ad-campaign-analyzer

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Ad Campaign Analyzer

广告活动分析技能

Take raw campaign performance data and turn it into clear decisions. This skill doesn't just summarize metrics — it diagnoses problems, identifies winners, checks statistical significance, and tells you exactly what to cut, scale, and test next.

Core principle: Most startup founders check their ad dashboard, see a ROAS number, and either panic or celebrate. This skill gives you the nuanced analysis a paid media specialist would: what's actually significant, what's noise, and where your next dollar should go.

将原始广告活动表现数据转化为清晰的决策依据。本技能不仅会汇总指标，还会诊断问题、识别有效策略、检验统计显著性，并明确告知你下一步应该削减、扩容和测试的具体内容。

核心原则： 大多数初创公司创始人查看广告仪表盘时，只会看ROAS数值，要么恐慌要么庆祝。而本技能能为你提供付费媒体专家级的精细化分析：哪些指标真正有意义，哪些是干扰数据，以及你的下一笔预算应该投向何处。

When to Use

适用场景

"Analyze my Google Ads performance"
"Which ads should I kill?"
"Is this campaign working?"
"Where am I wasting ad spend?"
"Optimize my Meta Ads"

"分析我的Google Ads表现"
"哪些广告应该停投？"
"这个广告系列有效吗？"
"我的广告预算浪费在了哪里？"
"优化我的Meta Ads"

Phase 0: Intake

阶段0：数据收集

Campaign data — One of:
- CSV export from Google Ads / Meta Ads Manager / LinkedIn Campaign Manager
- Pasted performance table
- Screenshots of dashboard (we'll extract the data)
Platform(s) — Google / Meta / LinkedIn / All
Time period — What date range does this cover?
Monthly budget — Total ad spend in this period
Primary goal — What conversion are you optimizing for? (Demos / Trials / Purchases / Leads)
Target metrics — Do you have target CPA or ROAS? (If not, we'll benchmark)
Any known changes? — Did you change creative, budget, or targeting during this period?

广告活动数据 — 以下形式之一：
- 从Google Ads / Meta Ads Manager / LinkedIn Campaign Manager导出的CSV文件
- 粘贴的表现数据表格
- 仪表盘截图（我们会提取其中的数据）
平台 — Google / Meta / LinkedIn / 全部
时间范围 — 数据覆盖的日期区间是什么？
月度预算 — 该时间段内的总广告支出
核心目标 — 你要优化的转化目标是什么？（演示申请 / 试用 / 购买 / 销售线索）
目标指标 — 你是否有目标CPA或ROAS？（如果没有，我们会提供基准值）
已知变动 — 在此期间你是否更改过创意素材、预算或定向设置？

Phase 1: Data Ingestion & Normalization

阶段1：数据导入与标准化

Accepted Data Formats

支持的数据格式

Source	Key Columns Expected
Google Ads	Campaign, Ad Group, Keyword, Impressions, Clicks, CTR, CPC, Conversions, Conv Rate, Cost, Conv Value
Meta Ads	Campaign, Ad Set, Ad, Impressions, Reach, Clicks, CTR, CPC, Conversions, Cost Per Result, Amount Spent, ROAS
LinkedIn Ads	Campaign, Impressions, Clicks, CTR, CPC, Conversions, Cost, Leads

Normalize all data into a standard analysis format:

Dimension	Impressions	Clicks	CTR	CPC	Conversions	Conv Rate	CPA	Spend	Revenue/Value

来源	预期关键列
Google Ads	Campaign, Ad Group, Keyword, Impressions, Clicks, CTR, CPC, Conversions, Conv Rate, Cost, Conv Value
Meta Ads	Campaign, Ad Set, Ad, Impressions, Reach, Clicks, CTR, CPC, Conversions, Cost Per Result, Amount Spent, ROAS
LinkedIn Ads	Campaign, Impressions, Clicks, CTR, CPC, Conversions, Cost, Leads

将所有数据标准化为统一的分析格式：

维度	Impressions	Clicks	CTR	CPC	Conversions	Conv Rate	CPA	Spend	Revenue/Value

Phase 2: Performance Diagnostics

阶段2：表现诊断

2A: Campaign-Level Health Check

2A：广告系列层面健康检查

For each campaign:

Metric	Value	Benchmark	Status
CTR	[X%]	[Industry avg]	[Good/Okay/Poor]
CPC	$[X]	[Category avg]	[Good/Okay/Poor]
Conv Rate	[X%]	[Benchmark]	[Good/Okay/Poor]
CPA	$[X]	[Target or benchmark]	[Good/Okay/Poor]
ROAS	[X]	[Target or benchmark]	[Good/Okay/Poor]
Impression Share	[X%]	[>60% ideal]	[Good/Okay/Poor]

