Back to Details

creative-health

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

/digital-marketing-pro:creative-health

/digital-marketing-pro:creative-health

Purpose

用途

Monitor creative health across all active advertising. Score each creative for fatigue risk, predict when fatigue will impact performance, generate refresh recommendations with specific change suggestions, and create A/B test plans for fatiguing creatives. Creative fatigue is one of the fastest ways to waste ad spend — a high-performing ad that ran too long silently bleeds money as CTR drops, CPM rises, and engagement fades. This command catches fatigue before it costs you, tells you exactly what to change, and gives you a structured test plan to validate the refresh. It covers the full creative lifecycle from launch through maturity to decline, so you always know which creatives are earning their spend and which need attention.
监控所有在投广告的创意健康状况。为每个创意评分以评估疲劳风险，预测疲劳何时会影响广告表现，生成带有具体修改建议的创意更新方案，并为出现疲劳的创意制定A/B测试计划。创意疲劳是浪费广告预算最快的方式之一——原本表现优异的广告投放时间过长后，会随着点击率（CTR）下降、千次展示成本（CPM）上升和用户参与度降低而悄无声息地消耗资金。该工具能在疲劳造成损失前及时发现问题，明确告知需要修改的内容，并提供结构化的测试计划来验证更新效果。它覆盖了创意从上线、成熟到衰退的完整生命周期，让你随时了解哪些创意物有所值，哪些需要重点关注。

Input Required

所需输入

The user must provide (or will be prompted for):
  • Active creatives with performance data: A list of currently running creatives, each with: creative ID or name, channel (paid social, display, search, email, video), current performance metrics (impressions served, frequency or average times shown per user, current CTR, current CPM or CPC, current engagement rate), baseline metrics from the creative's first 7-14 days (baseline CTR, baseline CPM, baseline engagement rate), days running since launch, audience size the creative is serving, and current daily or weekly spend. Can be provided as exported data or pulled from connected ad platform MCPs
  • Channel context: Which advertising channels the creatives run on — Meta Ads, Google Ads, TikTok Ads, LinkedIn Ads, display networks, programmatic, or email. Each channel has different fatigue dynamics (social fatigues faster than search, video fatigues differently than static)
  • Refresh constraints (optional): Any constraints on creative refreshes — brand guidelines that limit visual changes, approval processes that add lead time, production capacity (how many new creatives can be produced per week), or budget for creative production. These constraints shape the refresh recommendations to be actionable within real-world limits
  • Performance thresholds (optional): Brand-specific thresholds for when a creative is considered "fatigued" — e.g., "CTR drops 30% from baseline" or "CPM increases 25% from baseline." If not provided, industry-standard thresholds are applied per channel
用户必须提供（或会被提示补充）：
  • 带表现数据的在投创意：当前投放的创意列表，每个创意需包含：创意ID或名称、投放渠道（付费社交、展示广告、搜索广告、邮件广告、视频广告）、当前表现指标（展示量、触达频率或人均展示次数、当前CTR、当前CPM或CPC、当前用户参与率）、创意上线前7-14天的基准指标（基准CTR、基准CPM、基准参与率）、上线时长、触达受众规模、当前日均或周均投放预算。可通过导出数据或从已连接的广告平台MCP获取
  • 渠道背景：创意投放的具体广告渠道——Meta Ads、Google Ads、TikTok Ads、LinkedIn Ads、展示广告网络、程序化广告或邮件广告。不同渠道的疲劳规律不同（社交广告比搜索广告疲劳更快，视频广告与静态广告的疲劳模式存在差异）
  • 更新约束（可选）：创意更新的相关限制——品牌视觉规范、审批流程耗时、创意制作产能（每周可产出的新创意数量）、创意制作预算。这些约束会让更新建议更贴合实际可落地的范围
  • 表现阈值（可选）：品牌自定义的创意疲劳判定阈值——例如“CTR较基准下降30%”或“CPM较基准上升25%”。若未提供，将采用各渠道的行业标准阈值

