Run a SQL query against BigQuery and return results. Only SELECT queries are allowed. A LIMIT clause is automatically added if missing. Claude should use list_datasets, list_tables, and describe_table first to understand the schema before writing queries. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing.

Dry-run a SQL query to see how many bytes it would scan without actually executing it. Use this before running expensive queries to check cost.

List all datasets in the BigQuery project. Use this first to discover what data is available.

List all tables in a BigQuery dataset with their schemas. Uses INFORMATION_SCHEMA for efficiency. Use this to understand what tables and columns are available before writing queries.

Get detailed schema information for a specific BigQuery table including column names, types, descriptions, row count, size, partitioning, and clustering.

Preview sample rows from a table without writing SQL. Useful for quickly understanding what data looks like. Limited to 1GB bytes billed.

Find keywords from GSC bulk export data at positions 4 to 15 with high impressions. These are striking distance keywords that could be pushed to page one. Sorted by traffic opportunity. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing. PRESENTATION: Always present these results as a rich, interactive visualization using artifacts. Use summary cards for key metrics, colour-coded indicators for severity or change direction (green for positive, red for negative), bar charts or sparklines for comparisons, and tabbed sections to organise different categories of results. Make the output visually scannable and dashboard-like rather than plain text or raw tables.

Find pages with high impressions but CTR significantly below the expected benchmark for their ranking position. These are title and meta description optimisation candidates. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing. PRESENTATION: Always present these results as a rich, interactive visualization using artifacts. Use summary cards for key metrics, colour-coded indicators for severity or change direction (green for positive, red for negative), bar charts or sparklines for comparisons, and tabbed sections to organise different categories of results. Make the output visually scannable and dashboard-like rather than plain text or raw tables.

Find topics you should create content for. Returns queries where you get impressions but rank beyond position 20, meaning there is search demand but no real content targeting it. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing. PRESENTATION: Always present these results as a rich, interactive visualization using artifacts. Use summary cards for key metrics, colour-coded indicators for severity or change direction (green for positive, red for negative), bar charts or sparklines for comparisons, and tabbed sections to organise different categories of results. Make the output visually scannable and dashboard-like rather than plain text or raw tables.

Get a quick overview of how the site is performing. Returns total clicks, impressions, CTR, position, unique pages and queries with a comparison to the prior period. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing. PRESENTATION: Always present these results as a rich, interactive visualization using artifacts. Use summary cards for key metrics, colour-coded indicators for severity or change direction (green for positive, red for negative), bar charts or sparklines for comparisons, and tabbed sections to organise different categories of results. Make the output visually scannable and dashboard-like rather than plain text or raw tables.

Find pages with consistent traffic decline over three consecutive months from GSC bulk export data. One bad month is noise; three is a problem. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing. PRESENTATION: Always present these results as a rich, interactive visualization using artifacts. Use summary cards for key metrics, colour-coded indicators for severity or change direction (green for positive, red for negative), bar charts or sparklines for comparisons, and tabbed sections to organise different categories of results. Make the output visually scannable and dashboard-like rather than plain text or raw tables.

Find keywords where multiple pages from your site compete against each other. Shows which pages rank for the same query and their respective positions. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing. PRESENTATION: Always present these results as a rich, interactive visualization using artifacts. Use summary cards for key metrics, colour-coded indicators for severity or change direction (green for positive, red for negative), bar charts or sparklines for comparisons, and tabbed sections to organise different categories of results. Make the output visually scannable and dashboard-like rather than plain text or raw tables.

Find pages that lost the most traffic recently. Compares current period vs prior period and diagnoses whether each drop is a ranking loss, CTR collapse, or demand decline. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing. PRESENTATION: Always present these results as a rich, interactive visualization using artifacts. Use summary cards for key metrics, colour-coded indicators for severity or change direction (green for positive, red for negative), bar charts or sparklines for comparisons, and tabbed sections to organise different categories of results. Make the output visually scannable and dashboard-like rather than plain text or raw tables.

See how a group of pages performs as a whole. Aggregates clicks, impressions, CTR, and position for all pages matching a URL path pattern, plus top pages and queries. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing. PRESENTATION: Always present these results as a rich, interactive visualization using artifacts. Use summary cards for key metrics, colour-coded indicators for severity or change direction (green for positive, red for negative), bar charts or sparklines for comparisons, and tabbed sections to organise different categories of results. Make the output visually scannable and dashboard-like rather than plain text or raw tables.

