What does the Google Analytics AI skill do?

Pull GA4 reports, traffic data, and insights from the Google Analytics Data API. Use when asked about website traffic, user behavior, acquisition channels, conversions, or audience segments. Trigger phrases: "google analytics", "GA4", "traffic report", "analytics data", "user acquisition", "engagement metrics", "conversion tracking", "audience segments", "page views", "sessions".

Why use Google Analytics on TypingMind?

Because you install it once and use it with any model. Google Analytics 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 in TypingMind?

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

Which AI models can use Google Analytics?

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?

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

Is the Google Analytics AI skill free?

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

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.

Google Analytics by OpenClaudia — AI Skill for Any LLM

Google Analytics (GA4)

Pull reports and insights from GA4 using the Google Analytics Data API.

Prerequisites

Requires Google OAuth credentials:

GOOGLE_CLIENT_ID
GOOGLE_CLIENT_SECRET
A valid OAuth access token (refreshed as needed)

Set credentials in .env, .env.local, or ~/.claude/.env.global.

Getting an Access Token

bash
# Step 1: Get authorization code (user must visit this URL in browser)
echo "https://accounts.google.com/o/oauth2/v2/auth?client_id=${GOOGLE_CLIENT_ID}&redirect_uri=urn:ietf:wg:oauth:2.0:oob&scope=https://www.googleapis.com/auth/analytics.readonly&response_type=code&access_type=offline"

# Step 2: Exchange code for tokens
curl -s -X POST "https://oauth2.googleapis.com/token" \
  -d "code={AUTH_CODE}" \
  -d "client_id=${GOOGLE_CLIENT_ID}" \
  -d "client_secret=${GOOGLE_CLIENT_SECRET}" \
  -d "redirect_uri=urn:ietf:wg:oauth:2.0:oob" \
  -d "grant_type=authorization_code"

# Step 3: Refresh an expired token
curl -s -X POST "https://oauth2.googleapis.com/token" \
  -d "refresh_token={REFRESH_TOKEN}" \
  -d "client_id=${GOOGLE_CLIENT_ID}" \
  -d "client_secret=${GOOGLE_CLIENT_SECRET}" \
  -d "grant_type=refresh_token"

Store the refresh token securely. The access token expires after 1 hour.

Finding Your GA4 Property ID

bash
curl -s -H "Authorization: Bearer ${GA_ACCESS_TOKEN}" \
  "https://analyticsadmin.googleapis.com/v1beta/accountSummaries" \
  | python3 -c "
import json, sys
data = json.load(sys.stdin)
for acct in data.get('accountSummaries', []):
    for prop in acct.get('propertySummaries', []):
        print(f\"{prop['property']}  |  {prop.get('displayName','')}  |  Account: {acct.get('displayName','')}\")
"

The property ID format is properties/XXXXXXXXX.

API Base


POST https://analyticsdata.googleapis.com/v1beta/{property_id}:runReport

All report requests use POST with a JSON body. Always include Authorization: Bearer {ACCESS_TOKEN}.

1. Traffic Overview Report

Get sessions, users, page views, and engagement rate over a date range.

Example curl

bash
curl -s -X POST \
  "https://analyticsdata.googleapis.com/v1beta/properties/{PROPERTY_ID}:runReport" \
  -H "Authorization: Bearer ${GA_ACCESS_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "dateRanges": [{"startDate": "30daysAgo", "endDate": "today"}],
    "metrics": [
      {"name": "sessions"},
      {"name": "totalUsers"},
      {"name": "newUsers"},
      {"name": "screenPageViews"},
      {"name": "engagementRate"},
      {"name": "averageSessionDuration"},
      {"name": "bounceRate"}
    ]
  }'

Date Range Shortcuts

today, yesterday
7daysAgo, 14daysAgo, 28daysAgo, 30daysAgo, 90daysAgo
Specific dates: 2024-01-01
Compare periods by passing two dateRanges

2. User Acquisition Report

See where users come from (channels, sources, campaigns).

bash
curl -s -X POST \
  "https://analyticsdata.googleapis.com/v1beta/properties/{PROPERTY_ID}:runReport" \
  -H "Authorization: Bearer ${GA_ACCESS_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "dateRanges": [{"startDate": "30daysAgo", "endDate": "today"}],
    "dimensions": [
      {"name": "sessionDefaultChannelGroup"}
    ],
    "metrics": [
      {"name": "sessions"},
      {"name": "totalUsers"},
      {"name": "engagementRate"},
      {"name": "conversions"}
    ],
    "orderBys": [{"metric": {"metricName": "sessions"}, "desc": true}],
    "limit": 20
  }'

