--- name: google-analytics-top-landing-pages description: "Each Tuesday, the 10 landing pages that started the most GA4 sessions last week, with engagement, key events and which pages climbed or slipped. Use when the user asks for this, or when it runs on a schedule." --- # GA4 top landing pages Each Tuesday, the 10 landing pages that started the most GA4 sessions last week, with engagement, key events and which pages climbed or slipped. A landing page is where a visit begins, which makes it the nearest thing GA4 has to an answer for "which pages actually bring people in". Getting at it means Reports > Engagement > Landing page, a date comparison, and an export to clean up the query strings. The agent does that weekly and keeps the top 10. SEO leads see which content pulls its weight, marketers see whether the new campaign page lands anyone, and both notice when a page that used to carry traffic slides off the list. ## Two ways to get the data Use the API or MCP route when you have an MCP server, a CLI or an API token for the app. Otherwise, if you can drive a browser the user is signed in to (Claude in Chrome, a Playwright or Chrome DevTools MCP server), use the browser route. Say which one you used. ## Route A: API or MCP server ### What you need - Read access to the GA4 property (the Viewer role is enough) and its property ID. - An Analytics MCP server or connector, or Data API credentials for a Google Cloud service account that has been granted access to the property. If something is missing, say what and stop; do not invent numbers. ### Steps 1. **Rank last week's landing pages** (Google Analytics): Call `runReport` with `dimensions: [{ name: "landingPagePlusQueryString" }]`, the metrics `sessions`, `engagedSessions`, `keyEvents` and `newUsers`, the last 7 full days, ordered by `sessions` descending with `limit: 100`. 2. **Fold query strings into one page**: Cut everything after `?` (UTM tags, `gclid`, `fbclid`) and sum the metrics per path, then recompute engagement rate as `engagedSessions` over `sessions`. Leave out `(not set)`, which holds sessions that began without a page view. 3. **Line it up with the week before** (Google Analytics): Run the same report for the previous 7 days and join on the path. Flag pages whose sessions moved by 25% or more, and pages that entered or dropped out of the top 10. 4. **Post the ranking**: Ten rows: path, sessions, change, engagement rate and key events. The summary names the biggest climber and the biggest faller, and any top-10 page that keeps fewer than 40% of its visits engaged. ## Route B: the browser ### What you need - Signed in to Google with at least the Viewer role on the GA4 property. If something is missing, say what and stop; do not invent numbers. ### Steps Start at https://analytics.google.com/analytics/web/. The user is signed in already; never type passwords or codes, and ask if a sign-in page appears. 1. **Open the Landing page report**: Pick the property, then go to Reports > Engagement > Landing page. The primary dimension `Landing page + query string` is already set and the table is sorted by Sessions. 2. **Set the week and its comparison**: In the date picker choose `Last 7 days`, switch on Compare, pick `Previous period (match day of week)` and Apply. Set Rows per page under the table to `100` so the top 10 after merging query strings is on one page. 3. **Merge query strings**: Rows that share a path but differ after `?` (UTM tags, `gclid`, `fbclid`) belong to one page: add their Sessions and Key events. Skip `(not set)`. If there are too many variants to add by hand, use Share this report > Download file and sum them in a spreadsheet. 4. **Get the engagement rate from an exploration**: The Landing page report does not show Engagement rate by default. Open Explore > Blank, add the dimension `Landing page + query string` and the metrics `Sessions`, `Engaged sessions` and `Key events`, set the same 7 days, and compute engaged sessions over sessions for your top 10. A Viewer can create explorations. 5. **Write the ranking**: Ten rows with sessions, change, engagement rate and key events. Call out pages that moved 25% or more, pages that entered or left the top 10, and any top-10 page under 40% engagement. Note: Engagement rate needs the exploration step, or an editor who adds the column with Customize report once. Explorations and standard reports can differ by a few sessions because explorations apply thresholds differently. For more than a few hundred landing pages, download the report and work in a spreadsheet. ## The report - **Top 10 landing pages** by sessions last week, each with its change, engagement rate and key events. - **Climbers and fallers**: pages that moved 25% or more, or entered or left the top 10. - **Weak landers**: top-10 pages with an engagement rate under 40%. - What to act on, for example "/pricing gained 11% and converts best: link to it from the invoice templates". ## Post it to Briefkin When `BRIEFKIN_TOKEN` is set, or `~/.config/briefkin/env` exists (the installer from https://briefkin.dev/docs writes it), also send the result to the user's Briefkin board as one card. Keep the `item_key` the same on every run so the card updates in place, use a new `event_id` per run, and put today's real numbers in place of the example ones. If the request fails, say so once and carry on. ```bash [ -n "${BRIEFKIN_TOKEN:-}" ] || . ~/.config/briefkin/env curl -sS -X POST "${BRIEFKIN_URL:-https://briefkin.dev}/v1/events" \ -H "authorization: Bearer $BRIEFKIN_TOKEN" \ -H "content-type: application/json" \ -d @- <<'JSON' { "v": 1, "event_id": "google-analytics-top-landing-pages/", "item_key": "google-analytics-top-landing-pages", "project": "example.com", "source": "GA4 top landing pages skill", "kind": "update", "title": "Recurring invoices page climbs to 6th", "summary": "**/features/recurring-invoices** rose 38% after the launch email and now ranks 6th by sessions.\n**/templates/invoice-pdf** slipped 6%, its second weekly drop in a row.", "widget": [ { "type": "Table", "props": { "columns": [ "Landing page", "Sessions", "Change", "Engaged", "Key events" ], "align": [ "left", "right", "right", "right", "right" ], "rows": [ [ "/", 6840, "+4%", "52%", 188 ], [ "/pricing", 2910, "+11%", "68%", 214 ], [ "/templates/invoice-pdf", 2450, "-6%", "71%", 39 ], [ "/blog/how-to-write-an-invoice", 1980, "+22%", "64%", 12 ], [ "/templates/invoice-word", 1720, "+2%", "69%", 27 ], [ "/features/recurring-invoices", 1140, "+38%", "74%", 61 ], [ "/blog/net-30-payment-terms", 960, "+5%", "58%", 8 ], [ "/templates/receipt", 820, "+14%", "66%", 9 ], [ "/blog/late-payment-fees", 640, "-12%", "38%", 3 ], [ "/integrations/xero", 590, "new", "61%", 17 ] ] } }, { "type": "Callout", "props": { "text": "/blog/late-payment-fees keeps only 38% of visits engaged, the lowest in the top 10. Check that the answer sits near the top of the page.", "tone": "warn" } } ] } JSON ``` Widgets come from the Briefkin catalog (https://briefkin.dev/v1/catalog). Without a token, just give the user the report. ## Run it on a schedule Suggested: Tuesdays at 9:00 (`0 9 * * 2`). From cron, with the agent signed in on that machine: ```bash 0 9 * * 2 claude -p "Run the google-analytics-top-landing-pages skill" # Codex: codex exec, Gemini CLI: gemini -p, Copilot CLI: copilot -p, OpenCode: opencode run ``` Or use the agent's own scheduler (Claude Code routines, Codex automations, Claude or ChatGPT scheduled tasks): https://briefkin.dev/skills/google-analytics-top-landing-pages#schedule Source: https://briefkin.dev/skills/google-analytics-top-landing-pages