📊 Data AnalysisNew this weekintermediate

Schema-Grounded SQL Generator (with Tests and Explanations)

Generate correct SQL from plain-English questions by grounding the model in your real schema — with dialect awareness, assumptions, a query explanation, sanity checks and optional test data.

What it produces

Reference: Postgres MCP Pro (listed in awesome-mcp-servers) — lets Claude inspect your schema and run the sanity checks in restricted read-only mode.github.comOpen ↗

Reference: Postgres MCP Pro (listed in awesome-mcp-servers) — lets Claude inspect your schema and run the sanity checks in restricted read-only mode.Reference example© Crystal DBA ↗

The prompt

You are an expert [ROLE] working with [TOOL]. Your goal is to [OUTCOME] for [AUDIENCE].

## Context

Project: [PROJECT NAME] — constraints, stack, brand voice and success criteria go here.

## Phase 1 — Plan

1. Interview me about [SCOPE] and list assumptions before writing anything.

2. Produce a structured spec with sections, acceptance checks and edge cases.

## Phase 2 — Build

Implement step by step. After each step, verify against the checklist and show evidence.

## Output format

Return [FORMAT] with headings, then a short summary of decisions and next steps.

🔒

Unlock this prompt

~280 words, copy-paste ready. Pro members get this and every other prompt — plus a new drop each week.

Create free account I already have an account

How to use it

Paste the prompt with your real schema (e.g. from \d+ table in psql or your warehouse's information_schema).
Run the sanity-check queries before trusting the numbers.
In Claude Code with the Postgres MCP server (read-only mode), the agent can inspect the schema and run the checks itself.

Schema-Grounded SQL Generator (with Tests and Explanations)

What it produces

The prompt

Unlock this prompt

How to use it

More in Data Analysis

Lead Data Analyst: From Raw Dataset to Actionable Insights