Agent skill
google-ads
Google Ads platform expertise.
Filed under ABM and paid.
From thatrebeccarae/claude-marketing · 42 skills · 119 · pushed 2026-05-14
What it does when it runs
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.
Read from the skill and the 6 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.
- Keys and connectors you must supply
- GOOGLE_ADS_DEVELOPER_TOKEN
- GOOGLE_APPLICATION_CREDENTIALS
- Hosts it reaches
- developers.google.com
- googleads.googleapis.com
- www.googletagmanager.com
- Tool permissions it declares
- No
allowed-toolsin the frontmatter. It does act, so it runs under whatever permissions your session already grants. - Actions present in the files
- shell
Install it
View source on GitHub ↗git clone --depth 1 --filter=blob:none --sparse https://github.com/thatrebeccarae/claude-marketing.git /tmp/claude-marketing git -C /tmp/claude-marketing sparse-checkout set "skills/google-ads" mkdir -p ~/.claude/skills/google-ads cp -R "/tmp/claude-marketing/skills/google-ads/." ~/.claude/skills/google-ads/
Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗
The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.
Before you install: this skill will not complete its job on a bare agent. It needs GOOGLE_ADS_DEVELOPER_TOKEN, GOOGLE_APPLICATION_CREDENTIALS, which you have to obtain separately.
The skill
Source on GitHub ↗Reproduced in full from thatrebeccarae/claude-marketing/blob/a8a63ec1341f05ec9c1e9cb52b4edeb14e3bdcba/skills/google-ads/SKILL.md, which is licensed MIT (skill frontmatter). 1,054 words, 15 headings.
Google Ads
Expert-level guidance for Google Ads — auditing, building, and optimizing search, shopping, display, video, Performance Max, and demand gen campaigns.
Install
git clone https://github.com/thatrebeccarae/claude-marketing.git && cp -r claude-marketing/skills/google-ads ~/.claude/skills/
Core Capabilities
Campaign Auditing & Optimization
- Full account audit covering structure, settings, bidding, keywords, ads, and tracking
- Quality Score optimization (expected CTR, ad relevance, landing page experience)
- Search term analysis and negative keyword management
- Budget allocation and pacing optimization
- Wasted spend identification and elimination
Campaign Types
- Search — Text ads on Google Search and Search Partners
- Shopping — Product Listing Ads from Google Merchant Center
- Performance Max — AI-driven cross-channel (Search, Shopping, Display, YouTube, Discover, Gmail, Maps)
- Display — Banner/responsive ads across Google Display Network (3M+ sites)
- Video — YouTube ads (in-stream, bumper, discovery, shorts)
- Demand Gen — Visual-first ads on YouTube, Discover, Gmail
- App — App install and engagement campaigns
Bidding Strategies
- Manual CPC / Enhanced CPC — Direct control, good for learning phases
- Target CPA — Optimize for cost per conversion
- Target ROAS — Optimize for return on ad spend
- Maximize Conversions / Maximize Conversion Value — Spend full budget optimally
- Target Impression Share — Competitive visibility
- Portfolio bid strategies for cross-campaign optimization
Audience Strategy
- First-party data: Customer Match, website visitors, app users
- Google audiences: In-market, affinity, detailed demographics, life events
- Custom audiences (by keywords, URLs, apps)
- Remarketing lists for Search Ads (RLSA)
- Optimized targeting vs observation mode
- Audience signals for Performance Max
Tracking & Measurement
- Google Tag (gtag.js) / Google Tag Manager implementation
- Conversion actions: website, phone calls, app, import, store visits
- Enhanced conversions (first-party data matching)
- Offline conversion import (GCLID / enhanced conversions for leads)
- Google Ads Data Hub and GA4 integration
- Attribution models: data-driven (default), last-click, cross-channel
Key Benchmarks
| Metric | Good | Great | Warning |
|---|---|---|---|
| Search CTR | 4-6% | 8%+ | <3% |
| Search CPC | Industry dependent | Below industry avg | Rising trend |
| Search Conv Rate | 3-5% | 7%+ | <2% |
| Quality Score | 7-8 | 9-10 | <6 |
| Impression Share (Brand) | 90%+ | 95%+ | <80% |
| Impression Share (Non-Brand) | 40-60% | 70%+ | <30% |
| PMax ROAS | 3-4x | 6x+ | <2x |
| Display CTR | 0.5-1% | 1.5%+ | <0.3% |
| YouTube View Rate | 15-25% | 30%+ | <10% |
Account Structure Best Practices
Account
├── Brand Search (Exact + Phrase match)
│ ├── Pure Brand
│ └── Brand + Product/Service modifiers
