Plain English → correct SQL (with the gotchas)
Turn my request into SQL for {dialect: Postgres / MySQL / SQLite}. Given this schema: """ {paste CREATE TABLE statements or describe tables + columns} """ For the request: "{what I want to get}" Return: 1. The query, formatted and commented. 2. Any assumption you had to make about the schema or the intent. 3. Performance notes: which columns should be indexed for this to be fast, and any N+1 / full-scan risk. 4. One example of an input that would make this query return wrong results, if any.
fill the variables
This prompt has 3 variables. Pro fills them into a ready-to-paste prompt for you — no manual find-and-replace.
{dialect: Postgres / MySQL / SQLite}{paste CREATE TABLE statements or describe tables + columns}{what I want to get}
Unlock with Pro →when to use it
The schema block is what separates a usable query from a hallucinated one — always paste real DDL, not a description. Section 3 catches the classic 'works in dev, melts in prod' query by naming the missing index before you ship it. Section 4 surfaces off-by-one and NULL-handling traps (the ones that quietly return wrong numbers). Set the dialect explicitly; SQL that's valid in Postgres often isn't in MySQL.
tags
sqldatabaseperformance
source
Original · CC BY 4.0
more in Coding
Coding✓ tested
Senior code review (strict mode)
senior staff engineer running a merciless but fair review
Coding✓ tested
Debug by hypothesis, not by guessing
debugging partner who forms theories before touching code
Coding✓ tested
Generate tests from described behavior
test engineer who writes tests that would actually catch regressions