Process

执行流程

  1. Load brand context: Read 
    ~/.claude-marketing/brands/_active-brand.json
    for the active slug, then load 
    ~/.claude-marketing/brands/{slug}/profile.json
    . Apply brand creative guidelines, historical creative performance benchmarks, known fatigue patterns from past campaigns, and production capacity constraints. Also check for guidelines at 
    ~/.claude-marketing/brands/{slug}/guidelines/_manifest.json
    — if present, load visual identity restrictions and messaging guardrails that constrain refresh options. Check for agency SOPs at 
    ~/.claude-marketing/sops/
    . If no brand exists, ask: "Set up a brand first (/digital-marketing-pro:brand-setup)?" — or proceed with industry defaults.
  2. Score each creative's health: Execute 
    creative-fatigue-predictor.py
    with the performance data for each creative. The scoring model evaluates five fatigue signals — CTR ratio (current vs baseline, weighted 30%), CPM ratio (current vs baseline, weighted 25%), engagement ratio (current vs baseline, weighted 20%), frequency or impression saturation (weighted 15%), and time running relative to channel norms (weighted 10%). Each creative receives a health score from 0-100 where 100 is peak health and 0 is fully fatigued, plus a fatigue stage classification: Fresh (80-100), Mature (60-79), Fatiguing (40-59), Fatigued (20-39), or Exhausted (0-19).
  3. Predict fatigue timeline: For each creative not yet in Fatigued or Exhausted stage, project the estimated days until fatigue based on the current trajectory of decline — rate of CTR decay, CPM acceleration, and engagement erosion. Factor in audience size (smaller audiences fatigue faster), frequency rate (higher frequency accelerates fatigue), channel dynamics (social fatigues 2-3x faster than search), and seasonality effects. Output a "days remaining" estimate with confidence range for each creative.
  4. Generate refresh briefs for fatiguing creatives: For each creative in Fatiguing, Fatigued, or Exhausted stage, produce a specific refresh brief — what to keep (elements that drove initial performance: hook, value proposition, social proof, CTA that still resonates), what to change (elements contributing to fatigue: visual treatment, headline angle, color scheme, format, opening hook for video), and what to test (new angles or approaches worth experimenting with based on competitor creative trends and brand positioning). Ensure all refresh suggestions comply with brand guidelines.
  5. Create A/B test plan for each creative needing refresh: For each refresh brief, generate a structured A/B test plan — control (current creative), variant(s) with the recommended changes, hypothesis for why the variant should outperform, primary metric to evaluate (CTR, CPC, conversion rate depending on campaign objective), minimum sample size for statistical significance, expected test duration, and decision criteria for declaring a winner. Include a test naming convention for organized tracking.
  6. Prioritize by spend and impact: Rank all creatives needing attention by the combination of daily spend (higher spend = more waste if fatigued) and fatigue severity (more fatigued = more urgency). Creatives burning large budgets while deeply fatigued rank highest. Calculate the estimated spend waste — the incremental cost of running a fatigued creative versus a fresh one at baseline performance — to quantify the cost of inaction.
  1. 加载品牌背景：读取
    ~/.claude-marketing/brands/_active-brand.json
    获取当前品牌标识，再加载
    ~/.claude-marketing/brands/{slug}/profile.json
    。应用品牌创意规范、历史创意表现基准、过往 campaign 的已知疲劳模式及产能约束。同时检查
    ~/.claude-marketing/brands/{slug}/guidelines/_manifest.json
    中的规范——若存在，加载限制创意更新的视觉标识规则和内容传达准则。检查
    ~/.claude-marketing/sops/
    中的代理操作流程。若未设置品牌，将询问：“是否先设置品牌（/digital-marketing-pro:brand-setup）？”——或采用行业默认值继续执行。
  2. 为每个创意的健康状况评分：使用每个创意的表现数据运行
    creative-fatigue-predictor.py
    。评分模型评估五项疲劳信号——CTR比值（当前值vs基准值，权重30%）、CPM比值（当前值vs基准值，权重25%）、参与率比值（当前值vs基准值，权重20%）、触达频率或展示饱和度（权重15%）、投放时长相对于渠道常规周期的占比（权重10%）。每个创意会获得0-100分的健康评分（100分为最佳状态，0分为完全疲劳），并被归类到对应的疲劳阶段：新鲜（80-100）、成熟（60-79）、出现疲劳（40-59）、已疲劳（20-39）、彻底失效（0-19）。
  3. 预测疲劳时间线：对于尚未进入“已疲劳”或“彻底失效”阶段的创意，根据当前的表现下滑趋势——CTR衰减率、CPM涨幅、参与度下降速度——预测疲劳到来的预计天数。同时考虑受众规模（受众越小疲劳越快）、触达频率（频率越高疲劳加速越快）、渠道特性（社交广告疲劳速度是搜索广告的2-3倍）和季节性影响。为每个创意输出“剩余有效天数”预估及置信区间。
  4. 为出现疲劳的创意生成更新方案：针对处于“出现疲劳”“已疲劳”或“彻底失效”阶段的创意，生成具体的更新方案——保留哪些元素（驱动初始表现的核心：钩子、价值主张、社交证明、仍有效的CTA）、修改哪些元素（导致疲劳的因素：视觉风格、标题角度、配色方案、格式、视频开场钩子）、测试哪些方向（基于竞品创意趋势和品牌定位值得尝试的新角度或新方式）。确保所有更新建议符合品牌规范。
  5. 为需更新的创意制定A/B测试计划：针对每个更新方案，生成结构化的A/B测试计划——对照组（当前创意）、实验组（含建议修改内容的创意变体）、实验组应优于对照组的假设、核心评估指标（根据campaign目标选择CTR、CPC、转化率等）、具备统计显著性的最小样本量、预计测试时长、判定测试获胜者的标准。包含统一的测试命名规则以方便追踪。
  6. 按预算和影响优先级排序：结合日均投放预算（预算越高，疲劳造成的浪费越大）和疲劳严重程度（疲劳越严重，优先级越高），对所有需关注的创意进行排序。消耗大量预算且已严重疲劳的创意优先级最高。计算预估浪费预算——投放疲劳创意相较于投放基准表现的新鲜创意所增加的成本，以此量化不作为的损失。

