ad-campaign-analyzer

Name: ad-campaign-analyzer
Author: gooseworks-ai

43installs193forks

How to install ad-campaign-analyzer?

gooseworks-ai/goose-skills/ad-campaign-analyzer

$npx -y skills add gooseworks-ai/goose-skills --skill ad-campaign-analyzer

Installs into the current project.

Summary

Analyze ad campaign performance data (Google, Meta, LinkedIn) to identify what's working, what's wasting budget, and specific cut/scale/test recommendations. Runs statistical analysis, funnel diagnostics, and multi-channel budget reallocation with specific dollar-amount shift rec

Files · 1

View on GitHub

SKILL.md

1	# Ad Campaign Analyzer
2
3	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. Then it goes further: it compares channels on equal terms, finds where you're over-spending vs under-spending relative to results, and produces a concrete budget reallocation plan.
4
5	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. It also solves the allocation problem — most startups either spread budget too thin across channels (no channel gets enough to learn) or dump everything into one channel (missing cheaper opportunities elsewhere).
6
7	## When to Use
8
9	- "Analyze my Google Ads performance"
10	- "Which ads should I kill?"
11	- "Is this campaign working?"
12	- "Where am I wasting ad spend?"
13	- "Optimize my Meta Ads"
14	- "How should I split my ad budget?"
15	- "Should I spend more on Google or Meta?"
16	- "Reallocate my ad spend across channels"
17	- "Where am I getting the best return?"
18	- "I have $X/month for ads — how should I distribute it?"
19
20	## Phase 0: Intake
21
22	1. Campaign data — One of:
23	- CSV export from Google Ads / Meta Ads Manager / LinkedIn Campaign Manager
24	- Pasted performance table
25	- Screenshots of dashboard (we'll extract the data)
26	2. Platform(s) — Google / Meta / LinkedIn / All
27	3. Time period — What date range does this cover?
28	4. Monthly budget — Total ad spend in this period
29	5. Primary goal — What conversion are you optimizing for? (Demos / Trials / Purchases / Leads)
30	6. Target metrics — Do you have target CPA or ROAS? (If not, we'll benchmark)
31	7. Any known changes? — Did you change creative, budget, or targeting during this period?
32	8. Channels currently running — Google Ads, Meta Ads, LinkedIn Ads, Twitter/X Ads, TikTok Ads, other
33	9. Funnel data (if available):
34	- Lead → MQL rate
35	- MQL → SQL rate
36	- SQL → Close rate
37	- Average deal size
38	10. Channels you're considering but haven't tried — Want to test new channels?
39	11. Constraints — Minimum spend on any channel? Platform you must stay on?
