Google Analytics Tool logo

Google Analytics Tool

Community
garrettjsmith
google-analytics-tool

When the user wants traffic data, conversion tracking, user behavior on location pages, GBP traffic attribution, or geographic traffic patterns. Trigger on "Google Analytics," "GA4," "traffic," "conversions," "how many leads," "phone calls," "form submissions," "where is my traffic coming from," or "is my website converting."

Overview

Publishergarrettjsmith
Repositorylocalseoskills
Skill namegoogle-analytics-tool
Stars
140
Forks
27
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by garrettjsmith on GitHub. Read the source before you install it.

Installation

Install the Google Analytics Tool AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/garrettjsmith/localseoskills/tree/main/skills/google-analytics-tool
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/garrettjsmith/localseoskills.git /tmp/localseoskills
mkdir -p .claude/skills
cp -r /tmp/localseoskills/skills/google-analytics-tool .claude/skills/google-analytics-tool
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Google Analytics Tool in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Google Analytics Tool on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Google Analytics Tool is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Google Analytics (GA4) Tool

GA4 has an official MCP server from Google. When connected, use it for website traffic analysis, conversion attribution, and user behavior data. GA4 answers "what happens AFTER someone finds you."

When to Use GA4 vs Other Tools

You NeedUse GA4Use Instead
Traffic to location pages✅—
Conversion tracking (calls, forms, bookings)✅—
Traffic source attribution (organic vs paid vs GBP)✅—
Geographic traffic patterns✅—
User behavior (bounce rate, engagement, time on page)✅—
GBP-specific traffic (via UTM)✅—
What keywords people searched to find you❌ Very limitedGSC (query data)
Search rankings❌Local Falcon, Semrush
Backlinks❌Ahrefs
SERP features❌SerpAPI

Critical Distinction

GA4 shows what happens ON YOUR WEBSITE. It does NOT show:

  • GBP interactions that don't reach your website (calls from GBP, directions from GBP, map views)
  • Map pack clicks that go to the GBP profile, not the website
  • Local Falcon/ranking data

For complete local performance: GA4 (website) + GSC (organic queries) + GBP Insights (profile interactions) + Local Falcon (map rankings).

Core Workflows

Location Page Traffic Analysis

When: User asks "how are my location pages performing?" or "which locations get the most traffic?"

What to pull:

  1. Landing page report filtered to location page URLs
  2. Metrics: Sessions, users, engaged sessions, engagement rate, conversions
  3. Compare across location pages

How to interpret:

  • Location page with high traffic but low engagement: Content doesn't match what visitors expect — check title alignment
  • Location page with high engagement but low conversions: Missing or weak CTA (call button, form, booking link)
  • Location page with no traffic: Not indexed (check GSC) or no keyword targeting (check local-keyword-research)
  • Big traffic differences between location pages: Might reflect market size, or some pages are better optimized

Conversion Tracking

When: User asks "how many leads am I getting?" or wants to measure ROI.

Key local conversions to track:

Conversion EventHow to TrackSetup Required
Phone calls (click-to-call)Event on tel: link clicksYes — event must be configured
Form submissionsEvent on form submit/thank-you pageYes — event or thank-you page trigger
Direction requestsEvent on directions link clicksYes — event on link
Booking/schedulingEvent on booking completionYes — depends on booking system
Chat initiatedEvent on chat widget openYes — event on widget

If conversions aren't set up: Tell the user. GA4 doesn't track conversions automatically. Without configured events, you can only report traffic, not leads.

What to look for:

  • Conversion rate per traffic source (organic vs paid vs direct vs referral)
  • Conversion rate per location page
  • Which pages generate the most conversions (not just traffic)
  • Conversion trends over time (improving or declining?)

GBP Traffic Attribution

When: User wants to know how much traffic comes specifically from their Google Business Profile.

How it works: GBP website links should include UTM parameters. Common patterns:

  • utm_source=google&utm_medium=organic&utm_campaign=gbp
  • utm_source=gmb (older convention)

What to pull:

  1. Filter by source/medium matching GBP UTM parameters
  2. Sessions, users, conversions from GBP specifically
  3. Compare GBP traffic to overall organic traffic

If no UTM tracking: Most businesses don't set this up. Recommend adding UTM parameters to the GBP website URL so future data can be attributed.

Geographic Traffic Analysis

When: User wants to know where their website visitors are located.

What to pull:

  1. Geographic report by city/region
  2. Filter to organic traffic only
  3. Compare against service area

How to interpret for local:

  • Traffic concentrated in one city but business serves a wider area: Need service area pages for other cities
  • Traffic from cities outside service area: Content attracting non-local visitors (may or may not be useful)
  • No traffic from a city in the service area: No content targeting that area, or not ranking there

Traffic Source Comparison

When: User wants to understand their traffic mix.

Pull traffic by source/medium:

  • Organic search (Google/Bing) → SEO working
  • Direct → Brand awareness / repeat visitors
  • Referral → Links from other sites sending traffic
  • Paid search → Google Ads / PPC
  • Social → Social media channels

Healthy local business traffic mix:

  • Organic: 40-60% (should be the largest source)
  • Direct: 20-30% (brand recognition)
  • Referral: 5-15% (healthy backlink profile)
  • Paid: varies by budget
  • If organic is under 30%, SEO needs work

Key Metrics and What They Mean

MetricWhat It IsLocal SEO Context
SessionsWebsite visitsTotal demand reaching your site
Engaged SessionsSessions with meaningful interactionMore important than raw sessions
Engagement RateEngaged sessions ÷ Total sessionsBelow 50% on location pages = content problem
ConversionsCompleted goal actionsTHE metric — everything else is a means to this
Conversion RateConversions ÷ SessionsBenchmark: 3-5% for local service businesses
Bounce RateSessions with no interactionGA4 bounce = not engaged. High bounce on location pages = bad signal
Average Engagement TimeTime actively on pageUnder 30 seconds = content isn't connecting

What to Do Next

What You FoundNext ActionSkill
Location pages with low trafficCheck GSC for indexing, then check keyword targetinggoogle-search-console-tool, local-keyword-research
Traffic but no conversionsAdd/fix CTAs, forms, click-to-calllocal-landing-pages
No conversion tracking set upConfigure GA4 events before anything elseTechnical setup needed
GBP traffic not being trackedAdd UTM parameters to GBP website URLgbp-optimization
Good traffic from organic but bad conversion rateLanding page content/design issuelocal-landing-pages
Geographic gaps in trafficBuild location pages for underserved citieslocal-landing-pages, service-area-seo
Need this in a client reportInclude traffic and conversion data in reportslocal-reporting

Default next step: Traffic without conversion tracking is vanity metrics. If GA4 events aren't configured, that's the first thing to fix — before any SEO work, you need to be able to measure results.

Frequently asked questions

What does the Google Analytics Tool AI skill do?

When the user wants traffic data, conversion tracking, user behavior on location pages, GBP traffic attribution, or geographic traffic patterns. Trigger on "Google Analytics," "GA4," "traffic," "conversions," "how many leads," "phone calls," "form submissions," "where is my traffic coming from," or "is my website converting."

Why use Google Analytics Tool on TypingMind?

Because you install it once and use it with any model. Google Analytics Tool is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Google Analytics Tool in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/garrettjsmith/localseoskills/tree/main/skills/google-analytics-tool. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Google Analytics Tool?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Google Analytics Tool?

As many as you like. As long as a model supports skills, you can use Google Analytics Tool with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Google Analytics Tool AI skill free?

Yes. It is published on GitHub by garrettjsmith under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