mcpbeat Sign in

Geo Performance Analysis Agent Skill

Breaks down campaign performance by geographic location at whatever level matters — country, state, city, DMA, zip code. Flags underperforming geos that are quietly eating budget and high-performing ones that deserve more spend. Recommends geo bid adjustments or campaign splits. Platform: Google and Meta.

723 tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
1221
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/irinabuht12-oss/marketing-skills --skill geo-performance-analysis

The instruction itself

7 sections, as written by the author

24/ Geo Performance Analysis — Google + Meta

What it does

Breaks down campaign performance by geographic location at whatever level matters — country, state, city, DMA, zip code. Flags underperforming geos that are quietly eating budget and high-performing ones that deserve more spend. Recommends geo bid adjustments or campaign splits.

How it works

Claude analyzes your performance data segmented by location, identifies statistically significant performance differences (not just noise from low-volume areas), and calculates the cost of running campaigns in underperforming regions vs the conversions you'd lose by excluding or reducing them.

Practical example

Your national ecommerce campaigns spend evenly across the US. Claude finds that 8 states produce 65% of your conversions at a $24 CPA, while 12 states spend $8,400/month combined with a $71 CPA and only 118 conversions. Three metro areas — Dallas, Phoenix, and Atlanta — outperform their state averages by 40%+ and could absorb more budget. Recommendation: reduce bids 40% in the 12 underperforming states, increase 25% in the top 8, and create separate campaigns for the 3 outperforming metros to give them dedicated budgets.

What you get back

  • Performance breakdown by geo level with CPA, ROAS, CVR, and volume
  • Tier ranking of geos (top performers, average, underperformers) with clear thresholds
  • Bid adjustment recommendations by geo with projected impact
  • Campaign split recommendations for high-volume geos that deserve independent management
  • Spend reallocation model showing how redistributing from weak to strong geos affects total conversions

When to use it

  • When running national or multi-market campaigns and need to optimize allocation
  • After expanding into new regions to evaluate early performance
  • Quarterly to catch geo performance shifts as market conditions change
  • When clients ask "where should we focus" and you need data behind the recommendation

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

How to use it

Copy the folder

Take irinabuht12-oss/geo-performance-analysis from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.