Evaluates your campaign and ad set structure against your actual goals and budget. Flags over-segmentation that fragments your data, under-segmentation that hides performance differences, budget allocation issues, and consolidation opportunities that would improve algorithmic delivery and your ability to optimize. Platform: Google and Meta.
git clone https://github.com/irinabuht12-oss/marketing-skills.git--- name: account-structure-review description: Evaluates your campaign and ad set structure against your actual goals and budget. Flags over-segmentation that fragments your data, under-segmentation that hides performance differences, budget allocation issues, and consolidation opportunities that would improve algorithmic delivery and your ability to optimize. Platform: Google and Meta. metadata: platform: Google and Meta --- # 17/ Account Structure Review — Google + Meta ## What it does Evaluates your campaign and ad set structure against your actual goals and budget. Flags over-segmentation that fragments your data, under-segmentation that hides performance differences, budget allocation issues, and consolidation opportunities that would improve algorithmic delivery and your ability to optimize. ## How it works Claude maps your entire account structure — campaigns, ad sets/ad groups, targeting, budgets, and bid strategies — and evaluates it against best practices for your specific situation. It considers conversion volume per campaign (enough for algorithms to learn), budget distribution (too many campaigns splitting too little budget), targeting overlap, and whether your structure supports clean testing and reporting. ## Practical example Your Google Ads account has 34 search campaigns. Claude finds that 19 of them have fewer than 10 conversions per month — not enough for automated bidding to work. Twelve campaigns have daily budgets under $15, meaning they run out by noon. Three campaigns target nearly identical keyword sets in different geographies but could be consolidated with geo bid adjustments. Recommendation: consolidate down to 14 campaigns, which would give each campaign 25+ monthly conversions and $40+ daily budgets while maintaining clean reporting segments. ## What you get back - Full account structure map with performance metrics at each level - Campaigns flagged for insufficient conversion volume, budget fragmentation, or targeting overlap - Specific consolidation recommendations with projected performance impact - Recommended structure with campaign/ad group grouping logic explained - Migration plan showing how to consolidate without losing historical data or disrupting active campaigns ## When to use it - When inheriting a new account from a previous team or agency - Quarterly account health checks - When performance plateaus and structural issues might be holding back algorithms - Before scaling, because a messy structure at $20K/month becomes a disaster at $100K/month ## Data access (Ryze MCP) This skill works best with live account data. Connect the free Ryze MCP once and Claude reads your Google Ads, Meta Ads, GA4 and Search Console directly: - claude.ai / Claude Desktop: Settings → Connectors → Add custom connector → `https://connector.get-ryze.ai/mcp` - Claude Code: `claude mcp add ryze --transport http https://connector.get-ryze.ai/mcp` - Cursor: Settings → MCP → add the same URL Setup guide: https://www.get-ryze.ai/how-to-connect-claude-to-google-meta-ads-mcp
1. **Gather Data**: Export performance metrics (CPA, ROAS, CTR, spend) for the last 30-90 days from [PLATFORM] Ads Manager. Include audience, device, placement, and creative breakdowns. 2. **Define Goals**: Input your primary KPIs (e.g., CPA <$30, ROAS >3.0) and performance thresholds (e.g., CPA >$50 = underperforming) into the prompt template. 3. **Run Analysis**: Paste the prompt into your AI tool (e.g., Claude, ChatGPT) and review the output. Use the 'Revised Structure Table' to map current vs. proposed ad sets. 4. **Implement Changes**: Apply recommendations in your Ads Manager: merge ad sets, reallocate budgets, and set up DCO or consolidation tests. Monitor performance for 2-4 weeks. 5. **Iterate**: Re-run the analysis monthly to adjust for seasonality or shifts in audience behavior. Use A/B tests to validate consolidation or segmentation changes.
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/irinabuht12-oss/marketing-skills/tree/main/skills/account-structure-reviewCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Review the account structure for [PLATFORM: Google Ads or Meta Ads] campaign [CAMPAIGN_NAME]. Analyze the current ad set segmentation, budget allocation, and performance data to identify: (1) Over-segmentation that fragments data and limits learnings, (2) Under-segmentation that masks performance differences between audiences/products, (3) Budget allocation inefficiencies (e.g., over/under-spending on high/low-performing segments), and (4) Consolidation opportunities to improve algorithmic delivery and optimization. Provide specific recommendations for restructuring, including suggested ad set consolidation, budget reallocation, and testing priorities. Use [PERFORMANCE_THRESHOLDS] (e.g., CPA >$50, ROAS <2.0) to prioritize changes. Include a revised structure table if applicable.
For the 'Q3 Product Launch' Meta Ads campaign (Budget: $15,000/month), the current structure includes 12 ad sets split by audience (New vs. Returning), device type (Mobile vs. Desktop), and placement (Feed vs. Stories). Performance data shows: - **Over-segmentation**: Ad sets targeting 'Mobile Feed New Users' (CPA: $45) and 'Mobile Stories New Users' (CPA: $48) perform similarly but are split, fragmenting data. Combined, they’d have a 30% larger audience for the algorithm to optimize. - **Under-segmentation**: 'Desktop Feed Returning Users' (CPA: $32) and 'Mobile Feed Returning Users' (CPA: $35) are grouped together, masking a 9% CPA difference. Splitting them would reveal higher intent on desktop. - **Budget Inefficiency**: 'Lookalike 10% Audience' (CPA: $65) receives 40% of the budget despite underperforming vs. 'Engaged Shoppers' (CPA: $28, 25% budget). Reallocating $4,000 to 'Engaged Shoppers' would improve ROAS. - **Consolidation Opportunity**: 'Mobile Feed New Users' and 'Mobile Stories New Users' could merge into one ad set with dynamic creative optimization (DCO) to simplify management and improve delivery. **Recommended Restructure**: 1. Consolidate 4 ad sets into 2 (Mobile Feed New vs. Returning Users). 2. Increase budget for 'Engaged Shoppers' to $5,000/month (CPA: $28). 3. Pause 'Lookalike 10% Audience' (CPA: $65) and reallocate funds to testing a 5% lookalike audience. 4. Implement DCO for mobile placements to reduce ad set count by 30%.
skills-collection
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan