GA4 traffic report
Gives users, sessions, engagement and key events for the period against the period before and last year, by channel, source, device and country, with the daily trend and annotations.
| Item | Value |
|---|---|
| Skill name | ga4-traffic-report |
| Required MCP server | Pilot MCP, https://app.pilot.braike.com/mcp |
| Writes | None: the skill only reads |
| Download | ga4-traffic-report.zip |
MCP tools used
| Tool | Platform |
|---|---|
google_analytics_get_account_summaries | Google Analytics 4 |
google_analytics_get_property | Google Analytics 4 |
google_analytics_run_report | Google Analytics 4 |
google_analytics_batch_run_reports | Google Analytics 4 |
google_analytics_list_property_annotations | Google Analytics 4 |
Optional MCP servers
A file storage server to keep the result, a team messaging server to share it, a note-taking server to archive it. None is needed: the skill works with Pilot MCP alone.
Example requests
- "Give me the GA4 traffic report for the last four weeks."
- "Where does our site traffic come from?"
What the skill returns
The headline, totals and their change, tables by channel, source, device and country, the daily curve and its breaks, and three points to watch.
Install
Download ga4-traffic-report.zip, then follow the steps for your client: install a skill. With the Pilot CLI, one command is enough:
npx @braike/pilot skills install ga4-traffic-reportThe SKILL.md file
See the file as your assistant reads it
---
name: ga4-traffic-report
description: "Builds a Google Analytics 4 traffic report through the Pilot MCP server: users, sessions, engagement and key events over the period against the period before and last year, by channel, source and medium, device and country, the day-by-day trend, and the annotations that explain breaks. Use when the user asks for a GA4 report, site traffic, or where visitors come from. Triggers: GA4 traffic report, website traffic, traffic sources, Google Analytics report. Déclencheurs : rapport de trafic GA4, trafic du site, sources de trafic, rapport Google Analytics."
compatibility: "Requires the Pilot MCP server (https://app.pilot.braike.com/mcp) connected in the client and authorized on a workspace with a Google Analytics 4 property attached."
metadata:
pilot-mcp-server: "https://app.pilot.braike.com/mcp"
pilot-mcp-tools: "google_analytics_get_account_summaries google_analytics_get_property google_analytics_run_report google_analytics_batch_run_reports google_analytics_list_property_annotations"
pilot-mcp-read-only: "true"
---
# GA4 traffic report
Report how much traffic the site got, from where, how engaged it was, and what changed. Answer in the user's language.
## Requirements
- **Required MCP server:** Pilot MCP (`https://app.pilot.braike.com/mcp`), authorized on the workspace that holds the property.
- **Optional MCP servers:** a file storage or slide server to keep the report. None is needed.
- **Read-only:** never change anything in GA4.
## Tools
- `google_analytics_get_account_summaries`: GA4 properties reachable.
- `google_analytics_get_property`: time zone and currency.
- `google_analytics_run_report`: one report with dimensions and metrics over one or more date ranges.
- `google_analytics_batch_run_reports`: up to five reports in one call.
- `google_analytics_list_property_annotations`: dated notes on launches and changes.
## Steps
1. Call `google_analytics_get_account_summaries` and pick the property; call `google_analytics_get_property` for its time zone.
2. Set three ranges: the period (last 28 days by default), the period before, and the same period last year.
3. Call `google_analytics_batch_run_reports` with these reports, each with the three `dateRanges`:
- totals: no dimension, `metrics: ["totalUsers", "newUsers", "sessions", "engagedSessions", "engagementRate", "averageSessionDuration", "keyEvents"]`;
- channels: `dimensions: ["sessionDefaultChannelGroup"]`, `metrics: ["sessions", "engagementRate", "keyEvents"]`;
- sources: `dimensions: ["sessionSource", "sessionMedium"]`, same metrics, `limit: 25`;
- devices: `dimensions: ["deviceCategory"]`;
- countries: `dimensions: ["country"]`, `limit: 15`.
4. Call `google_analytics_run_report` with `dimensions: ["date"]` and `metrics: ["sessions", "keyEvents"]` over the period for the daily trend.
5. Call `google_analytics_list_property_annotations` to explain breaks in the trend. This endpoint may not be available on every property: if it fails, say so and go on.
6. Explain each large change by the channels and sources that carry it.
## Output
1. **Headline**: one sentence on the period.
2. **Totals**: users, sessions, engagement rate and key events, against the period before and last year.
3. **Channels and sources**: tables with the change.
4. **Devices and countries**: shares and changes.
5. **Trend**: the daily curve and its breaks, with annotations.
6. **To watch**: three points for a person.
## Rules
- Name the date ranges and the property time zone.
- GA4 key events and ad platform conversions are not the same count: never mix them.
- A small difference in users between reports comes from GA4's estimation: do not explain it as a trend.
- Data of the last day or two can still change.
## Examples
- "Give me the GA4 traffic report for the last four weeks."
- "D'où vient le trafic du site ce mois-ci, comparé à l'an dernier ?"
- "Quels canaux ont fait bouger les sessions ?"GA4 property audit
Checks a GA4 property setup in read-only mode: time zone and currency, streams and enhanced measurement, key events, custom definitions, Google Ads links, audiences, channel groups and signs of doubtful data.
GA4 funnel analysis
Builds the funnel from the events actually collected, measures completion and drop-off at each step, splits it by device and channel, shows what users who leave do next, and compares two periods.