40
41	## Phase 1: Data Ingestion & Normalization
42
43	### Accepted Data Formats
44
45	\| Source \| Key Columns Expected \|
46	\|--------\|---------------------\|
47	\| Google Ads \| Campaign, Ad Group, Keyword, Impressions, Clicks, CTR, CPC, Conversions, Conv Rate, Cost, Conv Value \|
48	\| Meta Ads \| Campaign, Ad Set, Ad, Impressions, Reach, Clicks, CTR, CPC, Conversions, Cost Per Result, Amount Spent, ROAS \|
49	\| LinkedIn Ads \| Campaign, Impressions, Clicks, CTR, CPC, Conversions, Cost, Leads \|
50
51	Normalize all data into a standard analysis format:
52
53	\| Dimension \| Impressions \| Clicks \| CTR \| CPC \| Conversions \| Conv Rate \| CPA \| Spend \| Revenue/Value \|
54	\|-----------\|------------\|--------\|-----\|-----\|-------------\|----------\|-----\|-------\|--------------\|
55
56	### Multi-Channel Normalization
57
58	When data spans multiple channels, also produce a channel-level rollup:
59
60	\| Channel \| Monthly Spend \| Impressions \| Clicks \| CTR \| CPC \| Conversions \| Conv Rate \| CPA \| ROAS \| CAC* \|
61	\|---------\|-------------\|------------\|--------\|-----\|-----\|-------------\|----------\|-----\|------\|------\|
62	\| Google Search \| $[X] \| [N] \| [N] \| [X%] \| $[X] \| [N] \| [X%] \| $[X] \| [X] \| $[X] \|
63	\| Google Display \| ... \| \| \| \| \| \| \| \| \| \|
64	\| Meta (FB/IG) \| ... \| \| \| \| \| \| \| \| \| \|
65	\| LinkedIn \| ... \| \| \| \| \| \| \| \| \| \|
66	\| [Other] \| ... \| \| \| \| \| \| \| \| \| \|
67	\| Total \| $[X] \| \| \| \| \| [N] \| \| $[X] avg \| [X] avg \| $[X] avg \|
68
69	*CAC = Full customer acquisition cost if funnel data provided (CPA × close-rate adjustment)
70
71	### Funnel-Adjusted CAC (If Funnel Data Available)
72
73	```
74	Channel CAC = CPA ÷ (MQL rate × SQL rate × Close rate)
75	```
76
77	This reveals which channels produce leads that actually close, not just convert.
78
79	## Phase 2: Performance Diagnostics
80
81	### 2A: Campaign-Level Health Check
82
83	For each campaign:
84
85	\| Metric \| Value \| Benchmark \| Status \|
86	\|--------\|-------\|-----------\|--------\|
87	\| CTR \| [X%] \| [Industry avg] \| [Good/Okay/Poor] \|
88	\| CPC \| $[X] \| [Category avg] \| [Good/Okay/Poor] \|
89	\| Conv Rate \| [X%] \| [Benchmark] \| [Good/Okay/Poor] \|
90	\| CPA \| $[X] \| [Target or benchmark] \| [Good/Okay/Poor] \|
91	\| ROAS \| [X] \| [Target or benchmark] \| [Good/Okay/Poor] \|
92	\| Impression Share \| [X%] \| [>60% ideal] \| [Good/Okay/Poor] \|
93
94	### 2B: Budget Waste Detection
95
96	Identify spend that produced no or negati

