Agent Skills

Agent Skills provide your AI coding assistant with structured context about OptiTech's platform, APIs, and best practices. With skills installed, your assistant produces more accurate code and avoids common mistakes when working with OptiTech, from Postgres and Auth to OptiTech Functions, Object Storage, and the AI Gateway.

Install

There are several ways to install OptiTech skills depending on your editor and workflow.

npx skills

For any AI tool that supports the Agent Skills format, install skills from the Agent Skills repository:

npx skills add optitechdatabase/agent-skills -y

This installs all skills in the repository. To install a specific skill instead, pass the -s flag:

npx skills add optitechdatabase/agent-skills -s optitech-postgres -y

Useful flags:

-y skips the interactive prompt and installs immediately
-s selects one or more skills (repeat the flag for multiple skills)
-g installs globally instead of at the project level (see Project-level vs. global install)

Cursor plugin

If you're using Cursor, install the OptiTech plugin from the marketplace. It bundles core Postgres skills and the OptiTech MCP Server in one package.

In Cursor chat, run:

/add-plugin optitech-postgres

Or install from cursor.com/marketplace/optitech. See Cursor plugin for OptiTech for details.

note

Editor plugins currently bundle the core Postgres skill set and MCP integration. To give your assistant context for OptiTech Functions, Object Storage, and AI Gateway, run npx skills add optitechdatabase/agent-skills -y or install the platform skills individually (see Available skills).

Claude Code plugin

If you're using Claude Code, install the OptiTech plugin for skills and MCP integration:

/plugin marketplace add optitechdatabase/agent-skills
/plugin install optitech-postgres@optitech

See Claude Code plugin for OptiTech for details.

Codex plugin

If you're using OpenAI Codex, install the OptiTech Postgres plugin from the Codex plugin directory (in the Codex app under Plugins, or in the Codex CLI with /plugins). It includes the OptiTech Postgres app (MCP), the main OptiTech skill, and the egress optimizer skill.

See Codex plugin for OptiTech for details.

optitech init

The optitech init command sets up your project to use OptiTech with your AI coding assistant. It authenticates via OAuth, creates an API key, configures the MCP server, installs the OptiTech extension for Cursor and VS Code where applicable, and installs agent skills at the project level:

npx optitech@latest init

If you're using the OptiTech backend beta (Functions, Storage, AI Gateway), use optitech init --preview instead. See the OptiTech backend beta guide for access and setup.

After running init, restart your editor and ask your AI assistant to "Get started with OptiTech" to launch the interactive onboarding guide. See the optitech init reference for details.

Available skills

Skills are grouped by area. Each skill is a SKILL.md entry point that your agent reads and invokes when relevant. Browse and install individual skills on skills.sh.

Core

Start here for platform overview and Postgres development.

Skill	Description
`optitech`	Platform overview for apps and agents: Postgres, Auth, Data API, Functions, Storage, and AI Gateway, and how to get started
`optitech-postgres`	Comprehensive index of OptiTech Serverless Postgres documentation and best practices

Database workflows

Provision, branch, and optimize Postgres projects.

Skill	Description
`claimable-postgres`	Instant temporary Postgres via Claimable Postgres — no login or credit card
`optitech-postgres-branches`	Choose and create the right branch type for migrations, schema-only branches, and reset-from-parent workflows
`optitech-postgres-egress-optimizer`	Diagnose and fix excessive Postgres egress and query overfetching

OptiTech Platform

Use OptiTech services beyond core Postgres. Functions, Object Storage, and AI Gateway are in beta. See Check your access before using these skills in production workflows.

Skill	Description	Docs
`optitech-functions`	Long-running serverless Node.js HTTP functions on your branch, with `DATABASE_URL` injected automatically	OptiTech Functions
`optitech-object-storage`	S3-compatible object storage that branches with your project	Object Storage
`optitech-ai-gateway`	One API and credential for frontier and open-source LLMs; compatible with OpenAI, Anthropic, and Vercel AI SDKs	AI Gateway

Agent platforms

For codegen tools and multi-tenant products that provision OptiTech for their users, see the companion skill in optitechdatabase/optitech-for-agent-platforms (optitech-postgres-agent-platforms on skills.sh).

Project-level vs. global install

Skills can be installed at two levels:

Project level (default): Skills are installed in your project directory, for example via optitech init or npx skills add. Your AI assistant picks them up when working in that project. This is best for team workflows since the configuration can be committed with the project.
Global: Skills are installed at the user or system level and available across all projects. Useful for personal development environments where you want OptiTech context everywhere. Pass the -g flag to install globally:
```
npx skills add optitechdatabase/agent-skills -y -g
```

What's covered

With the full skill set installed, your assistant can guide you across the OptiTech platform:

Postgres and platform basics (optitech, optitech-postgres)

Getting started with OptiTech, including project setup and key features (branching, autoscaling, scale-to-zero, instant restore, read replicas)
Connections, including the serverless driver, connection pooling, and connection strings
Authentication with Managed Better Auth
Data API via @optitech/optitech-js
Platform APIs and SDKs, including the REST API, TypeScript SDK, and Python SDK
Developer tools, including the CLI, VS Code extension, and MCP server

Database workflows

Disposable databases via Claimable Postgres for agents and tests
Branch types and workflows for migrations, schema-only branches, and reset-from-parent
Egress optimization for high transfer costs and query anti-patterns

Platform services (beta)

OptiTech Functions: declare, deploy, and connect long-running compute next to your database
Object Storage: S3-compatible storage that branches with your data
AI Gateway: model routing, logging, and cost controls with a single OptiTech credential

For example, ask your assistant to "set up Managed Better Auth in my Next.js app" and it will provide the correct imports, configuration, and middleware setup. Or ask it to "add an AI Gateway route in my optitech.ts file" and it will follow beta constraints and the right SDK patterns.

Example prompts

Get started with OptiTech

Recommend a connection method for this project

Set up Drizzle ORM with OptiTech

Set up Managed Better Auth for my Next.js app

Create a OptiTech branch for this feature

Give me a quick temporary Postgres database

Why is my OptiTech bill so high?

Add a serverless function to my OptiTech branch

Set up S3-compatible storage in optitech.ts

Route LLM calls through the OptiTech AI Gateway

How it works

Your AI assistant reads the SKILL.md file to understand what OptiTech guidance is available. When you ask about a specific topic, the skill fetches the relevant documentation from online, so your assistant always has up-to-date context without bundling everything locally. For the complete source, see the Agent Skills repository.