히 돌아선다, 프레임을 빠르게 가로지른다, 물방울이 아래로 흐른다, 연기가 얇게 퍼진다 |
| Audio | 조용한 환경음, 짧은 대사, 부드러운 금속음, 음악 없음 |
| Constraints | 로고, 라벨, 형태를 정확히 유지한다 |
@Image1은 참조 이미지이며 얼굴/제품 형태/로고를 정확히 유지한다. 변화는 [동작/조명/카메라]만 적용한다. 카메라: [한 가지 움직임]. 사운드: [음향 지시].
Preserve user-supplied dialogue. When drafting or adapting speech, load Speech Level (말투) in the vocabulary guide and keep the relationship and intended tone explicit. Offer register choices only where they affect the brief. Measure the actual spoken line; do not use a fixed multiplier or change politeness to fit an invented sync budget. Record any unresolved locale-review need.
When an adjective leaves the intended shot unclear, load Slop Traps in Korean vocabulary. Preserve a useful style or aesthetic term and add only the scene-specific action, framing, light, or sound needed to clarify it. The table offers authored options, not a default look or a proven model-performance rule. Keep the user's chosen energy, dialogue, reference tags, and settings. Offer distinct choices only when the ambiguity changes the scene; if the user delegated the choice, decide within that scope.
Return Korean prompt wording, optional English gloss when useful, and unchanged reference tags.