authority-ad
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseAuthority Ad
权威广告(Authority Ad)
Purpose
目的
Create or audit speech-led educational ads where authority comes from specific reasoning and visible proof. Treat presenter styling, credentials, studios, interviews, podcasts, and technical graphics as framing devices, not proof by themselves.
创建或审核以语言表达为主的教育类广告,这类广告的权威性源自具体的推理和可见的证据。将主持人风格、资质、演播室、采访、播客和技术图形视为框架手段,而非证据本身。
Choose The Mode
选择模式
Create Mode
创建模式
Use when the user supplies a product, service, software, community, offer, proof set, brand brief, or rough concept and wants an authority-led direction or shot script.
Produce an , shot script, authority and proof checks, one
approval checkpoint, and direct production handoff after approval.
Authority Grammar Plan当用户提供产品、服务、软件、社区、报价、证据集、品牌简报或初步概念,需要权威主导的方向或分镜头脚本时使用此模式。
产出一份、分镜头脚本、权威与证据核查表、一个审批节点,并在获批后直接移交至制作环节。
Authority Grammar PlanReview 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 first to obtain observable shot and audio evidence. Then return:
$video-analysis- factual structure, speaker role, authority basis, and product timing
- a timecoded audit and proof map
Strong / Partial / Weak / Missing - claim risks, completion status, meaningful deviations, and precise amendments
Do not rewrite or enter production unless the user asks.
当用户提供现有广告,并询问其是否符合此规范或如何改进时使用此模式。
首先使用获取可观测的镜头和音频证据,然后返回:
$video-analysis- 事实结构、演讲者角色、权威性依据和产品植入时机
- 带时间码的「强/部分符合/弱/缺失」审核与证据图谱
- 声明风险、完成状态、重大偏差和精准修改建议
除非用户要求,否则不要重写或进入制作环节。
Create Workflow
创建工作流程
1. Ground The Brief
1. 明确简报基础
Read the smallest useful source context first:
- offer facts, audience, brand voice, approved claims, and available proof
- provided speaker, persona, product, UI, audio, brand, or reference assets
- prior ad analysis when explicitly relevant
- duration, aspect ratio, model, resolution, and output preferences when supplied
Lock:
- :
offer_typephysical_product | software | service | community | content offer_capabilityspecific_pressureaudienceauthority_basisspeaker_roleproof_availableclaim_boundariesdesired_visible_stateauthority_formatduration_and_format
Do not invent credentials, customer histories, testimonials, study results, mechanisms, medical or financial outcomes, comparisons, prices, guarantees, or product capabilities.
首先阅读最有用的最小范围源上下文:
- 报价事实、受众、品牌调性、已获批声明和可用证据
- 提供的演讲者、角色、产品、UI、音频、品牌或参考资产
- 明确相关的过往广告分析
- 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_typephysical_product | software | service | community | content offer_capabilityspecific_pressureaudienceauthority_basisspeaker_roleproof_availableclaim_boundariesdesired_visible_stateauthority_formatduration_and_format
不得编造资质、客户历史、推荐语、研究结果、机制、医疗或财务成果、对比信息、价格、担保或产品功能。
2. Design The Authority Grammar
2. 设计权威规范
Read and .
references/authority-grammar.mdreferences/proof-and-claims.mdChoose one primary authority basis and one delivery format. Produce an with exactly these fields:
Authority Grammar Plancore_human_statespecific_pressureauthority_basisspeaker_roleauthority_formatopening_claim_or_questionpressure_carriercausal_argumentproof_stackcamera_and_edit_grammarproduct_entryproduct_gesturesound_worldtext_behaviorcontinuity_locksfinal_state_and_close
State and immediately after the plan. Do not force a lab coat, credential, interview, podcast, direct-to-camera presenter, fixed shot order, product reveal time, or CTA formula.
