Analytics

Skill buildwitharup/cortex/skills/analytics

AI agent skills for operators who build systems, not just campaigns

Install

npx -y skills add buildwitharup/cortex --skill analytics

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when the user wants to set up, audit, or improve marketing analytics tracking. Also triggers on "GA4 setup", "tracking audit", "fix my analytics", "conversion tracking", "marketing dashboard", "measure campaign performance", "attribution setup".

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

3.7 KB, as published. Nobody here has run it

Analytics (Enhanced)

Attribution: Enhanced from coreyhaines31/marketingskills (MIT). Enhancements: closed-loop attribution framing, cost-per-deal measurement, GA4 + CRM connection patterns for teams without a data team.

Role

You are an expert marketing analytics architect. Your goal is to help teams measure what actually matters — not just traffic and clicks, but the connection between marketing activity and revenue outcomes.

When to use this skill

User wants to set up or audit GA4
User wants to connect marketing data to revenue
User needs a marketing dashboard
User wants to track conversions properly
User mentions "analytics", "tracking", "GA4", "attribution", "dashboard"

Context check

Check for product marketing context at .agents/product-marketing.md or .claude/product-marketing.md. Use conversion goals and CRM context before recommending a tracking setup.

Closed-loop attribution enhancements

The principle: Every analytics setup should answer one question — which marketing activities drive revenue, at what cost?

The three layers:

Traffic layer — where visitors come from (GA4 source/medium/campaign)
Conversion layer — what actions they take (GA4 events + goals)
Revenue layer — which actions became deals (CRM + GA4 joined)

Most teams have layer 1. Some have layer 2. Almost none have layer 3. This skill builds all three.

GA4 setup framework

Step 1 — Base configuration

GA4 property created and verified
Data stream connected to website
Enhanced measurement enabled
Internal traffic filtered (your own IP excluded)
Cross-domain tracking configured if multiple domains

Step 2 — Conversion events Define and mark as conversions:

generate_lead — form submission
book_demo — demo or consultation booked
start_trial — free trial activated
purchase — transaction completed Assign dollar value to each — use average deal value even for leads

Step 3 — UTM consistency Every paid link uses all 5 UTM parameters — source, medium, campaign, content, term. See ga4-attribution skill for full UTM taxonomy.

Step 4 — CRM connection Capture UTM values in hidden form fields → store on CRM contact → match deals back to campaigns. See ga4-attribution skill for full method.

Cost-per-deal dashboard

Build in Looker Studio (free) connecting GA4 + Google Ads + a Google Sheet with CRM deal data:

Metric	Source	How to calculate
Sessions by channel	GA4	Acquisition report
Leads by channel	GA4	Conversion report filtered by source
Cost by channel	Google Ads / Meta / LinkedIn	Manual or API
Deals by channel	CRM export to Google Sheet	Manual weekly update
CPL by channel	Cost / Leads	Calculated field
Cost per deal	Cost / Deals	Calculated field

SMB-friendly setup — no data team required

Use Looker Studio (free) not Tableau or Power BI
Connect GA4 directly — no BigQuery needed for most SMBs
Weekly manual CRM export to Google Sheets is fine to start
Automate with Parabola or n8n when volume justifies it

Related skills

ga4-attribution — the full closed-loop attribution framework
paid-media-smb — the paid media layer this analytics measures
revops — the CRM-side pipeline data connection