Sql Queries
Turn business questions into dialect-correct SQL for reports and exploration when you are not a full-time data engineer.
Overview
SQL Queries is an agent skill most often used in Grow (also Build backend, Operate iterate) that generates dialect-aware SQL from natural language using your schema context.
Install
npx skills add https://github.com/phuryn/pm-skills --skill sql-queriesWhat is this skill?
- Four-step flow: schema intake, requirement clarification, optimized query generation, plain-English explanation and test
- Supports BigQuery, PostgreSQL, MySQL, Snowflake, and other dialects with performance notes for large datasets
- Reads uploaded schemas, diagrams, or documentation to infer keys and joins
- Commented SQL with alternative approaches when the data model allows
- Built for PMs and analysts translating natural language into production-ready queries
- 4-step workflow: schema, request, generate, explain and test
Adoption & trust: 1k installs on skills.sh; 12.3k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You know the business question but stall on joins, aggregations, and dialect-specific syntax across your warehouse or app database.
Who is it for?
Solo builders and PMs who own metrics and have schema docs or table lists but want faster, reviewed query drafts.
Skip if: Greenfield schema design without any table context, or environments where agents must not see production schemas without your redaction.
When should I use this skill?
Writing SQL, building data reports, exploring databases, or translating business questions into queries.
What do I get? / Deliverables
You receive commented, testable SQL with explained logic and performance notes ready to run in your chosen platform.
- Commented SQL query
- Plain-English logic explanation
- Validation and performance tips
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Product analytics and ad-hoc reporting sit in Grow/analytics as the canonical shelf for measuring what users do after ship. Analytics subphase covers querying warehouses and OLTP schemas to answer funnel, revenue, and usage questions.
Where it fits
Draft a weekly active-user and retention query for a investor update.
Prototype a revenue-by-plan query before hard-coding it into the admin API.
Investigate a spike in signups with a filtered aggregation across event tables.
Estimate whether existing tables can answer a pricing experiment question before building new instrumentation.
How it compares
Skill-side query generator from prose and schema—not an MCP database connector; you still run SQL in your own client.
Common Questions / FAQ
Who is sql-queries for?
Product managers, indie founders, and engineers who need accurate SQL from business questions and can supply schema or documentation.
When should I use sql-queries?
In Grow/analytics for dashboards and funnels; in Build/backend when defining reporting tables; in Operate/iterate when debugging data discrepancies; and whenever you explore a database with a natural-language question.
Is sql-queries safe to install?
Check the Security Audits panel on this Prism page; avoid pasting live credentials into the agent and prefer sanitized schema excerpts.
SKILL.md
READMESKILL.md - Sql Queries
# SQL Query Generator ## Purpose Transform natural language requirements into optimized SQL queries across multiple database platforms. This skill helps product managers, analysts, and engineers generate accurate queries without manual syntax work. ## How It Works ### Step 1: Understand Your Database Schema - If you provide a schema file (SQL, documentation, or diagram description), I will read and analyze it - Extract table names, column definitions, data types, and relationships - Identify primary keys, foreign keys, and indexing strategies ### Step 2: Process Your Request - Clarify the exact data you need to retrieve or analyze - Confirm the SQL dialect (BigQuery, PostgreSQL, MySQL, Snowflake, etc.) - Ask for any additional requirements (filters, aggregations, sorting) ### Step 3: Generate Optimized Query - Write efficient SQL that leverages your database structure - Include comments explaining complex logic - Add performance considerations for large datasets - Provide alternative approaches if applicable ### Step 4: Explain and Test - Explain the query logic in plain English - Suggest how to test or validate results - Offer tips for performance optimization - If you want, generate a test script or sample data ## Usage Examples **Example 1: Query from Schema File** ``` Upload your database_schema.sql file and say: "Generate a query to find users who signed up in the last 30 days and had at least 5 active sessions" ``` **Example 2: Query from Diagram Description** ``` "Here's my database: Users table (id, email, created_at), Sessions table (id, user_id, timestamp, duration). Generate a query for average session duration per user in January 2026." ``` **Example 3: Complex Analysis Query** ``` "Create a BigQuery query to analyze our revenue by region and customer tier, including year-over-year growth rates." ``` ## Key Capabilities - **Multi-Dialect Support**: Works with BigQuery, PostgreSQL, MySQL, Snowflake, SQL Server - **File Reading**: Reads schema files, SQL dumps, and data documentation - **Query Optimization**: Suggests indexes, partitioning, and performance improvements - **Explanation**: Breaks down queries for learning and documentation - **Testing**: Can generate test queries and sample data scripts - **Script Execution**: Create executable SQL scripts for your database ## Tips for Best Results 1. **Provide context**: Share your database schema or structure 2. **Be specific**: Clearly describe what data you need and any filters 3. **Mention database**: Specify which SQL dialect you're using 4. **Include constraints**: Mention data volume, time ranges, and performance needs 5. **Request format**: Ask for the query result format if you need specific output ## Output Format You'll receive: - **SQL Query**: Production-ready SQL code with comments - **Explanation**: What the query does and how it works - **Performance Notes**: Optimization tips and considerations - **Test Script** (if requested): Sample data and validation queries --- ### Further Reading - [The Product Analytics Playbook: AARRR, HEART, Cohorts & Funnels for PMs](https://www.productcompass.pm/p/the-product-analytics-playbook-aarrr) - [How to Become a Technology-Literate PM](https://www.productcompass.pm/p/how-to-become-a-technology-literate)