educational-ad

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Educational Ad

教育类广告

Purpose

目的

Create or audit short-form ads that teach one useful idea while building an evidence-backed case for an offer. Make the argument visible through a stable anchor, clause-matched evidence, readable product behavior, and a clear movement from pressure to understanding and agency.

Treat

educational

as an argument system, not a requirement for a lab coat, podium, lecture, talking head, medical topic, or serious tone.

创建或审核短视频广告，在传授实用理念的同时，为产品优惠构建有证据支撑的论证。通过稳定的锚点、与文案匹配的证据、清晰的产品表现，以及从压力到理解再到行动的明确转变，让论证可视化。

此处的“教育性”是指一套论证体系，而非要求穿着实验服、站在讲台、进行讲座、采用访谈镜头、涉及医疗话题或使用严肃语气。

Choose The Mode

选择模式

Create Mode

创建模式

Use when the user supplies an offer, brand brief, rough concept, approved facts, or prior analysis and wants an educational ad direction or shot script.

Produce an

Educational Grammar Plan

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

当用户提供产品优惠信息、品牌简报、初步概念、已核准事实或前期分析，需要教育类广告方向或分镜头脚本时使用此模式。

产出一份《教育语法方案》、证据台账、分镜头脚本、制作检查清单、一个审核节点，获批后直接移交制作。

Review Mode

审核模式

Use when the user supplies an existing 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 read

references/review-rubric.md

and return:

factual structure, offer timing, and education/evidence classification
a timecoded
```
Strong / Partial / Weak / Missing
```
audit and causal-closure gaps
completion status, meaningful deviations, and precise amendments

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

当用户提供现有广告，询问其是否符合此语法规范或如何改进时使用此模式。

先调用

$video-analysis

获取可观察的镜头和音频证据。然后阅读

references/review-rubric.md

，返回：

事实结构、优惠信息出现时机、教育/证据分类
带时间码的「优秀/部分符合/薄弱/缺失」审核结果，以及因果闭环缺口
完成状态、有意义的偏差，以及精准的修改建议

除非用户要求，否则不要重写广告或进入制作环节。

Create Workflow

创建工作流程

1. Ground The Brief

1. 锚定简报

Read the smallest useful source context first:

offer facts, audience, brand voice, claim boundaries, and approved proof
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
```
```
viewer_question
```
```
education_goal
```
```
desired_visible_state
```
```
audience
```
```
authority_basis
```
```
approved_facts_and_proof
```
```
claim_boundaries
```
```
visual_medium
```
```
duration_and_format
```

Do not invent credentials, mechanisms, research, medical or legal outcomes, comparative superiority, ingredients, prices, review counts, performance durations, guarantees, or other substantiation.

优先阅读最有用的最小范围源上下文：

产品优惠事实、受众、品牌调性、声明边界、已核准的证据
产品、用户画像、UI、音频、品牌或参考资产
明确相关的前期广告分析
若有提供，需注意时长、宽高比、模型、分辨率和输出偏好

锁定以下内容：

offer_type

physical_product | software | service | community | content

```
offer_capability
```
```
specific_pressure
```
```
viewer_question
```
```
education_goal
```
```
desired_visible_state
```
```
audience
```
```
authority_basis
```
```
approved_facts_and_proof
```
```
claim_boundaries
```
```
visual_medium
```
```
duration_and_format
```

不得编造资质、机制、研究成果、医疗或法律结果、相对优势、成分、价格、评论数量、性能持续时间、保证或其他佐证内容。

2. Design The Educational Grammar

2. 设计教育语法

Read

references/educational-grammar.md

Choose one primary education engine and one evidence system. Produce an

Educational Grammar Plan

with exactly these fields:

```
core_human_state
```
```
specific_pressure
```
```
viewer_question
```
```
education_engine
```
```
authority_anchor
```
```
pressure_carrier
```
```
mechanism_or_reason
```
```
evidence_system
```
```
camera_and_edit_grammar
```
```
speech_and_tone
```
```
text_behavior
```
```
offer_entry
```
```
offer_interaction
```
```
proof_plan
```
```
continuity_locks
```
```
final_state_and_close
```

State

Claim Boundaries

and an evidence ledger immediately after the plan. Mark each material statement as

approved

needs evidence

, or

prohibited

阅读

references/educational-grammar.md

。

选择一个核心教育引擎和一套证据体系。产出一份《教育语法方案》，需包含以下字段：

