meta-ads-analyzer

Name: meta-ads-analyzer
Author: gooseworks-ai

28installs193forks

How to install meta-ads-analyzer?

gooseworks-ai/goose-skills/meta-ads-analyzer

$npx -y skills add gooseworks-ai/goose-skills --skill meta-ads-analyzer

Installs into the current project.

Summary

Diagnose Meta Ads campaign performance using Meta's actual system mechanics — Breakdown Effect, Learning Phase, Auction Overlap, Pacing, and Creative Fatigue — and produce structured, testable recommendations that avoid judging segments by average CPA instead of marginal efficien

Files · 1

View on GitHub

SKILL.md

1	# Meta Ads Analyzer
2
3	Most "Meta Ads analysis" stops at "this CPA is high, pause it." That's wrong more often than it's right. Meta's delivery system optimizes for marginal efficiency — the cost of the next conversion — not average efficiency across a snapshot. A segment with a higher average CPA is often the one keeping your overall campaign cheap. Pausing it makes things worse.
4
5	This skill diagnoses Meta campaigns the way a senior media buyer would: at the right evaluation level, accounting for learning state, separating noise from signal, and explaining why the system is making the decisions it's making before recommending any change.
6
7	Core principle: Holistic first, then drill down. Marginal over average. Dynamic over static. Every recommendation is a testable hypothesis with expected impact, not a directive.
8
9	## When to Use
10
11	- "Analyze my Meta Ads campaign performance"
12	- "Why is the system spending more on the higher-CPA placement?"
13	- "Diagnose what's wrong with this ad set"
14	- "Should I pause this audience / placement / ad?"
15	- "My CPA jumped — is this normal or a real problem?"
16	- "Audit this campaign before I scale budget"
17	- "I exported my Meta data — what does it actually mean?"
18
19	## Phase 0: Intake
20
21	1. Campaign data — One of:
22	- CSV export from Meta Ads Manager (Campaign / Ad Set / Ad level + breakdowns)
23	- Pasted performance table
24	- Screenshots (we'll extract the metrics)
25	- Live data via your existing Meta Marketing API connection
26	2. Campaign setup:
27	- Objective (Awareness / Traffic / Engagement / Lead Gen / Conversions / Sales / App Installs)
28	- Budget type (Advantage+ Campaign Budget = CBO, or Ad Set Budget = ABO)
29	- Placements (Automatic vs. manual)
30	- Number of ad sets and ads
31	3. Time period — Date range covered, with any known events (creative refresh, budget change, audience edit, account issue)
32	4. Target metrics — CPA target, ROAS target, or "no target — benchmark me"
33	5. Funnel context (if relevant) — On-platform conversion vs. website event vs. downstream qualification rate
34	6. What's making you ask? — Specific concern ("CPA up 40%"), routine review, or pre-scale audit
35
36	## Phase 1: Identify the Correct Evaluation Level
37
38	This is the most important step. Evaluating at the wrong level is the #1 source of wrong recommendations.
39
40	\| Campaign Setup \| Correct Evaluation Level \| Why \|
41	\|---\|---\|---\|
42	\| Advantage+ Campaign Budget (CBO) \| Campaign level \| System pools budget across ad sets — only campaign totals reflect reality \|
43	\| Automatic placements (no CBO) \| Ad Set level \| System pools budget across placements within the ad set \|
44	\| Multiple ads in 1 ad set \| Ad Set level \| System pools delivery across ads \|
45	\| Manual placements + ABO \| Placement / Ad Set level \| Each is independent \|
46
47	Output for this phase: State the evaluation level explicitly and explain why before any metric is interpreted.
48
49	> If asked "is this Meta placement underperforming?" on a CBO campaign, the answer is "wrong question — at CBO the placement-level CPA is misleading. Here's the campaign total..."
50
51	## Phase 2: Check Learning Phase Status
52
53	Before judging anything, check delivery state per ad set.
54
55	Learning state checklist:
56	- Status is `Learning` (delivery less stable, CPA typically higher, results not predictive)
57	- Exits after ~50 optimization events within 7 days of last significant edit
58	- Shops ads exception: 17 website purchases + 5 Meta purchases
59	- Status `Learning Limited` = can't get enough events → flag as a structural issue, not a performance issue
60
61	Significant edits that reset learning:
62	- Targeting changes
63	- Optimization event change
64	- Creative changes (large)
65	- Bid strategy / amount changes
66	- Budget changes >20%
67
68	Output for this phase: Per ad set, mark `Active` / `Learning` / `Learning Limited`. Caveat all conclusions for anything in learning. Do not recommend pausing a Learning ad set based on CPA alone.
69
70	## Phase 3: Diagnose with Meta-Specific Lenses
71
72	Run the diagnosis through these five lenses. Each one explains a different class of "weird" behavior.
73
74	### 3A: Marginal Efficiency Analysis (Breakdown Effect)
75
76	The Breakdown Effect: the system shifts budget toward segments where the next conversion is cheapest, not where the average conversion is cheapest. A segment can have a high average CPA in a breakdown report and still be the right place for budget.
77
78	How to spot it:
79	- Time-series the segment's CPA. If marginal CPA is rising sharply, expect the system to shift budget out — even if average looks fine.
80	- A breakdown row with high average CPA + high spend usually means the system found ch

