ElasticFlow
AI SkillAnalyze CampaignMarketingby Gooseworks

Ad Campaign Analyzer — diagnose what to cut, scale, and test

Runs on
ClaudeClaudeChatGPTChatGPTOpenClawOpenClaw

Diagnose ad campaign performance and produce action items

  • Accepts CSV, paste, or screenshot data from Google/Meta/LinkedIn
  • Detects budget waste, zero-conversion items, and high-CPA outliers
  • Identifies winners with sample-size and significance checks
  • Diagnoses funnel drop-offs from impression to revenue
  • Outputs a prioritized action plan: pause, scale, test

Who this is for

Growth Marketer

You run experiments, optimize funnels, and own the numbers from signup to revenue. These skills handle the audit, analysis, and testing setup — so you spend time on strategy, not spreadsheets.

See skills for this role

What it does

Weekly campaign review

Replace dashboard staring with a diagnosis: what is working, what is wasting budget, and what to do this week.

Inherited account audit

When you take over an existing ad account, get a structured audit before you touch a single bid.

Pre-meeting prep

Generate an executive summary with the top recommendation before your weekly leadership review.

How it works

1

Take CSV, paste, or screenshot of campaign data as input

2

Normalize across platforms into apples-to-apples metrics

3

Run diagnostic: budget waste, winners, A/B significance, funnel drop-offs

4

Score each campaign: scale, optimize, or pause

5

Output a prioritized action plan with specific items per timeframe

Metrics this improves

Conversion Rate
Higher conversion rate after fixing funnel drop-offs the audit identifies
Marketing
Ad CTR
Higher CTR by replacing low-CTR creative flagged in the audit
Marketing
CPA
Lower CPA by killing zero-conversion spend and scaling proven items
Marketing

Works with

Google Ads
manual

Source of campaign performance CSV exports

LinkedIn
manual

Source of LinkedIn Campaign Manager exports

Meta Ads
manual

Source of Meta Ads Manager performance data

Similar skills

Auto-suggested by attribute overlap. Side-by-side comparison shows what differs.

Compare all 4 →

Search Ad Keyword Architect

by Gooseworks
↳ad-creative, ad-targetingvsad-targeting(Optimization surface)·text, file-uploadvstext, url(What you provide)·markdownvsmarkdown, csv(Output formats)

Meta Ads Campaign Builder

by Gooseworks
↳text, file-uploadvstext(What you provide)·markdownvsmarkdown, csv(Output formats)·nonevsapproval-required(Human review)

Trending Ad Hook Spotter

by Gooseworks
↳ad-creative, ad-targetingvsad-creative(Optimization surface)·text, file-uploadvstext, api-credentials(What you provide)·nonevsreview-required(Human review)
Sorted by attribute overlap × differentiation. Ad Campaign Analyzer shares 18+ attributes with each.
View on GitHub

Ad Campaign Analyzer

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.

When to Use

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

Phase 0: Intake

  1. 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)
  2. Platform(s) — Google / Meta / LinkedIn / All
  3. Time period — What date range does this cover?
  4. Monthly budget — Total ad spend in this period
  5. Primary goal — What conversion are you optimizing for? (Demos / Trials / Purchases / Leads)
  6. Target metrics — Do you have target CPA or ROAS? (If not, we'll benchmark)
  7. Any known changes? — Did you change creative, budget, or targeting during this period?

Phase 1: Data Ingestion & Normalization

Accepted Data Formats

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

Normalize all data into a standard analysis format:

DimensionImpressionsClicksCTRCPCConversionsConv RateCPASpendRevenue/Value

Phase 2: Performance Diagnostics

2A: Campaign-Level Health Check

For each campaign:

MetricValueBenchmarkStatus
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]

2B: Budget Waste Detection

Identify spend that produced no or negative return:

Waste TypeSignalAction
Zero-conversion keywords/adsSpend > $[X] with 0 conversionsPause or add negatives
High CPA outliersCPA > 3x targetPause or restructure
Low CTR adsCTR < 50% of campaign averageReplace creative
Broad match bleedSearch terms report showing irrelevant clicksAdd negative keywords
Audience overlapSame users hit by multiple campaignsExclude audiences
Dayparting wasteConversions cluster at certain hours; spend is 24/7Set ad schedule

2C: Winner Identification

Find what's actually working:

Winner TypeSignalAction
Top-performing keywordsLowest CPA, highest conv rateIncrease bid, add variants
Winning adsHighest CTR + conv rate comboScale spend, clone for other groups
Best audiencesLowest CPA segmentIncrease budget allocation
Best timesPeak conversion hours/daysConcentrate budget

2D: Statistical Significance Check

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.

Phase 3: Funnel Analysis

Click → Conversion Path

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

Drop-Off PointRateBenchmarkLikely CauseFix
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]

Phase 4: Output Format

# 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] |

---

## 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 |
|------|-----|----------|--------------|-------------------|

### Top Ads
| 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]

---

## Action Plan

### Immediate (This Week)
- [ ] **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]

### 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.

Cost

ComponentCost
Data analysisFree (LLM reasoning)
Statistical calculationsFree
TotalFree

Tools Required

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

Trigger Phrases

  • "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"