针对每个广告系列：

指标	数值	基准值	状态
CTR	[X%]	[行业平均值]	[良好/一般/不佳]
CPC	$[X]	[品类平均值]	[良好/一般/不佳]
Conv Rate	[X%]	[基准值]	[良好/一般/不佳]
CPA	$[X]	[目标值或基准值]	[良好/一般/不佳]
ROAS	[X]	[目标值或基准值]	[良好/一般/不佳]
Impression Share	[X%]	[理想值>60%]	[良好/一般/不佳]

2B: Budget Waste Detection

2B：预算浪费检测

Identify spend that produced no or negative return:

Waste Type	Signal	Action
Zero-conversion keywords/ads	Spend > $[X] with 0 conversions	Pause or add negatives
High CPA outliers	CPA > 3x target	Pause or restructure
Low CTR ads	CTR < 50% of campaign average	Replace creative
Broad match bleed	Search terms report showing irrelevant clicks	Add negative keywords
Audience overlap	Same users hit by multiple campaigns	Exclude audiences
Dayparting waste	Conversions cluster at certain hours; spend is 24/7	Set ad schedule

识别无回报或负回报的支出：

浪费类型	信号	行动建议
零转化关键词/广告	支出>$[X]但转化为0	暂停投放或添加否定关键词
高CPA异常项	CPA>目标值3倍	暂停投放或重组
低CTR广告	CTR<广告系列平均值的50%	替换创意素材
广泛匹配溢出	搜索词报告显示无关点击	添加否定关键词
受众重叠	同一用户被多个广告系列触达	排除重叠受众
时段投放浪费	转化集中在特定时段，但24小时持续投放	设置广告投放时段

2C: Winner Identification

2C：有效策略识别

Find what's actually working:

Winner Type	Signal	Action
Top-performing keywords	Lowest CPA, highest conv rate	Increase bid, add variants
Winning ads	Highest CTR + conv rate combo	Scale spend, clone for other groups
Best audiences	Lowest CPA segment	Increase budget allocation
Best times	Peak conversion hours/days	Concentrate budget

找出真正有效的内容：

有效类型	信号	行动建议
高表现关键词	CPA最低，转化最高	提高出价，添加变体词
优质广告	CTR与转化率组合最优	增加预算，复制到其他广告组
最佳受众	CPA最低的受众细分	增加预算分配
最佳时段	转化峰值时段/日期	集中预算投放

2D: Statistical Significance Check

2D：统计显著性检验

For any A/B test (ad variants, audiences, landing pages):

Test: [Variant A] vs [Variant B]
Metric: [Conv Rate / CTR / CPA]
Variant A: [X%] (n=[sample_size])
Variant B: [Y%] (n=[sample_size])
Confidence level: [X%]
Verdict: [Statistically significant / Not enough data / Too close to call]
Recommended action: [Pick winner / Continue test / Increase budget to reach significance]

Minimum sample: 100 clicks per variant for CTR tests, 30 conversions per variant for CPA tests.

针对任何A/B测试（广告变体、受众、着陆页）：

Test: [Variant A] vs [Variant B]
Metric: [Conv Rate / CTR / CPA]
Variant A: [X%] (n=[sample_size])
Variant B: [Y%] (n=[sample_size])
Confidence level: [X%]
Verdict: [Statistically significant / Not enough data / Too close to call]
Recommended action: [Pick winner / Continue test / Increase budget to reach significance]

最小样本量：CTR测试每个变体需100次点击，CPA测试每个变体需30次转化。

Phase 3: Funnel Analysis

阶段3：漏斗分析

Click → Conversion Path

点击→转化路径

Impressions: [N] (100%)
     ↓ CTR: [X%]
Clicks: [N] ([X%] of impressions)
     ↓ Landing page → Conversion: [X%]
Conversions: [N] ([X%] of clicks)
     ↓ Conversion → Revenue: $[X] avg
Revenue: $[N]

Impressions: [N] (100%)
     ↓ CTR: [X%]
Clicks: [N] ([X%] of impressions)
     ↓ Landing page → Conversion: [X%]
Conversions: [N] ([X%] of clicks)
     ↓ Conversion → Revenue: $[X] avg
Revenue: $[N]

