prisma-orm-setup

Agent skill for Claude Code, Codex & Cursor from prisma/skills · updated

Databases Official

How to install prisma-orm-setup

$ npx skills add https://github.com/prisma/skills --skill prisma-orm-setup
Advertisement

What prisma-orm-setup does

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.

SKILL.md

View source

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 point Path
Prisma 8 application Step 4, without reinitializing
New application without a version choice Step 3
Prisma 6 or 7 application, or an explicit earlier major Step 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:

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:

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.
Database Reference
PostgreSQL PostgreSQL
MySQL / MariaDB / PlanetScale MySQL
SQLite / Turso SQLite
Microsoft SQL Server / Azure SQL SQL Server
CockroachDB CockroachDB
MongoDB / Atlas on Prisma 6 MongoDB
Prisma Postgres with Prisma 7 Prisma 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.

Advertisement

More in Databases

banner-designDesign banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with optional generated or supplied visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter/X, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist, gradient, bold typography, photo-based, illustrated, geometric, retro, glassmorphism, 3D, neon, duotone, editorial, collage.nextlevelbuilder/ui-ux-pro-max-skillsetup-gbrainSet up gbrain for this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy. (gstack)garrytan/gstackdeprecation-and-migrationManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code.addyosmani/agent-skillsbackup-setupSet up, check, or restore local claude-mem database snapshots. Use when the user says "set up backups", "back up my memories", "backup status", or "restore my database".thedotmack/claude-memcloud-syncSet up or check claude-mem cloud sync with cmem.ai Pro. Use when the user says "set up cloud sync", "sync my memories", "cmem pro", "cloud backup", "sync status", or wants their memory database backed up or synced to their cmem.ai account.thedotmack/claude-mem