Push-based web analytics intelligence team — self-hosted Umami via MCP (primary) + GA4 (fallback). 9 specialist agents fetch data, detect anomalies, analyze funnels, verify claims adversarially, and deliver narrative reports across your entire site portfolio. Three tiers: 30-second pulse, 2-min brief, 5-min full deep-dive. Console / email / Slack delivery.

1 Skills

9 Agents

MIT License

Free Pricing

Installation

Open Claude Code and run this command:

/plugin install web-analytics@claude-code-plugins-plus

Use --global to install for all projects, or --project for current project only.

What It Does

> Push-based web analytics intelligence — self-hosted Umami (primary) via MCP + GA4 (fallback). 9 specialist agents fetch data, detect anomalies, analyze funnels, verify claims, and deliver narrative reports across your entire site portfolio.

Install: /plugin install web-analytics@claude-code-plugins-plus

Skills (1)

web-analytics SKILL.md View full skill →

'Push-based web analytics intelligence for your entire site portfolio.

ReadGlobGrepBash(date:*)Bash(node:*)Bash(curl:*)Bash(python3:*)Bash(source:*)TaskAskUserQuestion

Web Analytics Intelligence

Orchestrates a team of specialist agents to deliver business-grade analytics insights

across your entire site portfolio. Not a dashboard replacement — a push-based analytics

team that surfaces what matters.

Overview

This skill routes analytics requests to the right combination of specialist agents based

on the requested tier, compiles their outputs into a cohesive narrative, and delivers

via console, email, or Slack.

Architecture: Orchestrator (this skill) → Data Collector → Specialist Agents (parallel) → Reporter

Prerequisites

Umami credentials in ~/.env (UMAMI_PASSWORD for the admin user)
Sites configured in ${CLAUDESKILLDIR}/references/site-registry.md
For email delivery: /email skill working
For Slack delivery: /slack skill working

Data Access

The skill uses direct Umami REST API calls (more reliable than MCP):


# Get auth token
TOKEN=$(curl -s "https://analytics.intentsolutions.io/api/auth/login" \
  -X POST -H "Content-Type: application/json" \
  -d '{"username":"admin","password":"'"$UMAMI_PASSWORD"'"}' | \
  python3 -c "import sys,json; print(json.load(sys.stdin).get('token',''))")

# Get stats (uses epoch ms, compare=prev for prior period)
curl -s "https://analytics.intentsolutions.io/api/websites/{SITE_ID}/stats?startAt={START_MS}&endAt={END_MS}&compare=prev" \
  -H "Authorization: Bearer $TOKEN"

# Get active visitors
curl -s "https://analytics.intentsolutions.io/api/websites/{SITE_ID}/active" \
  -H "Authorization: Bearer $TOKEN"

# Get daily pageviews
curl -s "https://analytics.intentsolutions.io/api/websites/{SITE_ID}/pageviews?startAt={START_MS}&endAt={END_MS}&unit=day&timezone=America%2FNew_York" \
  -H "Authorization: Bearer $TOKEN"

Instructions

Step 1: Parse Request

Extract from $ARGUMENTS or conversation context:

Parameter	Default	Options
Tier	mini	`mini`, `medium`, `full`
Site	all	Site name from registry, or `all`
Period	7d	`today`, `yesterday`, `7d`, `30d`, `mtd`, `qtd`
Delivery	console	`--email`, `--slack`, `--all`
Compare	auto	Previous equivalent period

Examples:

/analyt



      
      
          How It Works
          
/analytics [tier]
   │
   ▼
orchestrator (this skill)
   │
   ▼
data-collector ──► self-hosted Umami via MCP (primary)
                   GA4 Data API (fallback)
   │
   ▼
parallel specialist agents:
   - traffic-intelligence    (channel attribution)
   - content-seo             (page performance)
   - anomaly-detector        (spike/drop detection)
   - conversion-funnel       (event/goal analysis)
   - audience-segmentation   (cohort/geo)
   - verification-agent      (adversarial QA)
   │
   ▼
reporting-narrative ──► console / email / Slack delivery

        

      
      

      
      

      
      
  Ready to use web-analytics?
  
    
    
  




      
      

      
      
          Tags
          
            analyticsumamiga4trafficmcpself-hostedmulti-agentpush-based