agent-creator

Generate composable AI agent systems with DAG-based planning in NestJS.

17|1|Updated Dec 7, 2025

Search Tags:#planning #agent #orchestration #NestJS #state-persistence #DAG

Ready to run

npx skills add https://github.com/mhylle/claude-skills-collection --skill agent-creator-mhylle

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: agent-creator
Source: https://github.com/mhylle/claude-skills-collection/tree/main/skills/agent-creator
Command: npx skills add https://github.com/mhylle/claude-skills-collection --skill agent-creator-mhylle

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables developers to design and deploy composable AI agent systems in NestJS, standardizing the orchestration of planners, executors, evaluators, and state management to accelerate building sophisticated agent architectures.

Core Features & Use Cases

Create modular agent architectures (orchestrator, planner, executor, evaluators) for NestJS projects.
Build DAG-based plans that enable parallel execution and robust dependency handling.
Persist agent runs and plan/state data in PostgreSQL, with nested agent calls and tool integration.
Use cases include building research agents, data-processing pipelines, and automated task orchestration in enterprise apps.

Quick Start

To start, generate a new agent scaffold with the provided orchestrator/planner/executor templates and wire a simple tool for a proof-of-concept.

Frequently Asked Questions about agent-creator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I build composable AI agents in NestJS with DAG-based planning?▼

This approach automates the design and deployment of composable AI agent systems within NestJS projects. It standardizes the orchestration of planners, executors, and evaluators to accelerate building sophisticated agent architectures.

How does state persistence work for AI agent runs in NestJS?▼

State persistence for AI agent runs in NestJS works by persisting agent runs and plan data in PostgreSQL. It uses TypeORM entities to manage state persistence and handle nested agent calls during execution.

Can I use this approach to build a research agent in a NestJS application?▼

Yes, you can build a research agent in a NestJS application using this method. It provides a modular module structure with standardized prompts, evaluators, and tool registries to enable end-to-end agent orchestration for research tasks.

What is the best way to structure an orchestrator and executor in NestJS?▼

The best way to structure an orchestrator and executor in NestJS is to use a modular module structure that separates these components. This allows for DAG-based planning, standardized tool registries, and robust dependency handling.

Do I need PostgreSQL to handle nested agent calls and tool integration?▼

Yes, you need PostgreSQL to handle nested agent calls and tool integration. The architecture relies on PostgreSQL-backed state persistence to store agent runs and plan data during execution.