Prisma Orm Setup logo

Prisma Orm Setup

Organization
prisma
prisma-orm-setup

Set up Prisma ORM in an application, connect its database, or troubleshoot the connection of an existing Prisma 6, 7, or 8 app. Defaults new applications to Prisma ORM 8 and loads the package-owned prisma-8 skill; keeps existing Prisma 6/7 apps on their version with provider references for PostgreSQL, MySQL, SQLite, SQL Server, CockroachDB, MongoDB, and Prisma Postgres.

Overview

Publisherprisma
Repositoryskills
Skill nameprisma-orm-setup
Stars
66
Forks
7
Bundled files
8
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 8 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by prisma on GitHub. Read the source before you install it.

Installation

Install the Prisma Orm Setup AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/prisma/skills/tree/main/prisma-orm-setup
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/prisma/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/prisma-orm-setup .claude/skills/prisma-orm-setup
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Prisma Orm Setup in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Prisma Orm Setup on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Prisma Orm Setup is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Prisma ORM setup

This skill owns ORM version selection for setup and connection work. Preserve the application's ORM version and intended database. A connection repair does not require a major upgrade.

New applications default to Prisma ORM 8. Detailed Prisma 8 configuration, queries, migrations, and runtime code belong to the versioned prisma-8 skill shipped with the ORM package.

1. Detect the starting point

Read the package manifest, lockfile, Prisma configuration, schema, and application imports. Identify the ORM version, database provider, and runtime. The CLI version alone does not identify the application's version: a Prisma 8 CLI can coexist with a legacy client, so inspect @prisma/client, @prisma/prisma7, and the schema and configuration.

Starting pointPath
Prisma 8 applicationStep 4, without reinitializing
New application without a version choiceStep 3
Prisma 6 or 7 application, or an explicit earlier majorStep 5

For a new application, check the selected Prisma 8 release's provider support and runtime requirements before installing. If the provider is unsupported, explain the limitation and offer an explicitly selected earlier version. Keep the requested database; do not silently fall back or invent a supported target.

Use an existing database when supplied. Load prisma-postgres-setup only when Prisma Postgres is needed and no connection has been selected yet; return here once connected.

2. Handle requested major upgrades separately

When the user requests a major upgrade, load a workflow that supports the source version and provider. For PostgreSQL 7-to-8, use the Prisma migration guide; for MongoDB 6-to-8, use prisma-mongodb-upgrade. Other providers need an explicitly supported migration path. prisma-upgrade-v7 covers 6 to 7; the package-owned prisma-8 upgrade reference covers updates within 8.

3. Bootstrap a new Prisma 8 application

Check the selected release's runtime requirements and initialization guide. Resolve and pin a published Prisma CLI 8 release, including its prerelease suffix if needed; verify its version before initialization. Do not rely on a floating latest remaining version 8.

Use the project's package manager to run the installed CLI. For PostgreSQL and Prisma schema language authoring:

bash
prisma orm init --yes --target postgres --authoring psl

Use the supported target for the selected provider. Preserve existing application files and connection configuration; do not let setup provision an unrelated database. Verify that the resolved ORM package is version 8 before proceeding.

4. Load the installed Prisma 8 guidance

Run the installed CLI through the project's package manager:

bash
prisma skills sync

Then read the synced prisma-8/SKILL.md, for example .agents/skills/prisma-8/SKILL.md, and follow its preconditions and selected references. Syncing alone does not load the instructions. If the package-owned guidance cannot be loaded, report the blocker. Continue with step 6.

5. Set up or repair an earlier version

For a new setup that explicitly selects an earlier version, pin packages to that major and use its runtime requirements. Keep the CLI, client, and SQL adapter releases compatible. Existing dependencies need not change for a connection repair.

  • Prisma 7 SQL: use the provider reference below and client setup.
  • Prisma 6 MongoDB: use MongoDB setup. SQL driver adapters do not apply.
  • Prisma 6 SQL: preserve its generator, schema URL, and client initialization. Use the provider's connection details below and the Prisma 6 documentation; do not copy the Prisma 7 configuration or adapter examples into it.
DatabaseReference
PostgreSQLPostgreSQL
MySQL / MariaDB / PlanetScaleMySQL
SQLite / TursoSQLite
Microsoft SQL Server / Azure SQLSQL Server
CockroachDBCockroachDB
MongoDB / Atlas on Prisma 6MongoDB
Prisma Postgres with Prisma 7Prisma Postgres

The Prisma 7 SQL examples were verified with Prisma 7.10.0; the MongoDB examples with Prisma 6.19.3.

6. Connect and verify

The CLI and the application can load different environment files. Load the intended environment for each without printing secrets, and keep credentials in ignored environment files or the host's secret configuration. For SQL adapters, make the adapter's runtime options address the same database as the CLI connection URL.

For an existing app, preserve schema, migrations, and generator configuration unless the requested work requires changes. Diagnose the connection before running schema-changing commands.

Run the project's relevant checks and a read-only query through the application's client against the intended database. Report the ORM version, the loaded prisma-8 skill version where applicable, and the query result. Package installation or a successful skill sync alone is not a completed setup.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Prisma Orm Setup AI skill do?

Set up Prisma ORM in an application, connect its database, or troubleshoot the connection of an existing Prisma 6, 7, or 8 app. Defaults new applications to Prisma ORM 8 and loads the package-owned prisma-8 skill; keeps existing Prisma 6/7 apps on their version with provider references for PostgreSQL, MySQL, SQLite, SQL Server, CockroachDB, MongoDB, and Prisma Postgres.

Why use Prisma Orm Setup on TypingMind?

Because you install it once and use it with any model. Prisma Orm Setup is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Prisma Orm Setup in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/prisma/skills/tree/main/prisma-orm-setup. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Prisma Orm Setup?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Prisma Orm Setup?

As many as you like. As long as a model supports skills, you can use Prisma Orm Setup with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Prisma Orm Setup AI skill free?

Yes. It is published on GitHub by prisma under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