Analyze paid advertising performance across channels

Ad spend optimizer

by guia-matthieu · MIT license · ★ 151 on GitHub

Analyze paid advertising performance across channels and recommend budget reallocation to maximize ROAS and minimize CAC. Use when: planning quarterly ad budget allocation, diagnosing underperforming ad channels, deciding whether to…

---
name: ad-spend-optimizer
description: "Analyze paid advertising performance across channels and recommend budget reallocation to maximize ROAS and minimize CAC. Use when: planning quarterly ad budget allocation, diagnosing underperforming ad channels, deciding whether to scale spend on a channel, calculating marginal ROI across Google Ads, Meta, LinkedIn, or TikTok, rebalancing media mix after performance shifts, or setting up a test-and-scale framework for new channels."
license: MIT
metadata:
  author: ClawFu
  version: 1.1.0
  mcp-server: "@clawfu/mcp-skills"
---

# Ad Spend Optimizer

> Analyze paid advertising performance across channels and recommend budget reallocation to maximize ROAS and minimize CAC.

## When to Use This Skill

- **Quarterly budget planning** — reallocate spend based on performance data
- **Channel mix optimization** — find the right balance across platforms

Overview

Validation checkpoint: If data is missing for any channel, flag it — incomplete data leads to wrong reallocations.

What you get

Analyzing multi-channel ad performance from provided data
Recommending budget shifts based on marginal ROI
Modeling reallocation scenarios with projected outcomes
Creating monitoring frameworks with alert thresholds

Manual install (npx, ZIP)

Claude Codenpx skills add guia-matthieu/clawfu-skills --skill ad-spend-optimizer -g -a claude-code

Claude Code (degit)npx degit guia-matthieu/clawfu-skills/skills/acquisition/ad-spend-optimizer#main ~/.claude/skills/ad-spend-optimizer

Claude.ai / desktopZip the folder and upload it under Settings → Capabilities → Skills.

Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

SKILL.md5.9 KB

Read SKILL.md here

guia-matthieu/main1 file shown

SKILL.md5.9 KB

Browse every file on GitHub↗

SKILL.md

Show the full text147 lines

ad-spend-optimizer/SKILL.md147 lines · 5.9 KB

PreviewCode

Outline

RawView on GitHub

Ad Spend Optimizer

Analyze paid advertising performance across channels and recommend budget reallocation to maximize ROAS and minimize CAC.

When to Use This Skill

Quarterly budget planning — reallocate spend based on performance data
Channel mix optimization — find the right balance across platforms
Performance troubleshooting — diagnose why CAC is rising or ROAS declining
Scaling decisions — determine if a channel has headroom to scale
New channel testing — structure test budgets with clear success criteria

Methodology Foundation

Aspect	Details
Source	Marginal ROI optimization + portfolio theory for marketing
Core Principle	Allocate each dollar where the marginal return is highest — shift spend from diminishing-returns channels to underspent ones
Framework	70/20/10 — 70% proven channels, 20% optimization tests, 10% new channel experiments

What Claude Does vs What You Decide

Claude Does	You Decide
Calculates ROAS, CAC, and CPL per channel and campaign	Total budget constraints
Identifies diminishing returns and reallocation opportunities	Risk tolerance for new channels
Models projected outcomes for different allocation scenarios	Business priorities and brand considerations
Creates monitoring dashboards and alert thresholds	Platform selection and creative direction

Instructions

Step 1: Audit Current Performance

Collect these metrics per channel and campaign:

Metric	Formula	Healthy Range
ROAS	Revenue ÷ Ad Spend	>3:1 for most B2B/B2C
CAC	Ad Spend ÷ New Customers	<LTV ÷ 3
CPL	Ad Spend ÷ Leads	Varies by industry
CTR	Clicks ÷ Impressions	>1% search, >0.5% social
Conv Rate	Conversions ÷ Clicks	>2% landing pages

Validation checkpoint: If data is missing for any channel, flag it — incomplete data leads to wrong reallocations.

Step 2: Attribution Analysis

Choose the model that matches the business:

Model	Best For	Trade-off
Last Click	Direct response, short cycles	Ignores awareness
First Click	Awareness campaigns	Ignores conversion assist
Linear	Balanced multi-touch view	Dilutes signal
Time Decay	Shorter sales cycles	Biases toward bottom-funnel
Position-Based	Balanced with emphasis	May miss mid-funnel
Data-Driven	Sophisticated, enough data	Requires volume

Step 3: Calculate Marginal ROI

For each channel, answer: Where does the next $1 produce the most return?