People who liked this also viewed

6 picks

Type

ad-campaign-analyzer

43installs193forks

View on GitHub

How to install ad-campaign-analyzer?

gooseworks-ai/goose-skills/ad-campaign-analyzer

$npx -y skills add gooseworks-ai/goose-skills --skill ad-campaign-analyzer

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Ad Campaign Analyzer
2
3	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. Then it goes further: it compares channels on equal terms, finds where you're over-spending vs under-spending relative to results, and produces a concrete budget reallocation plan.
4
5	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. It also solves the allocation problem — most startups either spread budget too thin across channels (no channel gets enough to learn) or dump everything into one channel (missing cheaper opportunities elsewhere).
6
7	## When to Use
8
9	- "Analyze my Google Ads performance"
10	- "Which ads should I kill?"
11	- "Is this campaign working?"
12	- "Where am I wasting ad spend?"
13	- "Optimize my Meta Ads"
14	- "How should I split my ad budget?"
15	- "Should I spend more on Google or Meta?"
16	- "Reallocate my ad spend across channels"
17	- "Where am I getting the best return?"
18	- "I have $X/month for ads — how should I distribute it?"
19
20	## Phase 0: Intake
21
22	1. Campaign data — One of:
23	- CSV export from Google Ads / Meta Ads Manager / LinkedIn Campaign Manager
24	- Pasted performance table
25	- Screenshots of dashboard (we'll extract the data)
26	2. Platform(s) — Google / Meta / LinkedIn / All
27	3. Time period — What date range does this cover?
28	4. Monthly budget — Total ad spend in this period
29	5. Primary goal — What conversion are you optimizing for? (Demos / Trials / Purchases / Leads)
30	6. Target metrics — Do you have target CPA or ROAS? (If not, we'll benchmark)
31	7. Any known changes? — Did you change creative, budget, or targeting during this period?
32	8. Channels currently running — Google Ads, Meta Ads, LinkedIn Ads, Twitter/X Ads, TikTok Ads, other
33	9. Funnel data (if available):
34	- Lead → MQL rate
35	- MQL → SQL rate
36	- SQL → Close rate
37	- Average deal size
38	10. Channels you're considering but haven't tried — Want to test new channels?
39	11. Constraints — Minimum spend on any channel? Platform you must stay on?
40
41	## Phase 1: Data Ingestion & Normalization
42
43	### Accepted Data Formats
44
45	\| Source \| Key Columns Expected \|
46	\|--------\|---------------------\|
47	\| Google Ads \| Campaign, Ad Group, Keyword, Impressions, Clicks, CTR, CPC, Conversions, Conv Rate, Cost, Conv Value \|
48	\| Meta Ads \| Campaign, Ad Set, Ad, Impressions, Reach, Clicks, CTR, CPC, Conversions, Cost Per Result, Amount Spent, ROAS \|
49	\| LinkedIn Ads \| Campaign, Impressions, Clicks, CTR, CPC, Conversions, Cost, Leads \|
50
51	Normalize all data into a standard analysis format:
52
53	\| Dimension \| Impressions \| Clicks \| CTR \| CPC \| Conversions \| Conv Rate \| CPA \| Spend \| Revenue/Value \|
54	\|-----------\|------------\|--------\|-----\|-----\|-------------\|----------\|-----\|-------\|--------------\|
55
56	### Multi-Channel Normalization
57
58	When data spans multiple channels, also produce a channel-level rollup:
59
60	\| Channel \| Monthly Spend \| Impressions \| Clicks \| CTR \| CPC \| Conversions \| Conv Rate \| CPA \| ROAS \| CAC* \|
61	\|---------\|-------------\|------------\|--------\|-----\|-----\|-------------\|----------\|-----\|------\|------\|
62	\| Google Search \| $[X] \| [N] \| [N] \| [X%] \| $[X] \| [N] \| [X%] \| $[X] \| [X] \| $[X] \|
63	\| Google Display \| ... \| \| \| \| \| \| \| \| \| \|
64	\| Meta (FB/IG) \| ... \| \| \| \| \| \| \| \| \| \|
65	\| LinkedIn \| ... \| \| \| \| \| \| \| \| \| \|
66	\| [Other] \| ... \| \| \| \| \| \| \| \| \| \|
67	\| Total \| $[X] \| \| \| \| \| [N] \| \| $[X] avg \| [X] avg \| $[X] avg \|
68
69	*CAC = Full customer acquisition cost if funnel data provided (CPA × close-rate adjustment)
70
71	### Funnel-Adjusted CAC (If Funnel Data Available)
72
73	```
74	Channel CAC = CPA ÷ (MQL rate × SQL rate × Close rate)
75	```
76
77	This reveals which channels produce leads that actually close, not just convert.
78
79	## Phase 2: Performance Diagnostics
80
81	### 2A: Campaign-Level Health Check
82
83	For each campaign:
84
85	\| Metric \| Value \| Benchmark \| Status \|
86	\|--------\|-------\|-----------\|--------\|
87	\| CTR \| [X%] \| [Industry avg] \| [Good/Okay/Poor] \|
88	\| CPC \| $[X] \| [Category avg] \| [Good/Okay/Poor] \|
89	\| Conv Rate \| [X%] \| [Benchmark] \| [Good/Okay/Poor] \|
90	\| CPA \| $[X] \| [Target or benchmark] \| [Good/Okay/Poor] \|
91	\| ROAS \| [X] \| [Target or benchmark] \| [Good/Okay/Poor] \|
92	\| Impression Share \| [X%] \| [>60% ideal] \| [Good/Okay/Poor] \|
93
94	### 2B: Budget Waste Detection
95
96	Identify spend that produced no or negati

People who liked this also viewed

6 picks

Type