gooseworks-aiPublisher · 155 listings

Preview

gooseworks-ai/goose-skills

# Meta Ads Analyzer

Most "Meta Ads analysis" stops at "this CPA is high, pause it." That's wrong more often than it's right. Meta's delivery system optimizes for **marginal efficie

This skill diagnoses Meta campaigns the way a senior media buyer would: at the right evaluation level, accounting for learning state, separating noise from sign

**Core principle:** Holistic first, then drill down. Marginal over average. Dynamic over static. Every recommendation is a testable hypothesis with expected imp

Repogooseworks-ai/goose-skills

LicenseMIT

TypeSkills

CategoryMarketing

UpdatedJul 2026

Repo stars1.0k

First seenJul 22, 2026

People who liked this also viewed

6 picks

Type

meta-ads-analyzer

28installs193forks

View on GitHub

How to install meta-ads-analyzer?

gooseworks-ai/goose-skills/meta-ads-analyzer

$npx -y skills add gooseworks-ai/goose-skills --skill meta-ads-analyzer

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Meta Ads Analyzer
2
3	Most "Meta Ads analysis" stops at "this CPA is high, pause it." That's wrong more often than it's right. Meta's delivery system optimizes for marginal efficiency — the cost of the next conversion — not average efficiency across a snapshot. A segment with a higher average CPA is often the one keeping your overall campaign cheap. Pausing it makes things worse.
4
5	This skill diagnoses Meta campaigns the way a senior media buyer would: at the right evaluation level, accounting for learning state, separating noise from signal, and explaining why the system is making the decisions it's making before recommending any change.
6
7	Core principle: Holistic first, then drill down. Marginal over average. Dynamic over static. Every recommendation is a testable hypothesis with expected impact, not a directive.
8
9	## When to Use
10
11	- "Analyze my Meta Ads campaign performance"
12	- "Why is the system spending more on the higher-CPA placement?"
13	- "Diagnose what's wrong with this ad set"
14	- "Should I pause this audience / placement / ad?"
15	- "My CPA jumped — is this normal or a real problem?"
16	- "Audit this campaign before I scale budget"
17	- "I exported my Meta data — what does it actually mean?"
18
19	## Phase 0: Intake
20
21	1. Campaign data — One of:
22	- CSV export from Meta Ads Manager (Campaign / Ad Set / Ad level + breakdowns)
23	- Pasted performance table
24	- Screenshots (we'll extract the metrics)
25	- Live data via your existing Meta Marketing API connection
26	2. Campaign setup:
27	- Objective (Awareness / Traffic / Engagement / Lead Gen / Conversions / Sales / App Installs)
28	- Budget type (Advantage+ Campaign Budget = CBO, or Ad Set Budget = ABO)
29	- Placements (Automatic vs. manual)
30	- Number of ad sets and ads
31	3. Time period — Date range covered, with any known events (creative refresh, budget change, audience edit, account issue)
32	4. Target metrics — CPA target, ROAS target, or "no target — benchmark me"
33	5. Funnel context (if relevant) — On-platform conversion vs. website event vs. downstream qualification rate
34	6. What's making you ask? — Specific concern ("CPA up 40%"), routine review, or pre-scale audit
35
36	## Phase 1: Identify the Correct Evaluation Level
37