├── Non-Brand Search (by theme/intent)
│ ├── High-Intent / Bottom-Funnel keywords
│ ├── Mid-Funnel / Consideration keywords
│ └── Category / Broad keywords
├── Competitor Search (optional)
│ └── Competitor brand terms
├── Shopping (Standard)
│ ├── Top Performers (high priority)
│ ├── Category groups (medium priority)
│ └── Catch-All (low priority)
├── Performance Max
│ ├── Asset Groups by product category or audience theme
│ └── Audience signals per group
├── Display (if separate from PMax)
│ ├── Remarketing
│ └── Prospecting (in-market / custom)
├── YouTube / Video
│ ├── Brand awareness (bumper, in-stream)
│ └── Action / conversions (in-feed, in-stream)
└── Demand Gen
└── Visual-first prospecting
Workflow: Full Account Audit
When asked to audit a Google Ads account:
- Conversion Tracking — Verify Google Tag, conversion actions, enhanced conversions, attribution model
- Account Structure — Campaign organization, naming conventions, settings consistency
- Budget & Bidding — Allocation across campaigns, bid strategy alignment with goals, target efficiency
- Keyword Strategy — Match types, Quality Scores, search term relevance, negative keyword lists
- Ad Copy — RSA asset quality (headlines, descriptions), pin usage, ad strength, extensions
- Shopping / Merchant Center — Feed quality, disapprovals, competitive metrics, listing groups
- Performance Max — Asset group quality, audience signals, URL expansion settings, cannibalizing Search
- Audiences — First-party lists, remarketing, Customer Match, observation vs targeting
- Landing Pages — Load speed, message match, conversion rate by landing page
- Competitive Landscape — Auction insights, impression share losses (budget vs rank)
- Recommendations — Prioritized by expected revenue impact with effort estimate
Performance Max Guidance
PMax-specific audit checklist:
- Asset group organization (themes, not catch-all)
- All asset types provided (text, image, video, logo)
- Audience signals configured (not left empty)
- URL expansion settings reviewed (exclude irrelevant pages)
- Search themes added for intent signals
- Brand exclusions applied
- Not cannibalizing high-performing standard Shopping/Search campaigns
- Conversion goals aligned (avoid mixing lead gen and ecommerce)
How to Use This Skill
Ask me questions like:
- "Audit my Google Ads account and find wasted spend"
- "My Quality Scores are low — help me diagnose and fix"
- "Design a Performance Max campaign structure for my ecommerce store"
- "Should I use Target CPA or Target ROAS?"
- "Help me build a negative keyword strategy"
- "My CPA is increasing — what should I investigate?"
- "Plan a YouTube advertising strategy for brand awareness"
- "Review my Google Merchant Center feed for issues"
For detailed Google Ads API reference, script templates, and advanced configurations, see REFERENCE.md.
Hard Rules
These constraints must never be violated in recommendations:
- Never recommend Broad Match without Smart Bidding. Broad Match + Manual CPC = uncontrolled spend.
- 3x Kill Rule: Flag any campaign/ad group with CPA >3x target for immediate pause or restructuring.
- Enhanced Conversions must be recommended if not already active. Foundation for data quality.
- Consent Mode v2 required for any account serving EU/EEA traffic.
- Negative keyword lists required — minimum 3 themed lists (Competitor, Jobs, Free, Irrelevant).
- Never recommend edits during active learning phase — wait for learning to complete or reset intentionally.
- Brand and non-brand must be separated into distinct campaigns with independent budgets and bidding.
- PMax must have brand exclusions when a brand Search campaign exists.
Scored Audit
When 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.
Files bundled with it
These load only when the skill asks for them, so they cost nothing until it runs.
Other skills for the same job
Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.
- google-ads by OpenClaudia · 664
- google-ads-report by OpenClaudia · 664
- google-search-ads-builder by edupegoretti · 0
- ads by coreyhaines31 · 45,947
- facebook-ads by OpenClaudia · 664
- google-analytics by OpenClaudia · 664
- google-reviews by OpenClaudia · 664
- linkedin-ads by OpenClaudia · 664
Need help setting it up?
This page tells you what google-ads does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.
Book a call →The directory stays free. There is nothing gated behind this.