```
core_human_state
```
```
specific_pressure
```
```
viewer_question
```
```
education_engine
```
```
authority_anchor
```
```
pressure_carrier
```
```
mechanism_or_reason
```
```
evidence_system
```
```
camera_and_edit_grammar
```
```
speech_and_tone
```
```
text_behavior
```
```
offer_entry
```
```
offer_interaction
```
```
proof_plan
```
```
continuity_locks
```
```
final_state_and_close
```

方案后需立即列出「声明边界」和证据台账，将每个重要标注标记为

approved

、

needs evidence

或

prohibited

。

3. Write The Shot Script

3. 撰写分镜头脚本

Read

references/shot-script-rubric.md

Return a shot table with exactly these columns:

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

After the table, provide:

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

Give each shot one dominant action, one causal idea, and one evidence job. Keep critical captions, labels, legal copy, numeric claims, prices, reviews, guarantees, and package text for approved post-production treatment.

阅读

references/shot-script-rubric.md

。

返回一个分镜头表格，需包含以下列：

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 | 证据作用 | 目的

表格后需提供：

```
Continuity Locks
```
（连续性锁定）
```
Proof Status
```
（证据状态）
```
Claim Boundaries
```
（声明边界）
```
Causal Closure Gate
```
（因果闭环节点）

每个镜头需有一个核心动作、一个核心因果理念和一个证据作用。关键字幕、标签、法律文案、数值声明、价格、评论、保证和包装文字留待后期制作处理。

4. Ask For Approval

4. 请求审核

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

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

Stop before production until the user approves.

用用户的语言提出一个简洁的审核问题，英文默认表述为：

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

在用户核准前，停止进入制作环节。

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 an authority persona, recurring user, product, location, comparison system, proof plate, interface, or animated character needs continuity assets. Feed approved still assets into

$video-batch-runner

Go directly to

$video-batch-runner

when identity, product, scenes, proof assets, and audio references are stable and validated.

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

阅读

references/workflow-handoff.md

，立即移交锁定的脚本。

当需要保持权威角色、重复用户、产品、场景、对比体系、证据模板、界面或动画角色的一致性资产时，优先默认调用

$image-batch-runner

。将获批的静态资产导入

$video-batch-runner

。

当身份、产品、场景、证据资产和音频参考均稳定且验证通过时，直接调用

$video-batch-runner

。

无需输出单独的制作简报或再次确认生成需求。

Quality Bar

质量标准

Establish one viewer question and stable anchor within the first three seconds.
Match evidence to spoken clauses and explain one causal chain before offer entry.
Show observable offer interaction and approved proof in readable framing.
End on an embodied state with one narrative job per location and shot.
Add exact captions, claims, legal copy, numbers, UI, and package text in post.

前三秒内确立一个观众疑问和稳定锚点。
证据与台词文案匹配，在引入优惠信息前解释一个因果链。
在清晰的取景中展示可观察的产品交互和已核准的证据。
以具象化状态收尾，每个场景和镜头承担一个叙事任务。
在后期添加准确的字幕、声明、法律文案、数字、UI和包装文字。

Non-Imitation Boundary

非模仿边界

Do not copy reference creators, faces, voices, credentials, wardrobe, exact sets, characters, brand marks, packaging, dialogue, websites, proprietary interfaces, or recognizable scenes.
Treat benchmark videos as inspiration-only for rhythm, framing, evidence linkage, and argument structure unless the user explicitly supplies separate binding persona, product, or audio references.
Do not prompt for a named creator, studio, or advertisement style. Translate references into generic production attributes.

不得抄袭参考创作者的面容、声音、资质、服装、场景、角色、品牌标识、包装、台词、网站、专有界面或可识别场景。
除非用户明确提供具有约束力的角色、产品或音频参考，否则仅将基准视频作为节奏、取景、证据关联和论证结构的灵感来源。
不得要求指定创作者、工作室或广告风格。将参考内容转化为通用制作属性。