38	This is the most important step. Evaluating at the wrong level is the #1 source of wrong recommendations.
39
40	\| Campaign Setup \| Correct Evaluation Level \| Why \|
41	\|---\|---\|---\|
42	\| Advantage+ Campaign Budget (CBO) \| Campaign level \| System pools budget across ad sets — only campaign totals reflect reality \|
43	\| Automatic placements (no CBO) \| Ad Set level \| System pools budget across placements within the ad set \|
44	\| Multiple ads in 1 ad set \| Ad Set level \| System pools delivery across ads \|
45	\| Manual placements + ABO \| Placement / Ad Set level \| Each is independent \|
46
47	Output for this phase: State the evaluation level explicitly and explain why before any metric is interpreted.
48
49	> If asked "is this Meta placement underperforming?" on a CBO campaign, the answer is "wrong question — at CBO the placement-level CPA is misleading. Here's the campaign total..."
50
51	## Phase 2: Check Learning Phase Status
52
53	Before judging anything, check delivery state per ad set.
54
55	Learning state checklist:
56	- Status is `Learning` (delivery less stable, CPA typically higher, results not predictive)
57	- Exits after ~50 optimization events within 7 days of last significant edit
58	- Shops ads exception: 17 website purchases + 5 Meta purchases
59	- Status `Learning Limited` = can't get enough events → flag as a structural issue, not a performance issue
60
61	Significant edits that reset learning:
62	- Targeting changes
63	- Optimization event change
64	- Creative changes (large)
65	- Bid strategy / amount changes
66	- Budget changes >20%
67
68	Output for this phase: Per ad set, mark `Active` / `Learning` / `Learning Limited`. Caveat all conclusions for anything in learning. Do not recommend pausing a Learning ad set based on CPA alone.
69
70	## Phase 3: Diagnose with Meta-Specific Lenses
71
72	Run the diagnosis through these five lenses. Each one explains a different class of "weird" behavior.
73
74	### 3A: Marginal Efficiency Analysis (Breakdown Effect)
75
76	The Breakdown Effect: the system shifts budget toward segments where the next conversion is cheapest, not where the average conversion is cheapest. A segment can have a high average CPA in a breakdown report and still be the right place for budget.
77
78	How to spot it:
79	- Time-series the segment's CPA. If marginal CPA is rising sharply, expect the system to shift budget out — even if average looks fine.
80	- A breakdown row with high average CPA + high spend usually means the system found ch

gooseworks-aiPublisher · 155 listings

Preview

gooseworks-ai/goose-skills

# Meta Ads Analyzer

Most "Meta Ads analysis" stops at "this CPA is high, pause it." That's wrong more often than it's right. Meta's delivery system optimizes for **marginal efficie

This skill diagnoses Meta campaigns the way a senior media buyer would: at the right evaluation level, accounting for learning state, separating noise from sign

**Core principle:** Holistic first, then drill down. Marginal over average. Dynamic over static. Every recommendation is a testable hypothesis with expected imp

Repogooseworks-ai/goose-skills

LicenseMIT

TypeSkills

CategoryMarketing

UpdatedJul 2026

Repo stars1.0k

First seenJul 22, 2026

People who liked this also viewed

6 picks

Type