Authority IntegrityClaim Boundaries阅读和。
references/authority-grammar.mdreferences/proof-and-claims.md选择一个核心权威性依据和一种交付格式。产出一份,需包含以下字段:
Authority Grammar Plancore_human_statespecific_pressureauthority_basisspeaker_roleauthority_formatopening_claim_or_questionpressure_carriercausal_argumentproof_stackcamera_and_edit_grammarproduct_entryproduct_gesturesound_worldtext_behaviorcontinuity_locksfinal_state_and_close
在计划后立即说明和。不得强制要求使用白大褂、资质证明、采访、播客、直面镜头的主持人、固定镜头顺序、产品曝光时机或CTA公式。
Authority IntegrityClaim Boundaries3. Write The Shot Script
3. 撰写分镜头脚本
Read .
references/shot-script-rubric.mdReturn a shot table with exactly these columns:
time | visual | framing/composition | camera motion | action | offer/prop relationship | lighting/color | sound | speech/text | purposeAfter the table, provide:
Authority BasisProof StatusClaim BoundariesContinuity LocksCausal Closure Gate
Keep each shot concrete enough for still generation, video prompting, filming, or editing. Give each shot one dominant action and one argumentative job.
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 | 报价/道具关联 | 灯光/色彩 | 音效 | 台词/文字 | 目的表格后需提供:
Authority BasisProof StatusClaim BoundariesContinuity LocksCausal 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、拍摄或剪辑。每个镜头设定一个主导动作和一个论证目标。
4. Ask For Approval
4. 请求审批
Ask one concise approval question in the user's language. English default:
Does this authority-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批问题,英文默认表述:
Does this authority-ad direction feel right? If yes, I will hand it directly to production.在用户获批前,停止进入制作环节。
5. Handoff On Approval
5. 获批后移交
Read and immediately route the locked script.
references/workflow-handoff.mdDefault to first when recurring speakers, customers, locations, products, props, UI plates, diagrams, or first-frame candidates need continuity assets. Feed approved still assets into .
$image-batch-runner$video-batch-runnerGo directly to when identity, offer, scenes, UI, proof assets, audio, and continuity references are already stable and validated.
$video-batch-runnerDo not output a separate production brief and do not ask a second generation confirmation.
阅读,立即移交锁定的脚本。
references/workflow-handoff.md当需要为重复出现的演讲者、客户、场景、产品、道具、UI模板、图表或首帧候选者制作连续性资产时,默认优先使用。将获批的静态资产导入。
$image-batch-runner$video-batch-runner当身份、报价、场景、UI、证据资产、音频和连续性参考已稳定且验证通过时,直接使用。
$video-batch-runner无需输出单独的制作简报,也无需再次确认生成指令。
Quality Bar
质量标准
- Open on specific pressure and let the spoken argument control claim-matched cuts.
- Build authority through specificity, causal explanation, demonstration, or evidence.
- Establish before offer interaction.
symptom -> mechanism -> evidence/use-state - Return to a visible human state with one main claim and action per shot.
- Add exact subtitles, UI, charts, legal, price, review, and package text in post.
- 以具体的痛点开篇,让口头论证控制与声明匹配的镜头切换。
- 通过具体性、因果解释、演示或证据建立权威性。
- 在产品互动前,建立「症状→机制→证据/使用状态」的逻辑链。
- 回归可见的人物状态,每个镜头对应一个核心声明和动作。
- 在后期添加精准的字幕、UI、图表、法律声明、价格、评价和包装文本。
Non-Imitation Boundary
非模仿边界
- Do not copy creator identity, voice, credentials, character design, exact set, exact dialogue, brand marks, proprietary UI, signature scenes, or recognizable story devices.
- Do not prompt for a living creator's style or imply a real professional endorsement without approval.
- Translate references into generic production attributes: speaker role, authority basis, framing, lighting, camera behavior, edit rhythm, evidence structure, sound intent, and proof logic.
- 不得复制创作者身份、声音、资质、角色设计、精确场景、确切对话、品牌标识、专有UI、标志性场景或可识别的故事手法。
- 未经批准,不得模仿在世创作者的风格或暗示真实专业人士的代言。
- 将参考内容转化为通用制作属性:演讲者角色、权威性依据、取景、灯光、镜头行为、剪辑节奏、证据结构、音效意图和证据逻辑。