mcpField
S
start

start

github.com/hainrixzData & databases2269 installsUpdated 6d ago
Repository

About start

start is a conversational skill for people beginning a project without a schema, migrations, or database. It asks plain-language questions about the project and its data needs, then recommends a database and outlines a starter model and next step.

Key features

  1. 01Seven-question conversational wizard
  2. 02Plain-language database recommendation
  3. 03Starter data model and diagram
  4. 04Optional project description prefill
  5. 05Clear suggested next step

Use cases

  1. 01Choose a starting database for a new project
  2. 02Outline entities and their relationships
  3. 03Turn project requirements into a starter model

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/hainrixz/claude-db --skill start

After installing, type/startin Claude Code to confirm it loaded.

Details

From the project README

/claude-db:start

The front door for someone with zero artifacts — no schema, no migrations, no database. It asks a short, plain-language wizard and ends with a concrete recommendation. No jargon: no "normalization", "cardinality", or "partition key" in the questions.

$ARGUMENTS = an optional one-line description. If present, pre-fill what you can and skip questions already answered.

How to run it

Follow the 7-question wizard in references/design-wizard.md (the canonical question set and the mapping from answers → paradigm/engine). Ask the questions conversationally, one cluster at a time, in plain words — roughly:

  1. What are you building, in one sentence?
  2. What are the main things you'll store (people, orders, messages, posts…)?
  3. How do those things relate to each other?
  4. What will you do most — look one thing up, list/search many, or crunch numbers over lots of rows?
  5. How much data and how many users, roughly (a hobby project, a startup, or huge)?
  6. Any hard rules — must never lose a record, must be fast above all, has to handle money or personal data?
  7. What are you comfortable running or paying for (managed/serverless vs self-hosted)?

What to produce

  • A plain-language recommendation: which database to start with, in one sentence, and why — defaulting to the boring, safe choice (usually Postgres) unless an answer genuinely points elsewhere.
  • A starter data model for the main things named, with the obvious relationships and the few constraints/keys that keep data clean — described in words, with a simple diagram.
  • A clear next step: "Save this as your schema, then run /claude-db:audit to score it" or "Run /claude-db:design for the full technical layer."

Honesty

  • Never fabricate prices, performance numbers, or row counts; describe trade-offs in plain qualitative terms.
  • If an answer is missing, ask — don't assume. Respond in the user's language (EN/ES).

Comments

Markdown supported