cartoon-ad

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Cartoon Ad

Purpose

目标

Create or audit animated ads that make the advertising argument visible. Use a coherent visual system to connect specific pressure, offer interaction, mechanism, proof, and a changed human state.

Treat

cartoon

as a storytelling system, not a named studio look or a requirement to be cute, childish, comedic, or metaphorical.

创建或审核能够将广告逻辑可视化的动画广告。运用连贯的视觉系统，将特定用户痛点、产品交互、运作机制、验证依据与用户状态变化关联起来。

将

cartoon

视为一种叙事体系，而非特定工作室风格，也无需刻意走可爱、幼稚、喜剧或隐喻路线。

Choose The Mode

选择模式

Create Mode

创建模式

Use when the user supplies a product, software, service, community, content offer, brand brief, or rough concept and wants an animated ad direction or shot script.

Produce a

Cartoon Grammar Plan

, shot script, production locks and checks, one approval checkpoint, and direct production handoff after approval.

当用户提供产品、软件、服务、社区、内容产品、品牌brief或初步概念，需要动画广告方向或分镜脚本时使用此模式。

输出

Cartoon Grammar Plan

、分镜脚本、制作锁定与检查项、一个审批节点，并在获批后直接移交制作环节。

Review Mode

审核模式

Use when the user supplies an existing animated ad and asks whether it fits this grammar or how it should improve.

Use

$video-analysis

first to obtain observable shot and audio evidence. Then return:

factual structure and offer first-appearance time
a
```
Strong / Partial / Weak / Missing
```
grammar audit with timecodes
narrative-engine and visual-argument classification
causal-closure gaps
likely
```
complete_ad / excerpt / incomplete
```
status
confirmed patterns, meaningful deviations, and precise skill or creative amendments

Do not enter production or rewrite the ad unless the user asks.

当用户提供现有动画广告，询问其是否符合此规范或如何优化时使用此模式。

首先调用

$video-analysis

获取可观测的镜头与音频证据，然后返回：

事实结构与产品首次出现的时间点
带有时间码的「达标/部分达标/未达标/缺失」规范审核结果
叙事引擎与视觉论证分类
因果逻辑缺口
广告的「完整/片段/未完成」状态判断
已确认的模式、有意义的偏差，以及精准的技能或创意修正建议

除非用户要求，否则不进入制作环节或重写广告。

Create Workflow

创建工作流程

1. Ground The Brief

1. 明确brief核心信息

Read the smallest useful source context first:

offer facts, audience, brand voice, claim boundaries, and available proof
provided product, persona, UI, audio, brand, or reference assets
prior ad analysis when explicitly relevant
duration, aspect ratio, model, resolution, and output preferences when supplied

Lock:

offer_type

physical_product | software | service | community | content

```
offer_capability
```
```
specific_pressure
```
```
desired_visible_state
```
```
audience
```
```
offer_interaction
```
```
proof_available
```
```
claim_boundaries
```
```
visual_medium
```
```
duration_and_format
```

Do not invent medical, physiological, comparative, ingredient, price, review-count, performance-duration, or guarantee claims.

优先读取最关键的源上下文：

产品信息、受众、品牌调性、声明边界、可用验证依据
提供的产品、用户画像、UI、音频、品牌或参考素材
明确相关的过往广告分析
若有提供，需关注时长、宽高比、模型、分辨率及输出偏好

锁定以下信息：

offer_type

physical_product | software | service | community | content

```
offer_capability
```
```
specific_pressure
```
```
desired_visible_state
```
```
audience
```
```
offer_interaction
```
```
proof_available
```
```
claim_boundaries
```
```
visual_medium
```
```
duration_and_format
```

不得编造医疗、生理、对比、成分、价格、评论数量、性能时长或质保相关声明。

2. Design The Cartoon Grammar

2. 设计卡通广告规范

Read

references/narrative-grammar.md

and

references/metaphor-and-proof.md

Choose one primary narrative engine and one visual-argument mode. Produce a

Cartoon Grammar Plan

with exactly these fields:

```
core_human_state
```
```
specific_pressure
```
```
narrative_engine
```
```
offer_type
```
```
pressure_carrier
```
```
visual_argument_mode
```
```
visual_argument_system
```
```
character_system
```
```
camera_and_edit_grammar
```
```
offer_entry
```
```
offer_interaction
```
```
mechanism_trace
```
```
proof_plan
```
```
continuity_locks
```
```
final_state_and_close
```

State

Claim Boundaries

immediately after the plan. Do not force a metaphor, fixed shot order, character type, material style, joke, product category, or ending formula.