Compare your actual CTR per page against industry benchmarks by position. Flags pages significantly underperforming for their ranking position with verdicts. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing. PRESENTATION: Always present these results as a rich, interactive visualization using artifacts. Use summary cards for key metrics, colour-coded indicators for severity or change direction (green for positive, red for negative), bar charts or sparklines for comparisons, and tabbed sections to organise different categories of results. Make the output visually scannable and dashboard-like rather than plain text or raw tables.

Check for SEO alerts: position drops, CTR collapses, click losses, and pages that disappeared from search results. Returns severity-rated alerts so you know what needs attention first. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing. PRESENTATION: Always present these results as a rich, interactive visualization using artifacts. Use summary cards for key metrics, colour-coded indicators for severity or change direction (green for positive, red for negative), bar charts or sparklines for comparisons, and tabbed sections to organise different categories of results. Make the output visually scannable and dashboard-like rather than plain text or raw tables.

Get actionable content recommendations by cross-referencing quick wins, content gaps, and cannibalisation data. Returns prioritised actions: pages to update, content to create, and pages to consolidate. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing. PRESENTATION: Always present these results as a rich, interactive visualization using artifacts. Use summary cards for key metrics, colour-coded indicators for severity or change direction (green for positive, red for negative), bar charts or sparklines for comparisons, and tabbed sections to organise different categories of results. Make the output visually scannable and dashboard-like rather than plain text or raw tables.

Generate a comprehensive markdown performance report. Covers site snapshot, alerts, quick wins, traffic drops, content decay, and recommendations. Returns the full report as markdown. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing. PRESENTATION: Always present these results as a rich, interactive visualization using artifacts. Use summary cards for key metrics, colour-coded indicators for severity or change direction (green for positive, red for negative), bar charts or sparklines for comparisons, and tabbed sections to organise different categories of results. Make the output visually scannable and dashboard-like rather than plain text or raw tables.

Analyse anonymous (hidden) query traffic that the GSC API cannot show. Reveals what percentage of your clicks come from queries Google redacts, and which pages get the most hidden traffic. Only possible with BigQuery bulk export. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing. PRESENTATION: Always present these results as a rich, interactive visualization using artifacts. Use summary cards for key metrics, colour-coded indicators for severity or change direction (green for positive, red for negative), bar charts or sparklines for comparisons, and tabbed sections to organise different categories of results. Make the output visually scannable and dashboard-like rather than plain text or raw tables.

Year-over-year seasonal traffic analysis. Shows monthly clicks, impressions, CTR, and position with YoY comparison. Requires 12+ months of BigQuery data. Impossible with the 16-month rolling GSC API. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing. PRESENTATION: Always present these results as a rich, interactive visualization using artifacts. Use summary cards for key metrics, colour-coded indicators for severity or change direction (green for positive, red for negative), bar charts or sparklines for comparisons, and tabbed sections to organise different categories of results. Make the output visually scannable and dashboard-like rather than plain text or raw tables.

Find queries where mobile and desktop rank different pages from your site. This device cannibalisation is invisible in the GSC UI and impossible to detect via the API's 3-dimension limit. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing. PRESENTATION: Always present these results as a rich, interactive visualization using artifacts. Use summary cards for key metrics, colour-coded indicators for severity or change direction (green for positive, red for negative), bar charts or sparklines for comparisons, and tabbed sections to organise different categories of results. Make the output visually scannable and dashboard-like rather than plain text or raw tables.

Classify all your ranking queries by search intent (informational, transactional, commercial, navigational) using regex pattern matching at scale. Shows clicks, impressions, and CTR by intent category. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing. PRESENTATION: Always present these results as a rich, interactive visualization using artifacts. Use summary cards for key metrics, colour-coded indicators for severity or change direction (green for positive, red for negative), bar charts or sparklines for comparisons, and tabbed sections to organise different categories of results. Make the output visually scannable and dashboard-like rather than plain text or raw tables.

Extract the most common meaningful terms across your entire query set, ranked by clicks. A lightweight alternative to keyword clustering that reveals emerging topics and content themes. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing. PRESENTATION: Always present these results as a rich, interactive visualization using artifacts. Use summary cards for key metrics, colour-coded indicators for severity or change direction (green for positive, red for negative), bar charts or sparklines for comparisons, and tabbed sections to organise different categories of results. Make the output visually scannable and dashboard-like rather than plain text or raw tables.

Discover queries that appeared in your recent data but were not present in the baseline period. Useful for spotting new ranking opportunities, trending topics, or the impact of recently published content. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing. PRESENTATION: Always present these results as a rich, interactive visualization using artifacts. Use summary cards for key metrics, colour-coded indicators for severity or change direction (green for positive, red for negative), bar charts or sparklines for comparisons, and tabbed sections to organise different categories of results. Make the output visually scannable and dashboard-like rather than plain text or raw tables.

