botify-tables-sql
Query Botify's data warehouse (crawl, logs, Search Console, AI visibility) through the Botify MCP tables_* tools using BigQuery Standard SQL, and turn the results into SEO and GEO (Generative Engine Optimization) analyses. Use this skill whenever the user asks for an SEO audit, a GEO/AI-bot audit, crawl budget analysis, log file analysis, Googlebot or GPTBot behavior, Search Console trends, AI visibility / citation analysis, or any question that requires querying Botify project data — even if they don't mention SQL or the tables tools explicitly. Also use it when the user mentions tables_query, tables_schema, tables_list, the "catalog." prefix, or Botify log tables.
Install
With your agent
Install OMGSkills skill "botify-hq/ai-plugins:skills/botify-tables-sql" into this agent's normal skills directory: call the OMGSkills MCP get_install_plan tool for your agent and run the script it returns (it installs only the pinned commit and verifies SKILL.md), and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.
Manual command
git clone https://github.com/botify-hq/ai-plugins /tmp/ai-plugins && ln -s /tmp/ai-plugins/skills/botify-tables-sql ~/.claude/skills/botify-tables-sqlFrom README
Botify Tables SQL — SEO & GEO analysis via the Botify MCP This skill explains how to reliably query Botify's BigQuery-backed data catalog through the MCP tables tools, and how to structure the queries for SEO and GEO analysis. The tools are deferred: always call toolsearch first (e.g. toolsearch(query="tables query schema Botify")) to load them before use. Every tables call requires organization and project slugs. If they aren't known from the conversation, call listprojects to enumerate accessible org/project pairs rather than guessing (a wrong slug returns "No access to this organization/project"). The connector occasionally times out with "The connector's server isn't responding" — simply retry the same call once or twice before treating it as a failure. Queries are priced in credits computed from bytes shuffled. Be mindful of bytes shuffled (e.g. through partitioning etc) to limit your footprint.