Useful Acquisition Dimensions

Dimension	Description
`sessionDefaultChannelGroup`	Channel grouping (Organic, Paid, Social, etc.)
`sessionSource`	Traffic source (google, facebook, etc.)
`sessionMedium`	Medium (organic, cpc, referral, etc.)
`sessionCampaignName`	UTM campaign name
`firstUserSource`	First-touch attribution source

3. Top Pages Report

Find the highest-traffic pages on the site.

bash
curl -s -X POST \
  "https://analyticsdata.googleapis.com/v1beta/properties/{PROPERTY_ID}:runReport" \
  -H "Authorization: Bearer ${GA_ACCESS_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "dateRanges": [{"startDate": "30daysAgo", "endDate": "today"}],
    "dimensions": [
      {"name": "pagePath"}
    ],
    "metrics": [
      {"name": "screenPageViews"},
      {"name": "totalUsers"},
      {"name": "engagementRate"},
      {"name": "averageSessionDuration"}
    ],
    "orderBys": [{"metric": {"metricName": "screenPageViews"}, "desc": true}],
    "limit": 25
  }'

4. Engagement Metrics

Understand how users interact with your content.

bash
curl -s -X POST \
  "https://analyticsdata.googleapis.com/v1beta/properties/{PROPERTY_ID}:runReport" \
  -H "Authorization: Bearer ${GA_ACCESS_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "dateRanges": [{"startDate": "30daysAgo", "endDate": "today"}],
    "dimensions": [
      {"name": "pagePath"}
    ],
    "metrics": [
      {"name": "engagedSessions"},
      {"name": "engagementRate"},
      {"name": "averageSessionDuration"},
      {"name": "screenPageViewsPerSession"},
      {"name": "eventCount"}
    ],
    "orderBys": [{"metric": {"metricName": "engagedSessions"}, "desc": true}],
    "limit": 20
  }'

Key Engagement Metrics

Metric	What It Measures
`engagementRate`	% of sessions that were engaged (>10s, 2+ pages, or conversion)
`averageSessionDuration`	Mean session length in seconds
`screenPageViewsPerSession`	Pages per session
`bounceRate`	% of sessions with no engagement
`eventCount`	Total events fired

5. Conversion Tracking

Report on conversion events (purchases, signups, etc.).

bash
curl -s -X POST \
  "https://analyticsdata.googleapis.com/v1beta/properties/{PROPERTY_ID}:runReport" \
  -H "Authorization: Bearer ${GA_ACCESS_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "dateRanges": [{"startDate": "30daysAgo", "endDate": "today"}],
    "dimensions": [
      {"name": "eventName"}
    ],
    "metrics": [
      {"name": "eventCount"},
      {"name": "totalUsers"},
      {"name": "eventValue"}
    ],
    "dimensionFilter": {
      "filter": {
        "fieldName": "eventName",
        "inListFilter": {
          "values": ["purchase", "sign_up", "generate_lead", "begin_checkout"]
        }
      }
    }
  }'

Conversion by Channel

bash
curl -s -X POST \
  "https://analyticsdata.googleapis.com/v1beta/properties/{PROPERTY_ID}:runReport" \
  -H "Authorization: Bearer ${GA_ACCESS_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "dateRanges": [{"startDate": "30daysAgo", "endDate": "today"}],
    "dimensions": [
      {"name": "sessionDefaultChannelGroup"}
    ],
    "metrics": [
      {"name": "sessions"},
      {"name": "conversions"},
      {"name": "totalRevenue"}
    ],
    "orderBys": [{"metric": {"metricName": "conversions"}, "desc": true}]
  }'

6. Audience Segments

Break down traffic by device, geography, and demographics.

By Device Category

bash
curl -s -X POST \
  "https://analyticsdata.googleapis.com/v1beta/properties/{PROPERTY_ID}:runReport" \
  -H "Authorization: Bearer ${GA_ACCESS_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "dateRanges": [{"startDate": "30daysAgo", "endDate": "today"}],
    "dimensions": [{"name": "deviceCategory"}],
    "metrics": [
      {"name": "sessions"},
      {"name": "totalUsers"},
      {"name": "engagementRate"},
      {"name": "conversions"}
    ]
  }'

By Country

Replace deviceCategory with country in the dimensions.