Funnel Drop-Off Diagnosis

漏斗流失诊断

Drop-Off Point	Rate	Benchmark	Likely Cause	Fix
Impression → Click	[CTR%]	[Benchmark]	[Ad relevance / targeting]	[Copy/targeting change]
Click → Conversion	[Conv%]	[Benchmark]	[Landing page / offer / audience mismatch]	[LP optimization]
Conversion → Revenue	[Close%]	[Benchmark]	[Lead quality / sales process]	[Qualification criteria]

流失节点	比例	基准值	可能原因	修复建议
曝光→点击	[CTR%]	[基准值]	[广告相关性/定向]	[修改文案/定向]
点击→转化	[Conv%]	[基准值]	[着陆页/优惠/受众不匹配]	[优化着陆页]
转化→营收	[Close%]	[基准值]	[线索质量/销售流程]	[调整资格标准]

Phase 4: Output Format

阶段4：输出格式

markdown

undefined

markdown

undefined

Ad Campaign Analysis — [Product/Client] — [DATE]

Period: [Date range] Total spend: $[X] Platform(s): [Google / Meta / LinkedIn] Primary goal: [Conversions / Revenue / Leads]

Executive Summary

[3-5 sentences: Overall performance verdict, biggest win, biggest problem, top recommendation]

Performance Dashboard

Campaign	Spend	Impressions	Clicks	CTR	CPC	Conversions	CPA	ROAS	Verdict
[Name]	$[X]	[N]	[N]	[X%]	$[X]	[N]	$[X]	[X]	[Scale/Optimize/Pause]

Campaign	Spend	Impressions	Clicks	CTR	CPC	Conversions	CPA	ROAS	Verdict
[Name]	$[X]	[N]	[N]	[X%]	$[X]	[N]	$[X]	[X]	[Scale/Optimize/Pause]

Budget Waste Report

Total estimated waste: $[X] ([X%] of total spend)

Wasted on zero-conversion items: $[X]

[List of keywords/ads/audiences with spend but no conversions]

Wasted on high-CPA items: $[X]

[List of items with CPA > 3x target]

Recommended saves: $[X]/month

[Specific items to pause]

Winners to Scale

Top Keywords/Audiences

Item	CPA	Conv Rate	Current Spend	Recommended Spend

Item	CPA	Conv Rate	Current Spend	Recommended Spend

Top Ads

Ad	CTR	Conv Rate	Why It Works

Ad	CTR	Conv Rate	Why It Works

A/B Test Results

[Test Name]

Variant A: [Metric] (n=[N])
Variant B: [Metric] (n=[N])
Confidence: [X%]
Verdict: [Winner / Continue / Inconclusive]

Variant A: [Metric] (n=[N])
Variant B: [Metric] (n=[N])
Confidence: [X%]
Verdict: [Winner / Continue / Inconclusive]

Action Plan

Immediate (This Week)

Pause: [Specific items — keywords, ads, audiences]
Scale: [Specific items — increase budget/bids]
Add negatives: [Specific keywords from search terms]

Pause: [Specific items — keywords, ads, audiences]
Scale: [Specific items — increase budget/bids]
Add negatives: [Specific keywords from search terms]

This Month

Test: [New ad angles / audiences / landing pages]
Restructure: [Ad groups that need splitting or merging]
Optimize: [Bid strategy changes]

Test: [New ad angles / audiences / landing pages]
Restructure: [Ad groups that need splitting or merging]
Optimize: [Bid strategy changes]

Next Month

Expand: [New campaigns / channels to test]
Review: [Run this analysis again]


Save to `clients/<client-name>/ads/campaign-analysis-[YYYY-MM-DD].md`.

Expand: [New campaigns / channels to test]
Review: [Run this analysis again]


保存至 `clients/<client-name>/ads/campaign-analysis-[YYYY-MM-DD].md`。

Cost

成本

Component	Cost
Data analysis	Free (LLM reasoning)
Statistical calculations	Free
Total	Free

组件	费用
数据分析	免费（LLM推理）
统计计算	免费
总计	免费

Tools Required

所需工具

No external tools needed — pure reasoning skill
User provides campaign data as CSV, paste, or screenshot

无需外部工具 — 纯推理技能
用户需提供CSV、粘贴数据或截图形式的广告活动数据

Trigger Phrases

触发短语

"Analyze my ad campaign performance"
"Which ads should I pause?"
"Where am I wasting ad budget?"
"Is my Google Ads campaign working?"
"Optimize my Meta Ads spend"

"Analyze my ad campaign performance"
"Which ads should I pause?"
"Where am I wasting ad budget?"
"Is my Google Ads campaign working?"
"Optimize my Meta Ads spend"