Google Analytics logo

Google Analytics

Community
LichAmnesia
google-analytics

Analyze Google Analytics 4 data — review website performance, identify traffic patterns, diagnose high-bounce pages, compare time periods, and suggest data-driven improvements. Use when the user asks about analytics, website metrics, traffic analysis, conversion rates, user behavior, or performance optimization.

Overview

PublisherLichAmnesia
Repositorylich-skills
Skill namegoogle-analytics
Stars
231
Forks
26
Bundled files
6
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.

  • 6 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Google Analytics 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/LichAmnesia/lich-skills/tree/main/skills/google-analytics
  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/LichAmnesia/lich-skills.git /tmp/lich-skills
mkdir -p .claude/skills
cp -r /tmp/lich-skills/skills/google-analytics .claude/skills/google-analytics
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Google Analytics 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 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 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 4 Analysis

Pull GA4 data via the Data API and turn it into actionable, prioritized recommendations. Scripts are TypeScript (run with Bun or npx tsx).

When to use

  • "Give me a daily SEO report for this property" → daily-report.ts (the out-of-the-box default)
  • "Review our Google Analytics performance for the last 30 days"
  • "How is organic search doing?" / "Which landing pages pull organic traffic?"
  • "What are our top traffic sources?"
  • "Which pages have the highest bounce rates?"
  • "Compare this month vs last month"
  • "Why is mobile converting worse than desktop?"

When NOT to use

  • Real-time / streaming analytics — this uses the batch reporting API
  • Editing GA config, audiences, or events — read-only by design
  • Anything needing PII / individual-user data — GA4 returns aggregates only

Setup

1. Credentials (env vars)

bash
export GOOGLE_ANALYTICS_PROPERTY_ID="YOUR_PROPERTY_ID_HERE"   # numeric, not the G- id
export GOOGLE_APPLICATION_CREDENTIALS="/path/to/service-account-key.json"

Or copy .env.example → .env (Bun auto-loads .env; under tsx, export the vars instead). Full service-account walkthrough is inside .env.example.

Never commit the JSON key or .env. Store the key outside the repo; grant the service account only the Viewer role on the GA4 property.

2. Install the one dependency

bash
cd skills/google-analytics/scripts
bun install            # or: npm install

The only runtime dep is @google-analytics/data (official Google client, fully typed).

Scripts

daily-report.ts — SEO daily report (out-of-the-box default) ⭐

Point it at one property and get a complete, opinionated organic-search report — zero config beyond credentials. This is the SEO-expert default template.

bash
bun run daily-report.ts --property 123456789      # one property → one report
bun run daily-report.ts                            # uses GOOGLE_ANALYTICS_PROPERTY_ID
bun run daily-report.ts --format json --output today.json

Default template (in order): Organic KPIs (rolling 28d vs prior 28d — the Search-Console 4-week-block convention that removes day-of-week skew) · daily anomaly check (yesterday vs same weekday last week, flags drops ≥ 25%) · organic trend sparkline · top organic landing pages (the SEO money view) · by search engine · by country · by device (mobile-first) · auto-generated prioritized recommendations. Everything is filtered to sessionDefaultChannelGroup = "Organic Search".

Flags: --property <id>, --days <n> (default 28), --channel <name> (default "Organic Search"), --anomaly-threshold <pct> (default 25), --format md|json (default md), --output FILE, --help. Writes seo-daily-<date>.md by default.

It auto-detects whether the property uses GA4's conversions or the newer keyEvents metric, and any single failing sub-query degrades gracefully instead of aborting the report.

GA4 limitation: GA4 has no keyword / impression / CTR / average-position data — that lives in Google Search Console (a different API). This report covers the organic behavior GA4 owns; pair with GSC for the query side.

ga-client.ts — raw report query

Thin wrapper over runReport. Any metrics × dimensions combo.

bash
# Last 30 days of sessions + users (JSON)
bun run ga-client.ts --days 30 --metrics sessions,users

# Top pages by views, table output
bun run ga-client.ts --days 7 --metrics screenPageViews \
  --dimensions pagePath --order-by screenPageViews --limit 20 --format table

# Specific window, filtered by country
bun run ga-client.ts --start 2026-01-01 --end 2026-01-31 \
  --metrics sessions,bounceRate --dimensions country --filter "country:United States"