Output

输出内容

A creative health report containing:
  • Creative health dashboard: All active creatives scored and classified — showing creative name or ID, channel, health score (0-100), fatigue stage (Fresh/Mature/Fatiguing/Fatigued/Exhausted), key metrics versus baseline (CTR ratio, CPM ratio, engagement ratio), frequency, days running, and daily spend
  • Fatigue predictions: For each non-exhausted creative, estimated days remaining before performance drops below acceptable thresholds — with confidence range and the primary driver of projected fatigue (frequency saturation, audience exhaustion, or creative wear-out)
  • Refresh priority list: Creatives ranked by urgency — combining fatigue severity with spend level to show which refreshes will save the most budget, with estimated daily spend waste for each fatigued creative
  • Refresh briefs per creative: Specific, actionable refresh recommendations for each fatiguing or fatigued creative — what to keep, what to change, what to test, and why, all within brand guidelines and production constraints
  • A/B test plans: Structured test plans for each creative refresh — control and variant definitions, hypothesis, primary metric, sample size requirement, test duration estimate, and success criteria with statistical confidence threshold
  • Creative lifecycle timeline: A timeline view showing when each active creative was launched, its current lifecycle stage, and projected transition dates — enabling proactive production planning so fresh creatives are ready before current ones fatigue out
  • Estimated performance recovery: Projected improvement in CTR, CPM, and engagement if fatigued creatives are refreshed — quantifying the expected return on creative production investment
一份创意健康报告，包含：
  • 创意健康仪表盘：所有在投创意的评分与分类——展示创意名称或ID、渠道、健康评分（0-100）、疲劳阶段（新鲜/成熟/出现疲劳/已疲劳/彻底失效）、关键指标与基准值对比（CTR比值、CPM比值、参与率比值）、触达频率、上线时长、日均预算
  • 疲劳预测：针对未彻底失效的创意，预估其表现降至可接受阈值以下的剩余天数——包含置信区间及预测疲劳的主要驱动因素（触达频率饱和、受众耗尽、创意老化）
  • 更新优先级列表：按紧急程度排序的创意——结合疲劳严重程度与预算规模，展示哪些创意更新能节省最多预算，并标注每个疲劳创意的日均预估浪费预算
  • 分创意更新方案：针对每个出现疲劳或已疲劳的创意提供具体、可执行的更新建议——保留内容、修改内容、测试方向及原因，所有建议均符合品牌规范与制作约束
  • A/B测试计划：针对每个创意更新的结构化测试计划——对照组与实验组定义、假设、核心指标、样本量要求、预估测试时长、具备统计置信度的成功标准
  • 创意生命周期时间线：时间线视图展示每个在投创意的上线时间、当前生命周期阶段及预计阶段转换日期——支持提前规划创意制作，确保新鲜创意在当前创意失效前准备就绪
  • 预估表现恢复情况：若更新疲劳创意，预估CTR、CPM和参与度的提升幅度——量化创意制作投入的预期回报

Agents Used

使用的Agent

  • content-creator — Creative refresh ideation including new visual angles, headline variations, hook alternatives, and format experiments grounded in brand voice and positioning, refresh brief generation with specific keep/change/test recommendations, and A/B test variant design with clear hypotheses tied to fatigue diagnosis
  • media-buyer — Performance analysis across channels with fatigue-adjusted benchmarking, spend waste calculation for fatigued creatives, budget impact prioritization ranking refreshes by cost of inaction, and channel-specific fatigue threshold calibration based on platform dynamics and audience behavior
  • performance-monitor-agent — Fatigue signal detection from performance metric trends, health score calculation using weighted multi-signal composite model, fatigue timeline projection based on decay rate analysis, and creative lifecycle stage classification with transition monitoring
  • content-creator — 基于品牌调性与定位进行创意更新构思，包括新视觉角度、标题变体、钩子替代方案和格式尝试；生成包含具体保留/修改/测试建议的更新方案；设计A/B测试变体并结合疲劳诊断提出清晰假设
  • media-buyer — 跨渠道表现分析与疲劳校准基准对比；计算疲劳创意的浪费预算；结合不作为成本对创意更新进行预算影响优先级排序；基于平台特性与受众行为校准渠道专属疲劳阈值
  • performance-monitor-agent — 从表现指标趋势中检测疲劳信号；使用加权多信号复合模型计算健康评分；基于衰减率分析预测疲劳时间线；对创意生命周期阶段进行分类并监控阶段转换