Forecast organic traffic using BigQuery ML ARIMA_PLUS. Trains a time-series model on your historical click data and projects future clicks with confidence intervals. Requires sufficient historical data (ideally 6+ months). This is only possible with BigQuery ML. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing. PRESENTATION: Always present these results as a rich, interactive visualization using artifacts. Use summary cards for key metrics, colour-coded indicators for severity or change direction (green for positive, red for negative), bar charts or sparklines for comparisons, and tabbed sections to organise different categories of results. Make the output visually scannable and dashboard-like rather than plain text or raw tables.

Detect traffic anomalies using BigQuery ML. Unlike threshold-based alerts, this understands seasonality and weekly patterns, so it only flags genuinely unexpected traffic changes. Requires sufficient historical data (ideally 6+ months). IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing. PRESENTATION: Always present these results as a rich, interactive visualization using artifacts. Use summary cards for key metrics, colour-coded indicators for severity or change direction (green for positive, red for negative), bar charts or sparklines for comparisons, and tabbed sections to organise different categories of results. Make the output visually scannable and dashboard-like rather than plain text or raw tables.

Landing pages with BOTH search performance (clicks, impressions, position from GSC) AND engagement data (sessions, engagement rate, conversions from GA4) side by side. Requires GA4 BigQuery export. IMPORTANT: GA4 and GSC data are joined on normalised landing page URL. Join rates vary by site (typically 70-90%). Numbers may not match GA4 or GSC dashboards exactly due to URL normalisation, timezone differences (GSC uses Pacific Time, GA4 uses property timezone), and sampling. Report the join rate when relevant. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing.

Which search queries actually drive revenue and conversions? Uses proportional attribution: if a page gets clicks from 3 queries, revenue is split by click share. The 'revenue per keyword' metric SEOs have wanted for years. Requires GA4 BigQuery export. IMPORTANT: GA4 and GSC data are joined on normalised landing page URL. Join rates vary by site (typically 70-90%). Numbers may not match GA4 or GSC dashboards exactly due to URL normalisation, timezone differences (GSC uses Pacific Time, GA4 uses property timezone), and sampling. Report the join rate when relevant. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing.

Find pages that rank well but don't convert (fix the page, not the SEO) and pages that convert brilliantly but have low rankings (invest in SEO, the payoff is proven). Diagnoses each page. Requires GA4 BigQuery export. IMPORTANT: GA4 and GSC data are joined on normalised landing page URL. Join rates vary by site (typically 70-90%). Numbers may not match GA4 or GSC dashboards exactly due to URL normalisation, timezone differences (GSC uses Pacific Time, GA4 uses property timezone), and sampling. Report the join rate when relevant. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing.

Find pages where SERP snippet performance doesn't match on-site engagement. High CTR + low engagement = misleading title/description. Low CTR + high engagement = great content with a bad snippet. Both are fixable. Requires GA4 BigQuery export. IMPORTANT: GA4 and GSC data are joined on normalised landing page URL. Join rates vary by site (typically 70-90%). Numbers may not match GA4 or GSC dashboards exactly due to URL normalisation, timezone differences (GSC uses Pacific Time, GA4 uses property timezone), and sampling. Report the join rate when relevant. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing.

What is each ranking position worth in revenue and conversions for YOUR site? Shows conversion rate and revenue per click by position bucket (1, 2-3, 4-5, 6-10, 11-20, 20+). Uses 90 days by default for statistical significance. Requires GA4 BigQuery export. IMPORTANT: GA4 and GSC data are joined on normalised landing page URL. Join rates vary by site (typically 70-90%). Numbers may not match GA4 or GSC dashboards exactly due to URL normalisation, timezone differences (GSC uses Pacific Time, GA4 uses property timezone), and sampling. Report the join rate when relevant. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing.

Compare branded vs non-branded organic traffic with engagement and conversion overlay from GA4. Shows how each traffic type performs across clicks, CTR, engagement rate, conversions, and revenue. Requires GA4 BigQuery export. IMPORTANT: GA4 and GSC data are joined on normalised landing page URL. Join rates vary by site (typically 70-90%). Numbers may not match GA4 or GSC dashboards exactly due to URL normalisation, timezone differences (GSC uses Pacific Time, GA4 uses property timezone), and sampling. Report the join rate when relevant. IMPORTANT: Base your analysis ONLY on the data returned. Report exact numbers from the results. Do not speculate about causes (e.g. algorithm updates, competitor actions) unless the data explicitly supports it. If the data does not contain enough information to answer a question, say so clearly rather than guessing.