Expertise·Marketing, SEO & Social·v1.0.0

Google Ads

Google Ads platform expertise: audit campaigns, keywords, audiences, bidding, and conversion tracking.

You say
Buy it · $29 Read it before you buy $29 Written by thatrebeccarae · unverified publisher
Context cost
17.2k tokensestimated from the bundle, loaded when it triggers
Bundle
6 files · 68.9 kBtext throughout, nothing executable
Licence
MITpaid listing
Last change
v1.0.0
Servers it uses
Noneruns standalone

What it does

Google Ads platform expertise. Audit campaigns, keywords, audiences, bidding, and conversion tracking. Use when the user asks about Google Ads, PPC, search advertising, Performance Max, Shopping ads, display campaigns, YouTube ads, or paid search optimization.

Installed, it changes the agent in these ways.

What this skill changes about the agent is not written down here yet. The listing was collected from its source, and the description is in its own SKILL.md.

Expertise

Domain judgement the base model does not have.

adsppcgoogle-adspaid-media

The skill itself

This is the whole product. A skill is instructions the model reads, so there is nothing behind the listing you cannot see first — the front matter loads with every session, and the body below it loads when the skill triggers.

SKILL.md7.9 kB · 171 lines
--- name: google-ads description: Google Ads platform expertise. Audit campaigns, keywords, audiences, bidding, and conversion tracking. Use when the user asks about Google Ads, PPC, search advertising, Performance Max, Shopping ads, display campaigns, YouTube ads, or paid search optimization. license: MIT origin: custom author: Rebecca Rae Barton author_url: https://github.com/thatrebeccarae metadata: version: 1.0.0 category: paid-media domain: google-ads updated: 2026-03-11 tested: 2026-03-17 tested_with: "Claude Code v2.1" ---
17# Google Ads
18
19Expert-level guidance for Google Ads — auditing, building, and optimizing search, shopping, display, video, Performance Max, and demand gen campaigns.
20
21## Install
22
23```bash
24git clone https://github.com/thatrebeccarae/claude-marketing.git && cp -r claude-marketing/skills/google-ads ~/.claude/skills/
25```
26
27## Core Capabilities
28
29### Campaign Auditing & Optimization
30- Full account audit covering structure, settings, bidding, keywords, ads, and tracking
31- Quality Score optimization (expected CTR, ad relevance, landing page experience)
32- Search term analysis and negative keyword management
33- Budget allocation and pacing optimization
34- Wasted spend identification and elimination
35
36### Campaign Types
37- **Search** — Text ads on Google Search and Search Partners
38- **Shopping** — Product Listing Ads from Google Merchant Center
39- **Performance Max** — AI-driven cross-channel (Search, Shopping, Display, YouTube, Discover, Gmail, Maps)
40- **Display** — Banner/responsive ads across Google Display Network (3M+ sites)
41- **Video** — YouTube ads (in-stream, bumper, discovery, shorts)
42- **Demand Gen** — Visual-first ads on YouTube, Discover, Gmail
43- **App** — App install and engagement campaigns
44
45### Bidding Strategies
46- **Manual CPC / Enhanced CPC** — Direct control, good for learning phases
47- **Target CPA** — Optimize for cost per conversion
48- **Target ROAS** — Optimize for return on ad spend
49- **Maximize Conversions / Maximize Conversion Value** — Spend full budget optimally
50- **Target Impression Share** — Competitive visibility
51- Portfolio bid strategies for cross-campaign optimization
52
53### Audience Strategy
54- First-party data: Customer Match, website visitors, app users
55- Google audiences: In-market, affinity, detailed demographics, life events
56- Custom audiences (by keywords, URLs, apps)
57- Remarketing lists for Search Ads (RLSA)
58- Optimized targeting vs observation mode
59- Audience signals for Performance Max
60
61### Tracking & Measurement
62- Google Tag (gtag.js) / Google Tag Manager implementation
63- Conversion actions: website, phone calls, app, import, store visits
64- Enhanced conversions (first-party data matching)
65- Offline conversion import (GCLID / enhanced conversions for leads)
66- Google Ads Data Hub and GA4 integration
67- Attribution models: data-driven (default), last-click, cross-channel
68
69## Key Benchmarks
70
71| Metric | Good | Great | Warning |
72|--------|------|-------|---------|
73| Search CTR | 4-6% | 8%+ | <3% |
74| Search CPC | Industry dependent | Below industry avg | Rising trend |
75| Search Conv Rate | 3-5% | 7%+ | <2% |
76| Quality Score | 7-8 | 9-10 | <6 |
77| Impression Share (Brand) | 90%+ | 95%+ | <80% |
78| Impression Share (Non-Brand) | 40-60% | 70%+ | <30% |
79| PMax ROAS | 3-4x | 6x+ | <2x |
80| Display CTR | 0.5-1% | 1.5%+ | <0.3% |
81| YouTube View Rate | 15-25% | 30%+ | <10% |
82
83## Account Structure Best Practices