Signal	Meaning	Action
CAC well below target	Headroom to scale	Increase spend 50%, monitor weekly
CAC at target	Optimized	Maintain, test creative
CAC above target	Diminishing returns	Reduce spend, reallocate
Low volume, good CAC	Underinvested	Scale cautiously (2x)
High volume, rising CAC	Hitting ceiling	Cap spend, diversify

Step 4: Model Reallocation Scenarios

Build 3 scenarios (conservative, moderate, aggressive) showing projected leads, CAC, and ROAS at each budget level. Include:

Per-channel breakdowns with expected performance
Warning thresholds — CAC levels that trigger spend cuts
Implementation timeline — weekly changes, not all at once

Step 5: Implement and Monitor

Weekly monitoring checklist:

Spend pacing vs. plan
CAC by channel vs. target
Lead volume vs. forecast
Any channel crossing warning threshold?

Scaling rule: If CAC stays 15%+ below target for 2 consecutive weeks, increase spend by 25%. If CAC exceeds target for 2 weeks, reduce by 25%.

Examples

Example: B2B SaaS Budget Reallocation

Input: $100K/month — Google ($50K), Meta ($30K), LinkedIn ($15K), Other ($5K). Target: $200 CAC, 500 leads/month. Current: 395 leads, $253 CAC.

Diagnosis:

Google Display ($15K → 30 leads, $500 CAC) — cut entirely
Meta Lookalike ($15K → 85 leads, $176 CAC) — star performer, scale
LinkedIn Lead Gen ($5K → 10 leads, $500 CAC) — cut

Proposed reallocation:

Channel	Current	Proposed	Expected CAC
Google Ads	$50K	$35K	$206
Meta	$30K	$50K	$196
LinkedIn	$15K	$8K	$286
Testing	$5K	$7K	Variable

Projected result: 473 leads (+20%), $211 CAC (-17%).

Skill Boundaries

What This Skill Does Well

Analyzing multi-channel ad performance from provided data
Recommending budget shifts based on marginal ROI
Modeling reallocation scenarios with projected outcomes
Creating monitoring frameworks with alert thresholds

What This Skill Cannot Do

Access ad platform accounts or pull live data
Make real-time bid adjustments or campaign changes
Evaluate creative quality (headlines, images, video)
Account for brand lift or offline conversion effects

References

Google Ads Optimization Guide
Meta Business Suite Best Practices
LinkedIn Marketing Solutions
Common Thread Collective — ad spend allocation methodology

google-ads-expert — Google-specific campaign optimization
aarrr-metrics — Full funnel view beyond paid acquisition
growth-loops — Sustainable growth beyond paid channels

