Write Query

anthropics/knowledge-work-pluginsOfficial

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.

skills.sh installs: 3.1K
GitHub stars: 35.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add anthropics/knowledge-work-plugins --skill write-query --agent claude-code

Installs into .claude/skills of the current project.

Files

/write-query - Write Optimized SQL

If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.

Write a SQL query from a natural language description, optimized for your specific SQL dialect and following best practices.

Usage

/write-query <description of what data you need>

Workflow

1. Understand the Request

Parse the user's description to identify:

Output columns: What fields should the result include?
Filters: What conditions limit the data (time ranges, segments, statuses)?
Aggregations: Are there GROUP BY operations, counts, sums, averages?
Joins: Does this require combining multiple tables?
Ordering: How should results be sorted?
Limits: Is there a top-N or sample requirement?

2. Determine SQL Dialect

If the user's SQL dialect is not already known, ask which they use:

SKILL.md on GitHub

Details

Repository: github.com/anthropics/knowledge-work-plugins
Category: Databases
First seen: Apr 16, 2026