84
85```
86Account
87├── Brand Search (Exact + Phrase match)
88│ ├── Pure Brand
89│ └── Brand + Product/Service modifiers
90├── Non-Brand Search (by theme/intent)
91│ ├── High-Intent / Bottom-Funnel keywords
92│ ├── Mid-Funnel / Consideration keywords
93│ └── Category / Broad keywords
94├── Competitor Search (optional)
95│ └── Competitor brand terms
96├── Shopping (Standard)
97│ ├── Top Performers (high priority)
98│ ├── Category groups (medium priority)
99│ └── Catch-All (low priority)
100├── Performance Max
101│ ├── Asset Groups by product category or audience theme
102│ └── Audience signals per group
103├── Display (if separate from PMax)
104│ ├── Remarketing
105│ └── Prospecting (in-market / custom)
106├── YouTube / Video
107│ ├── Brand awareness (bumper, in-stream)
108│ └── Action / conversions (in-feed, in-stream)
109└── Demand Gen
110 └── Visual-first prospecting
111```
112
113## Workflow: Full Account Audit
114
115When asked to audit a Google Ads account:
116
1171. **Conversion Tracking** — Verify Google Tag, conversion actions, enhanced conversions, attribution model
1182. **Account Structure** — Campaign organization, naming conventions, settings consistency
1193. **Budget & Bidding** — Allocation across campaigns, bid strategy alignment with goals, target efficiency
1204. **Keyword Strategy** — Match types, Quality Scores, search term relevance, negative keyword lists
1215. **Ad Copy** — RSA asset quality (headlines, descriptions), pin usage, ad strength, extensions
1226. **Shopping / Merchant Center** — Feed quality, disapprovals, competitive metrics, listing groups
1237. **Performance Max** — Asset group quality, audience signals, URL expansion settings, cannibalizing Search
1248. **Audiences** — First-party lists, remarketing, Customer Match, observation vs targeting
1259. **Landing Pages** — Load speed, message match, conversion rate by landing page
12610. **Competitive Landscape** — Auction insights, impression share losses (budget vs rank)
12711. **Recommendations** — Prioritized by expected revenue impact with effort estimate
128
129## Performance Max Guidance
130
131PMax-specific audit checklist:
132- Asset group organization (themes, not catch-all)
133- All asset types provided (text, image, video, logo)
134- Audience signals configured (not left empty)
135- URL expansion settings reviewed (exclude irrelevant pages)
136- Search themes added for intent signals
137- Brand exclusions applied
138- Not cannibalizing high-performing standard Shopping/Search campaigns
139- Conversion goals aligned (avoid mixing lead gen and ecommerce)
140
141## How to Use This Skill
142
143Ask me questions like:
144- "Audit my Google Ads account and find wasted spend"
145- "My Quality Scores are low — help me diagnose and fix"
146- "Design a Performance Max campaign structure for my ecommerce store"
147- "Should I use Target CPA or Target ROAS?"
148- "Help me build a negative keyword strategy"
149- "My CPA is increasing — what should I investigate?"
150- "Plan a YouTube advertising strategy for brand awareness"
151- "Review my Google Merchant Center feed for issues"
152
153For detailed Google Ads API reference, script templates, and advanced configurations, see [REFERENCE.md](REFERENCE.md).
154
155## Hard Rules
156
157These constraints must never be violated in recommendations:
158
1591. **Never recommend Broad Match without Smart Bidding.** Broad Match + Manual CPC = uncontrolled spend.
1602. **3x Kill Rule:** Flag any campaign/ad group with CPA >3x target for immediate pause or restructuring.
1613. **Enhanced Conversions must be recommended** if not already active. Foundation for data quality.
1624. **Consent Mode v2 required** for any account serving EU/EEA traffic.
1635. **Negative keyword lists required** — minimum 3 themed lists (Competitor, Jobs, Free, Irrelevant).
1646. **Never recommend edits during active learning phase** — wait for learning to complete or reset intentionally.
1657. **Brand and non-brand must be separated** into distinct campaigns with independent budgets and bidding.
1668. **PMax must have brand exclusions** when a brand Search campaign exists.
167
168## Scored Audit
169
170When performing an account audit, load skills/shared/scoring-system.md for the weighted scoring algorithm and CHECKS.md for the 74-check Google Ads audit checklist. Produce a health score (0-100, grade A-F) with Quick Wins and a prioritized action plan.
171
In the file
SKILL.md1,119 words
Files6
LicenceMIT
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈140
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
17,085
on trigger
The instruction body and 5 supporting files, read only when the skill fires.
8.6%
of a 200k window
Ten skills this size would take about 86% of the window before you open a file.
050k100k150k200k context window

