agent-sdk-definitions

Define Claude agents programmatically with TypeScript or Python using the AgentDefinition schema.

Updated Apr 12, 2026
One-click install
npx skills add https://github.com/gil00pita/lanify --skill agent-sdk-definitions-gil00pita
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-sdk-definitions
Source: https://github.com/gil00pita/lanify/tree/main/.agents/skills/agent-sdk-definitions
Command: npx skills add https://github.com/gil00pita/lanify --skill agent-sdk-definitions-gil00pita

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

For SDK-based applications, agents can be defined programmatically instead of as markdown files.

Core Features & Use Cases

  • Programmatic agent definitions using TypeScript and Python to configure agents inside code.
  • Includes an AgentDefinition schema with fields like description, prompt, tools, and model for precise control.
  • Supports SDK-based workflows, dynamic agent orchestration, and integration with Claude Agent SDK.

Quick Start

Create an AgentDefinition with a description and prompt in TypeScript or Python, then pass it to the Claude Agent SDK query function.

Frequently Asked Questions about agent-sdk-definitions

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

FAQPage Schema
How do I define Claude agents programmatically instead of using Markdown files?

You define Claude agents programmatically by creating an AgentDefinition schema in TypeScript or Python. This schema includes fields for description, prompt, tools, and model, which you then pass directly to the Claude Agent SDK query function.

What is an AgentDefinition schema in the Claude Agent SDK?

An AgentDefinition schema is a programmatic configuration object for the Claude Agent SDK. It uses fields like description, prompt, tools, and model to set up agent behavior directly within TypeScript and Python SDK applications.

Can I configure agent routing and tools dynamically with the Claude SDK?

Yes, you can configure agent routing and tools dynamically. The Claude Agent SDK supports dynamic agent orchestration by allowing you to programmatically set prompts and tools within the AgentDefinition schema in your TypeScript or Python code.

Does the Claude Agent SDK support both TypeScript and Python for agent creation?

Yes, the Claude Agent SDK supports both TypeScript and Python for defining agents. You can use the AgentDefinition schema in either language to programmatically configure prompts, tools, and models for your SDK applications.

When should I use programmatic agent definitions instead of Markdown files?

Use programmatic agent definitions for SDK-based applications requiring dynamic orchestration. If your workflow needs configurable prompts, tools, and routing directly in TypeScript or Python code, use the AgentDefinition schema instead of static Markdown files.