Back to Skills

generating-orm-code

jeremylongshore
Updated Today
17 views
712
74
712
View on GitHub
Metaaidata

About

This skill generates ORM models and database schemas for frameworks like TypeORM, Prisma, and SQLAlchemy. Use it when a developer requests to create entities, migrations, or a database schema from code. It supports bidirectional generation, converting between database structures and ORM code.

Documentation

Overview

This skill empowers Claude to automate the creation of Object-Relational Mapping (ORM) models and database schemas, significantly accelerating backend development. It handles generating code for various ORM frameworks, simplifying database interactions.

How It Works

  1. Identify ORM and Language: The skill parses the user's request to determine the target ORM framework (e.g., TypeORM, SQLAlchemy) and programming language (e.g., TypeScript, Python).
  2. Schema/Model Definition: Based on the request, the skill either interprets an existing database schema or defines a new schema based on provided model specifications.
  3. Code Generation: The skill generates the corresponding ORM model code, including entities, relationships, and any necessary configuration files, tailored to the chosen ORM framework.

When to Use This Skill

This skill activates when you need to:

  • Create ORM models from a database schema.
  • Generate a database schema from existing ORM models.
  • Generate model code for a specific ORM framework (e.g., TypeORM, Prisma).

Examples

Example 1: Generating TypeORM entities

User request: "Generate TypeORM entities for a blog with users, posts, and comments, including relationships and validation rules."

The skill will:

  1. Generate TypeScript code defining TypeORM entities for User, Post, and Comment, including properties, relationships (e.g., one-to-many), and validation decorators.
  2. Output the generated code, ready to be integrated into a TypeORM project.

Example 2: Creating a SQLAlchemy schema

User request: "Create a SQLAlchemy schema for an e-commerce application with products, categories, and orders."

The skill will:

  1. Generate Python code defining SQLAlchemy models for Product, Category, and Order, including relationships (e.g., many-to-one), data types, and primary/foreign key constraints.
  2. Output the generated code, ready to be used with SQLAlchemy.

Best Practices

  • Specificity: Be as specific as possible about the desired ORM framework and data model.
  • Relationships: Clearly define relationships between entities (e.g., one-to-many, many-to-many).
  • Validation: Specify validation rules to ensure data integrity.

Integration

This skill integrates with other code generation tools and plugins within Claude Code, allowing for seamless integration into existing projects and workflows. It can be used in conjunction with database migration tools to create and manage database schemas.

Quick Install

/plugin add https://github.com/jeremylongshore/claude-code-plugins-plus/tree/main/orm-code-generator

Copy and paste this command in Claude Code to install this skill

GitHub 仓库

jeremylongshore/claude-code-plugins-plus
Path: backups/skills-batch-20251204-000554/plugins/database/orm-code-generator/skills/orm-code-generator
aiautomationclaude-codedevopsmarketplacemcp

Related Skills

sglang

Meta

SGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.

View skill

evaluating-llms-harness

Testing

This Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.

View skill

llamaguard

Other

LlamaGuard is Meta's 7-8B parameter model for moderating LLM inputs and outputs across six safety categories like violence and hate speech. It offers 94-95% accuracy and can be deployed using vLLM, Hugging Face, or Amazon SageMaker. Use this skill to easily integrate content filtering and safety guardrails into your AI applications.

View skill

langchain

Meta

LangChain is a framework for building LLM applications using agents, chains, and RAG pipelines. It supports multiple LLM providers, offers 500+ integrations, and includes features like tool calling and memory management. Use it for rapid prototyping and deploying production systems like chatbots, autonomous agents, and question-answering services.

View skill