Flags: --days N | --start --end (YYYY-MM-DD or NdaysAgo/yesterday), --metrics (required, comma-sep), --dimensions, --limit (default 10), --order-by (prefix - desc / + asc), --filter "field:value", --format json|table, --output FILE.

analyze.ts — higher-level analysis + recommendations

Pre-built analyses that return metrics plus prioritized recommendations.

bash
bun run analyze.ts --analysis-type seo      --days 28   # organic-only KPIs + top landing pages
bun run analyze.ts --analysis-type overview --days 30   # current vs previous period
bun run analyze.ts --analysis-type sources  --days 30   # traffic sources + optimizations
bun run analyze.ts --analysis-type content  --days 30   # high-bounce pages + diagnosis (all channels)
bun run analyze.ts --analysis-type devices  --days 30   # mobile vs desktop gap (all channels)

--output FILE writes JSON to disk instead of stdout. --channel <name> overrides the organic channel group for the seo cut.

Which report do I actually need? For SEO, reach for daily-report.ts first and --analysis-type seo for a quick organic snapshot. overview / sources are useful general cuts. content and devices are all-channel (not organic-only) and content keys off bounceRate (a de-emphasized GA4 metric) — keep them for general GA use, but for SEO the daily report's organic-filtered device/landing cuts supersede them.

No Bun? Swap bun run X.ts → npx tsx X.ts everywhere (and export the env vars, since tsx won't read .env).

Workflow

When the user asks an analytics question:

  1. Pick the script — a specific metric/dimension question → ga-client.ts; a "how are we doing / what should we fix" question → analyze.ts.
  2. Run it, capture the JSON.
  3. Interpret — surface trends, anomalies, bottlenecks, and conversion opportunities.
  4. Recommend — concrete actions, each with priority (HIGH/MEDIUM/LOW) and expected impact. Lead with the single highest-leverage fix.

See EXAMPLES.md for end-to-end question → command → analysis patterns, and REFERENCE.md for the full metric/dimension catalog.

Run it every day (automation)

The report is a single self-contained command, so any scheduler works. Two options:

Plain cron — write a dated report to a folder each morning (GA4 finalizes "yesterday" within ~24h, so an early-AM run is safe):

bash
# crontab -e  (8:00 every day) — adjust the absolute paths
0 8 * * * cd /path/to/skills/google-analytics/scripts && \
  GOOGLE_ANALYTICS_PROPERTY_ID=123456789 \
  GOOGLE_APPLICATION_CREDENTIALS=/secure/sa.json \
  /usr/local/bin/bun run daily-report.ts --output "/reports/seo-$(date +\%F).md"

Claude Code /schedule — schedule an agent that runs daily-report.ts, then reads the Markdown and messages you the 2-3 highest-priority recommendations (turns the raw report into a daily briefing). Ask: "schedule a daily 8am SEO report for property 123456789 and summarize the HIGH recommendations."

Either way: one property in → one report out, every day.

Troubleshooting

  • Auth error — GOOGLE_APPLICATION_CREDENTIALS points at a valid JSON key, the service account has Viewer on the property, and GOOGLE_ANALYTICS_PROPERTY_ID is the numeric property ID (not the G-XXXX measurement ID).
  • No data — verify the property ID, that the date range has data, and that access was granted in GA4. Use yesterday (not today) — today's data is incomplete.
  • Module not found — run bun install (or npm install) inside scripts/.

Security & privacy

  • Credentials come from env vars / .env only — never hardcoded.
  • The service-account JSON lives outside version control; rotate keys periodically.
  • Least privilege: Viewer role only.
  • Accesses aggregated data only — no PII, no persistence, no third-party sharing, no config writes.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Google Analytics AI skill do?

Analyze Google Analytics 4 data — review website performance, identify traffic patterns, diagnose high-bounce pages, compare time periods, and suggest data-driven improvements. Use when the user asks about analytics, website metrics, traffic analysis, conversion rates, user behavior, or performance optimization.

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/LichAmnesia/lich-skills/tree/main/skills/google-analytics. TypingMind reads its SKILL.md and bundles its files 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 LichAmnesia 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 👇