By Landing Page + Source

bash
curl -s -X POST \
  "https://analyticsdata.googleapis.com/v1beta/properties/{PROPERTY_ID}:runReport" \
  -H "Authorization: Bearer ${GA_ACCESS_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "dateRanges": [{"startDate": "30daysAgo", "endDate": "today"}],
    "dimensions": [
      {"name": "landingPage"},
      {"name": "sessionSource"}
    ],
    "metrics": [
      {"name": "sessions"},
      {"name": "engagementRate"},
      {"name": "conversions"}
    ],
    "orderBys": [{"metric": {"metricName": "sessions"}, "desc": true}],
    "limit": 30
  }'

7. Period Comparison

Compare two time periods to identify trends.

bash
curl -s -X POST \
  "https://analyticsdata.googleapis.com/v1beta/properties/{PROPERTY_ID}:runReport" \
  -H "Authorization: Bearer ${GA_ACCESS_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "dateRanges": [
      {"startDate": "30daysAgo", "endDate": "today", "name": "current"},
      {"startDate": "60daysAgo", "endDate": "31daysAgo", "name": "previous"}
    ],
    "metrics": [
      {"name": "sessions"},
      {"name": "totalUsers"},
      {"name": "conversions"},
      {"name": "engagementRate"}
    ]
  }'

Response Parsing

GA4 API returns JSON. Parse with python3 or jq:

bash
# Parse report into a table
curl -s -X POST "..." | python3 -c "
import json, sys
data = json.load(sys.stdin)
headers = [h['name'] for h in data.get('dimensionHeaders',[])] + [m['name'] for m in data.get('metricHeaders',[])]
print(' | '.join(headers))
print('-' * (len(headers) * 20))
for row in data.get('rows', []):
    dims = [d['value'] for d in row.get('dimensionValues',[])]
    mets = [m['value'] for m in row.get('metricValues',[])]
    print(' | '.join(dims + mets))
"

Workflow: Monthly Analytics Report

When asked for a monthly report:

Pull traffic overview (sessions, users, page views) with period comparison
Pull acquisition breakdown by channel
Pull top 20 pages by page views
Pull conversion summary by channel
Pull device and country breakdown

Present as a structured report with tables, trends (up/down arrows), and recommendations:


## Monthly Analytics Report: {Property Name}
### Period: {date range} vs {previous period}

### Traffic Summary
| Metric | Current | Previous | Change |
|--------|---------|----------|--------|
| Sessions | X | Y | +Z% |
| ...

### Top Channels
...

### Top Pages
...

### Conversion Summary
...

### Recommendations
- [Based on data patterns]

Common Issues

403 Forbidden: User lacks access to the GA4 property
Empty rows: No data for the requested date range or filters
Quota exceeded: GA4 API has daily quotas; reduce date ranges or batch requests
Property not found: Verify the property ID format (properties/XXXXXXXXX)

Publisher	OpenClaudia
Repository	`openclaudia-skills`
Skill name	`google-analytics`
Stars	714
Forks	60
Bundled files	Instructions only
License	MIT
Links	Skill source Repository Homepage

Google Analytics

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Google Analytics (GA4)

Prerequisites

Getting an Access Token

Finding Your GA4 Property ID

API Base

1. Traffic Overview Report

Example curl

Date Range Shortcuts

2. User Acquisition Report

Useful Acquisition Dimensions

3. Top Pages Report

4. Engagement Metrics

Key Engagement Metrics

5. Conversion Tracking

Conversion by Channel

6. Audience Segments

By Device Category

By Country

By Landing Page + Source

7. Period Comparison

Response Parsing

Workflow: Monthly Analytics Report

Common Issues

Frequently asked questions

Set up your own AI workspace now

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Google Analytics (GA4)

Prerequisites

Getting an Access Token

Finding Your GA4 Property ID

API Base

1. Traffic Overview Report

Example curl

Date Range Shortcuts

2. User Acquisition Report

Useful Acquisition Dimensions

3. Top Pages Report

4. Engagement Metrics

Key Engagement Metrics

5. Conversion Tracking

Conversion by Channel

6. Audience Segments

By Device Category

By Country

By Landing Page + Source

7. Period Comparison

Response Parsing

Workflow: Monthly Analytics Report

Common Issues

Frequently asked questions

Related AI Skills

Set up your own AI workspace now