AnalyticsSearch Console and SEO analysisIntermediateAnalyses your data

Search Console page-level decline diagnosis

Breaks a traffic decline into impressions, CTR and position changes by page and query so the right class of cause is investigated first.

For: Performance marketers, Marketing analysts, Growth marketers · Works with: Google Search Console, Any capable chat model (ChatGPT, Claude, Gemini, others)

Public beta. This prompt was drafted with AI assistance and checked by automated rules, but it has not been reviewed or tested by a person yet. Treat it as a starting point and check the output. It is hidden from search engines while in beta. Use the “Was this prompt useful?” box to tell us what works.

Your prompt

Act as an SEO analyst. Diagnose the decline for the /blog section by comparing 1 Jun-31 Aug 2026 with 1 Sep-30 Sep 2026 in the Search Console data below. Data (query | clicks A | impressions A | position A | clicks B | impressions B | position B): Query | Clicks A | Impr A | Pos A | Clicks B | Impr B | Pos B utm tracking guide | 900 | 21000 | 4.2 | 520 | 20500 | 4.4 what is utm | 600 | 38000 | 7.0 | 260 | 24000 | 9.8 Known changes in this period: redesigned blog templates on 3 September. Tasks: 1. State assumptions (equal period lengths, seasonality, data lag, dropped or anonymised rows). 2. Decompose the click change into impressions change and CTR change, using the formula clicks = impressions x CTR, and show the numbers. 3. Identify which queries drive the decline and whether the cause looks like lost impressions (visibility), lower CTR (snippet or SERP changes) or worse positions; use only the data. 4. List possible causes for each pattern as hypotheses (algorithm changes, content changes, competitor changes, seasonality, technical issues, SERP feature changes) with the checks that would confirm each. 5. Say what you cannot determine from Search Console alone. 6. Suggest a prioritised investigation order. Rules: do not invent causes as facts, benchmarks or industry trends. If data is missing or not provided, request it. Verify arithmetic. Do not state causation; these are correlations.

Customize

The fields start with example values so you can see how the prompt works. Everything stays in your browser.

What declined.

Baseline.

Comparison; ideally equal length.

Paste your comparison. The default is small fictional sample data so the preview works; replace it with your own export.

Site or SERP changes you know about.

Example of what to expect

Illustrative only. It describes the kind of result this prompt aims for; real output varies by tool, model and run.

A decomposition of the click change into impressions and CTR effects, queries driving the decline, hypotheses by pattern with checks, limits of Search Console data and a prioritised investigation list. (Illustrative.)

Expected format: Assumptions, decomposition table, pattern analysis, hypotheses, investigation order.

How to use it

  1. Use equal-length periods.
  2. Check template or technical changes first.
  3. Verify with analytics and crawl data.

Limitations

  • Search Console cannot show why rankings changed.
  • Seasonality and SERP changes can mimic site problems.

Platform notes

Google Search Console

Official docs read · checked 2026-10-11

Search Console data lags by 2-3 days, adding page or query dimensions can drop rows, and the API caps rows per request (per Google's documentation); account for this when comparing recent periods.

General notes on Google Search Console
  • Adding page or query dimensions can drop rows, and data lags by 2-3 days, so recent days look artificially low. Totals computed without page/query dimensions are more accurate.

Any capable chat model (ChatGPT, Claude, Gemini, others)

Official docs read · checked 2026-10-11

Works in any capable chat model. Paste a small anonymised export and recompute the key numbers yourself: chat models can misread columns or miscalculate.

General notes on Any capable chat model (ChatGPT, Claude, Gemini, others)
  • These prompts are plain text and work in any chat assistant. For analytics prompts, paste a small, anonymised export; a chat model can misread columns or miscalculate, so recompute key numbers yourself.

Source, license and attribution

Origin
Original by MarketerTools
Publisher
MarketerTools
License
Original work by MarketerTools, free to copy and use. Informed by the linked documentation; no third-party text is reproduced.
Platform assumptions checked
2026-10-11

Documentation and references behind this prompt

These informed the structure and the platform notes. A reference is not a license, and no third-party prompt text is copied here.

Spotted an attribution error, or are you a source owner with a request? Use the chat button at the bottom right and quote prompt ID ana-020. We will correct or remove it.

Related prompts

  • AnalyticsIntermediateBuilds a checklist

    GA4 sudden traffic or conversion drop triage

    A structured triage that separates tracking and measurement problems from real demand changes, in the order a careful analyst would check them.

    Google Analytics 4 · Any capable chat model (ChatGPT, Claude, Gemini, others)

  • AnalyticsIntermediateAnalyses your data

    Search Console keyword cannibalization candidates

    Finds queries where several of your pages compete, and helps decide whether it is harmful or harmless before merging or redirecting anything.

    Google Search Console · Any capable chat model (ChatGPT, Claude, Gemini, others)