Turns natural language data questions into production-ready SQL with proper CTEs, dialect-specific optimizations, and performance considerations baked in. It asks which SQL flavor you're using (Snowflake, BigQuery, Postgres, etc.) then structures queries with early filtering, appropriate joins, and partition awareness. The workflow is practical: it parses your request, discovers schema if you have a warehouse connected, writes the query with meaningful CTE names and comments, then explains each section and how to modify it. The best part is it actively avoids the usual mistakes like SELECT *, correlated subqueries where joins would work, and exploding many-to-many joins. Good for both quick aggregations and complex cohort analyses where you need someone who remembers the performance gotchas.
npx -y skills add anthropics/knowledge-work-plugins --skill write-query --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
juliusbrussee/caveman
mattpocock/skills
shadcn/improve
obra/superpowers
forrestchang/andrej-karpathy-skills
vercel-labs/skills