17.2k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

Adoption
Installsnone yet
Ratingno reviews yet

The procedure it runs

The procedure has not been published here. It is in the skill’s own SKILL.md, which its author has not sent to the marketplace yet.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

It writes no files and reaches no network. All it changes is how the model reasons and writes.

What it asks for
Writes filesno
Network accessno

Read from the allowed-tools line of this skill’s own SKILL.md. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

6 files, 68.9 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

  • .env.example1.2 kB
  • CHECKS.md23.8 kB
  • EXAMPLES.md24.5 kB
  • REFERENCE.md11.4 kB
  • SKILL.md7.9 kB
  • requirements.txt0.1 kB
What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 6 files you can review in full before installing. The MIT licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

$29 once
Google Ads · MIT · thatrebeccarae
one-time
Price$29 once
LicenceMIT — the author’s, unchanged by this purchase
Paid throughStripe, once, on the card you add at the checkout
Keeps workingfor good — the files are yours once they are on disk
Updatesevery release of 1.x through this account

You can read the whole bundle before paying — the SKILL.md above is the product, not a preview of it. What the money buys is the delivery: the folder packaged and handed to your machine by key, every update its author ships, and our support if it does not do what this listing says. The terms of use are MIT, set by the author and unchanged by buying it here.

Payment runs through Stripe, on a page like this one rather than a redirect. Once there is an account it joins the same mcprush invoice as everything else you run, so there is never a second card to enter.

Which clients pick it up on their own

A skill is a folder of text. A client with a skills folder reads it without being told; everywhere else the same text works, it is just handed to the model rather than found.

Claude Code.claude/skills/
Claude Desktop
ChatGPT
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok.grok/skills/
Zed.agents/skills/
Windsurf.windsurf/skills/
Agent SDK.claude/skills/
HTTP / API
This release
Version1.0.0
Publishedno release date on file
Price$29
Referencethatrebeccarae/google-ads

Versions

v1.0.0 is what is on the shelf; no release here carries a date. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v1.0.0
  • No earlier releases have been published to the marketplace.
Pinning

Put thatrebeccarae/google-ads@1.0.0 in the install command to hold this exact version. Without the suffix you get whatever is current the day you install, and nothing moves under you afterwards.

Reviews

no reviews yet · no installs yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Who can post

Only accounts that have had the skill installed for fourteen days, so a review is written after living with it rather than after reading it. Publishers may reply once.

Who wrote it

TH
thatrebeccarae

Publishes on mcprush.

0 servers listed2 skills listednot claimed
Profile
Publisher
Servers0