Back to Details

action-continuity-choreography

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Action continuity choreography

Action continuity choreography

Turn the method into an executable, Case-grounded workflow. The Skill is incomplete unless the final artifact can be traced to one named anchor Case.
将该方法转化为可执行的、基于案例的工作流。若最终产出物无法追溯到一个指定的锚定案例，则本Skill未完成。

Inputs

输入

Ask only for missing inputs:
  • Target duration, aspect ratio, model, and delivery platform.
  • Opening frame, ending frame, reference image, source video, or depth/motion guide when available.
  • Character, camera, action, continuity, sound, and special-operation requirements.
  • Preferred anchor Case from 
    references/cases.md
    , or permission to select one.
仅询问缺失的输入项：
  • 目标时长、宽高比、模型及发布平台。
  • 可用的起始帧、结束帧、参考图像、源视频或深度/动效引导。
  • 角色、镜头、动作、连续性、音效及特殊操作要求。
  • 优先从
    references/cases.md
    中选择锚定案例，或授权我方选择一个。

Required evidence gate

必备证据门槛

  • Read 
    references/cases.md
    before drafting on every invocation.
  • Select exactly one anchor Case. Name it in the response; do not average several unrelated visual styles.
  • Inspect the anchor's finished media with an available image, video, or browser tool. If the media cannot be inspected, say so and do not claim visual fidelity.
  • Write a reference contract before the artifact:
    • Preserve: at least three structural traits supported by the Case evidence.
    • Replace: subject, copy, brand, or context supplied by the user.
    • Avoid: unrelated dominant motifs and superficial copying of creator identity.
  • 每次调用起草前都需阅读
    references/cases.md
    。
  • 仅选择一个锚定案例。在回复中明确其名称；不得混合多种不相关的视觉风格。
  • 使用可用的图像、视频或浏览器工具检查锚定案例的成品媒体。若无法检查该媒体，需明确说明，且不得声称视觉还原度。
  • 在生成产出物前撰写参考约定：
    • 保留项： 至少三项由案例证据支撑的结构性特征。
    • 替换项： 用户提供的主体、文案、品牌或背景。
    • 规避项： 不相关的主导主题以及对创作者身份的表面复制。

Workflow

工作流

  1. Restate the requested deliverable, audience, and success criteria.
  2. Read 
    references/cases.md
    and select one anchor Case.
  3. Inspect its finished media, summary, and prompt excerpt.
  4. Produce the Preserve / Replace / Avoid reference contract.
  5. Fix character and movement direction.
  6. Split setup, conflict, and resolution.
  7. Constrain camera, speed, and continuity shot by shot.
  8. Produce the requested artifact using the output contract below.
  9. Compare it with the anchor Case, then revise material failures once.
  1. 重述需求交付物、受众及成功标准。
  2. 阅读
    references/cases.md
    并选择一个锚定案例。
  3. 检查其成品媒体、摘要及提示词片段。
  4. 制定“保留/替换/规避”参考约定。
  5. 确定角色及运动方向。
  6. 划分铺垫、冲突及解决环节。
  7. 逐镜头约束运镜、速度及连续性。
  8. 使用下方的输出约定生成所需产出物。
  9. 将其与锚定案例对比，对实质性问题进行一次修订。

Output contract

输出约定

  • A reference contract naming one anchor Case, with Preserve, Replace, and Avoid decisions.
  • A shot-by-shot motion brief.
  • A complete video prompt with timing, camera, action, continuity, and audio constraints.
  • A reference-assets and special-steps checklist.
  • A short verification checklist for motion and continuity.
  • 明确单个锚定案例的参考约定，包含保留、替换及规避决策。
  • 逐镜头动效说明。
  • 完整的视频提示词，包含时序、镜头、动作、连续性及音频约束。
  • 参考资产及特殊步骤检查清单。
  • 简短的动效与连续性验证检查清单。

Verification

验证

  • Every shot has a subject, action, camera instruction, and duration or sequence position.
  • Reference media and special preprocessing steps are named instead of implied.
  • Continuity risks such as identity drift, limb errors, direction changes, and rhythm breaks are testable.
  • The response names one anchor Case and confirms that its evidence file was read.
  • At least three visible or structural traits in the artifact map back to the Preserve list.
  • No unrelated theme becomes dominant unless the user explicitly requested it.
  • If finished media was inaccessible, the response labels the result as prompt-grounded rather than visually verified.
  • Distinguish observed evidence from your own recommendation.
  • Link or name the relevant GoodCase evidence used for the artifact.
  • 每个镜头都包含主体、动作、镜头指令以及时长或序列位置。
  • 参考媒体及特殊预处理步骤需明确列出，而非隐含。
  • 身份漂移、肢体错误、方向变化及节奏断裂等连续性风险需可验证。
  • 回复中需明确一个锚定案例，并确认已阅读其证据文件。
  • 产出物中至少有三项可见或结构性特征对应保留项列表。
  • 除非用户明确要求，否则不得让不相关的主题占据主导。
  • 若无法获取成品媒体，回复需将结果标记为“基于提示词”而非“经过视觉验证”。
  • 需区分观察到的证据与自身的建议。
  • 链接或列明产出物所使用的相关GoodCase证据。

Safety and attribution

安全与归属

  • Do not invent an original prompt, model, result, creator, metric, or source.
  • Do not imply this Skill is authored, endorsed, or officially distributed by a referenced creator.
  • Preserve creator attribution when reproducing or discussing a source Case.
  • Transfer structure and decision logic; do not impersonate a creator or present a close copy as original work.
  • Do not publish, purchase, upload private assets, or make external account changes without explicit user approval.
  • 不得虚构原创提示词、模型、结果、创作者、指标或来源。
  • 不得暗示本Skill由所引用的创作者创作、认可或官方发布。
  • 在转载或讨论源案例时，需保留创作者署名。
  • 仅借鉴结构与决策逻辑；不得冒充创作者，也不得将高度相似的复制内容作为原创作品呈现。
  • 未经用户明确批准，不得发布、购买、上传私有资产，或进行外部账户变更。