阅读

references/narrative-grammar.md

和

references/metaphor-and-proof.md

。

选择一个核心叙事引擎和一种视觉论证模式，输出包含以下字段的

Cartoon Grammar Plan

：

```
core_human_state
```
```
specific_pressure
```
```
narrative_engine
```
```
offer_type
```
```
pressure_carrier
```
```
visual_argument_mode
```
```
visual_argument_system
```
```
character_system
```
```
camera_and_edit_grammar
```
```
offer_entry
```
```
offer_interaction
```
```
mechanism_trace
```
```
proof_plan
```
```
continuity_locks
```
```
final_state_and_close
```

在方案后立即注明「声明边界」。不得强制使用隐喻、固定镜头顺序、特定角色类型、材质风格、笑话、产品品类或结尾公式。

3. Write The Shot Script

3. 编写分镜脚本

Read

references/shot-script-rubric.md

and

references/continuity-rules.md

Return a shot table with exactly these columns:

time | visual | framing/composition | camera motion | action | offer/prop relationship | lighting/color | sound | speech/text | purpose

After the table, provide:

```
Continuity Locks
```
```
Proof Status
```
```
Claim Boundaries
```
```
Causal Closure Gate
```

Keep each shot concrete enough for still generation, video prompting, or animation production. Give each shot one dominant action and one causal idea.

阅读

references/shot-script-rubric.md

和

references/continuity-rules.md

。

返回包含以下列的分镜表：

时间 | 视觉内容 | 取景/构图 | 镜头运动 | 动作 | 产品/道具关联 | 灯光/色彩 | 音效 | 台词/文字 | 目标

表格后需提供：

```
Continuity Locks
```
```
Proof Status
```
```
Claim Boundaries
```
```
Causal Closure Gate
```

每个镜头的内容需足够具体，以支持静态图生成、视频提示或动画制作。每个镜头仅保留一个核心动作和一个因果逻辑点。

4. Ask For Approval

4. 请求审批

Ask one concise approval question in the user's language. English default:

Does this cartoon-ad direction feel right? If yes, I will hand it directly to production.

Stop before production until the user approves.

用用户使用的语言提出一个简洁的审批问题，英文默认表述：

Does this cartoon-ad direction feel right? If yes, I will hand it directly to production.

在用户批准前，停止推进制作环节。

5. Handoff On Approval

5. 获批后移交

Read

references/workflow-handoff.md

and immediately route the locked script.

Default to

$image-batch-runner

first when recurring characters, locations, offers, UI, or visual systems need continuity assets. Feed approved still assets into

$video-batch-runner

Go directly to

$video-batch-runner

when persona, offer, scene, UI, and effect references are already stable and validated.

Do not output a separate production brief and do not ask a second generation confirmation.

阅读

references/workflow-handoff.md

，立即移交锁定后的脚本。

当需要重复使用角色、场景、产品、UI或视觉系统以保证素材连贯性时，优先调用

$image-batch-runner

。将获批的静态素材导入

$video-batch-runner

。

当用户画像、产品、场景、UI及效果参考已稳定并验证通过时，直接调用

$video-batch-runner

。

无需输出单独的制作brief，也无需二次确认生成指令。

Quality Bar

质量标准

Open on specific pressure and use one coherent
```
visual_argument_system
```
.
Show plausible offer interaction, mechanism trace, and causal result behavior.
Treat aspirational peers as illustration, not proof; use approved proof layers.
End on an embodied human state and keep one main idea per shot.
Add exact packaging, legal, numeric, UI, and subtitle text in post.

以特定用户痛点开篇，使用一套连贯的
```
visual_argument_system
```
。
展示合理的产品交互、运作机制轨迹及因果行为结果。
将标杆同行仅作为示例，而非验证依据；使用已获批的验证层级。
以具象化的用户状态收尾，每个镜头仅保留一个核心观点。
在后期添加精准的包装、法律、数字、UI及字幕文本。

Non-Imitation Boundary

非模仿边界

Do not copy reference characters, creator identity, brand marks, exact scenes, package designs, signature jokes, or recognizable story devices.
Do not prompt for a named animation studio or living creator's style.
Translate references into generic production attributes: material, proportions, expression range, lighting, camera behavior, edit rhythm, visual argument, and proof logic.

不得复制参考角色、创作者身份、品牌标识、精确场景、包装设计、标志性笑话或可识别的叙事手法。
不得要求生成特定动画工作室或在世创作者的风格。
将参考素材转化为通用制作属性：材质、比例、表情范围、灯光、镜头行为、剪辑节奏、视觉论证及验证逻辑。