1	---
2	name: ad-spend-optimizer
3	description: "Analyze paid advertising performance across channels and recommend budget reallocation to maximize ROAS and minimize CAC. Use when: planning quarterly ad budget allocation, diagnosing underperforming ad channels, deciding whether to scale spend on a channel, calculating marginal ROI across Google Ads, Meta, LinkedIn, or TikTok, rebalancing media mix after performance shifts, or setting up a test-and-scale framework for new channels."
4	license: MIT
5	metadata:
6	author: ClawFu
7	version: 1.1.0
8	mcp-server: "@clawfu/mcp-skills"
9	---
10
11	# Ad Spend Optimizer
12
13	> Analyze paid advertising performance across channels and recommend budget reallocation to maximize ROAS and minimize CAC.
14
15	## When to Use This Skill
16
17	- Quarterly budget planning — reallocate spend based on performance data
18	- Channel mix optimization — find the right balance across platforms
19	- Performance troubleshooting — diagnose why CAC is rising or ROAS declining
20	- Scaling decisions — determine if a channel has headroom to scale
21	- New channel testing — structure test budgets with clear success criteria
22
23	## Methodology Foundation
24
25	\| Aspect \| Details \|
26	\|--------\|---------\|
27	\| Source \| Marginal ROI optimization + portfolio theory for marketing \|
28	\| Core Principle \| Allocate each dollar where the marginal return is highest — shift spend from diminishing-returns channels to underspent ones \|
29	\| Framework \| 70/20/10 — 70% proven channels, 20% optimization tests, 10% new channel experiments \|
30
31	## What Claude Does vs What You Decide
32
33	\| Claude Does \| You Decide \|
34	\|-------------\|------------\|
35	\| Calculates ROAS, CAC, and CPL per channel and campaign \| Total budget constraints \|
36	\| Identifies diminishing returns and reallocation opportunities \| Risk tolerance for new channels \|
37	\| Models projected outcomes for different allocation scenarios \| Business priorities and brand considerations \|
38	\| Creates monitoring dashboards and alert thresholds \| Platform selection and creative direction \|
39
40	## Instructions
41
42	### Step 1: Audit Current Performance
43
44	Collect these metrics per channel and campaign:
45
46	\| Metric \| Formula \| Healthy Range \|
47	\|--------\|---------\|---------------\|
48	\| ROAS \| Revenue ÷ Ad Spend \| >3:1 for most B2B/B2C \|
49	\| CAC \| Ad Spend ÷ New Customers \| <LTV ÷ 3 \|
50	\| CPL \| Ad Spend ÷ Leads \| Varies by industry \|
51	\| CTR \| Clicks ÷ Impressions \| >1% search, >0.5% social \|
52	\| Conv Rate \| Conversions ÷ Clicks \| >2% landing pages \|
53
54	Validation checkpoint: If data is missing for any channel, flag it — incomplete data leads to wrong reallocations.
55
56	### Step 2: Attribution Analysis
57
58	Choose the model that matches the business:
59
60	\| Model \| Best For \| Trade-off \|
61	\|-------\|----------\|-----------\|
62	\| Last Click \| Direct response, short cycles \| Ignores awareness \|
63	\| First Click \| Awareness campaigns \| Ignores conversion assist \|
64	\| Linear \| Balanced multi-touch view \| Dilutes signal \|
65	\| Time Decay \| Shorter sales cycles \| Biases toward bottom-funnel \|
66	\| Position-Based \| Balanced with emphasis \| May miss mid-funnel \|
67	\| Data-Driven \| Sophisticated, enough data \| Requires volume \|
68
69	### Step 3: Calculate Marginal ROI
70
71	For each channel, answer: Where does the next $1 produce the most return?
72
73	\| Signal \| Meaning \| Action \|
74	\|--------\|---------\|--------\|
75	\| CAC well below target \| Headroom to scale \| Increase spend 50%, monitor weekly \|
76	\| CAC at target \| Optimized \| Maintain, test creative \|
77	\| CAC above target \| Diminishing returns \| Reduce spend, reallocate \|
78	\| Low volume, good CAC \| Underinvested \| Scale cautiously (2x) \|
79	\| High volume, rising CAC \| Hitting ceiling \| Cap spend, diversify \|
80
81	### Step 4: Model Reallocation Scenarios
82
83	Build 3 scenarios (conservative, moderate, aggressive) showing projected leads, CAC, and ROAS at each budget level. Include:
84
85	- Per-channel breakdowns with expected performance
86	- Warning thresholds — CAC levels that trigger spend cuts
87	- Implementation timeline — weekly changes, not all at once
88
89	### Step 5: Implement and Monitor
90
91	Weekly monitoring checklist:
92	- [ ] Spend pacing vs. plan
93	- [ ] CAC by channel vs. target
94	- [ ] Lead volume vs. forecast
95	- [ ] Any channel crossing warning threshold?
96
97	Scaling rule: If CAC stays 15%+ below target for 2 consecutive weeks, increase spend by 25%. If CAC exceeds target for 2 weeks, reduce by 25%.
98
99	## Examples
100
101	### Example: B2B SaaS Budget Reallocation
102
103	Input: $100K/month — Google ($50K), Meta ($30K), LinkedIn ($15K), Other ($5K). Target: $200 CAC, 500 leads/month. Current: 395 leads, $253 CAC.
104
105	Diagnosis:
106	- Google Display ($15K → 30 leads, $500 CAC) — cut entirely
107	- Meta Lookalike ($15K → 85 leads, $176 CAC) — star performer, scale
108	- LinkedIn Lead Gen ($5K → 10 leads, $500 CAC) — cut
109
110	Proposed reallocation:
111
112	\| Channel \| Current \| Proposed \| Expected CAC \|
113	\|---------\|---------\|----------\|-------------\|
114	\| Google Ads \| $50K \| $35K \| $206 \|
115	\| Meta \| $30K \| $50K \| $196 \|
116	\| LinkedIn \| $15K \| $8K \| $286 \|
117	\| Testing \| $5K \| $7K \| Variable \|
118
119	Projected result: 473 leads (+20%), $211 CAC (-17%).
120
121	## Skill Boundaries
122
123	### What This Skill Does Well
124	- Analyzing multi-channel ad performance from provided data
125	- Recommending budget shifts based on marginal ROI
126	- Modeling reallocation scenarios with projected outcomes
127	- Creating monitoring frameworks with alert thresholds
128
129	### What This Skill Cannot Do
130	- Access ad platform accounts or pull live data
131	- Make real-time bid adjustments or campaign changes
132	- Evaluate creative quality (headlines, images, video)
133	- Account for brand lift or offline conversion effects
134
135	## References
136
137	- Google Ads Optimization Guide
138	- Meta Business Suite Best Practices
139	- LinkedIn Marketing Solutions
140	- Common Thread Collective — ad spend allocation methodology
141
142	## Related Skills
143
144	- `google-ads-expert` — Google-specific campaign optimization
145	- `aarrr-metrics` — Full funnel view beyond paid acquisition
146	- `growth-loops` — Sustainable growth beyond paid channels
147