mcpbeat Sign in

Conversion Path Analysis Agent Skill

Maps out how users move through your funnel from first ad click to conversion. Identifies where the biggest drop-offs happen, which campaigns contribute most at each stage, and how long the typical conversion path takes across different audience segments. Platform: Google and Meta.

705 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 conversion-path-analysis

The instruction itself

7 sections, as written by the author

16/ Conversion Path Analysis — Google + Meta

What it does

Maps out how users move through your funnel from first ad click to conversion. Identifies where the biggest drop-offs happen, which campaigns contribute most at each stage, and how long the typical conversion path takes across different audience segments.

How it works

Claude analyzes your conversion data, assisted conversions, and multi-touch paths to show the full journey. It looks at first-touch vs last-touch attribution, identifies common paths (e.g., Meta prospecting → Google brand → conversion), and flags where users are falling out of the funnel at higher-than-expected rates.

Practical example

Your ecommerce account shows that 62% of conversions involve 2+ touchpoints. The most common path is Meta prospecting ad → Google branded search → purchase. But Claude also discovers that users who see a Meta retargeting ad between those two steps convert at 3.2x the rate. Meanwhile, users who click PMax ads rarely convert on the first visit and almost never return — suggesting PMax is driving low-intent traffic. Claude recommends increasing retargeting budget for Meta-sourced traffic and re-evaluating PMax targeting.

What you get back

  • Most common conversion paths ranked by volume and conversion rate
  • Average time to conversion by path and audience segment
  • Drop-off points in the funnel with estimated revenue impact
  • Campaign-level contribution at each funnel stage (awareness, consideration, conversion)
  • Recommendations for budget and targeting adjustments based on path analysis

When to use it

  • When attribution feels murky and you need to understand the actual user journey
  • Before making budget cuts to understand which "low-performing" campaigns assist conversions elsewhere
  • When conversion lag is long (B2B, high-ticket ecommerce) and last-click data misleads
  • During multi-channel strategy reviews

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/conversion-path-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.