One-click install
npx skills add https://github.com/aircrushin/promptMinder --skill agent-sdk-aircrushin
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-sdk
Source: https://github.com/aircrushin/promptMinder/tree/main/.claude/skills/agent-sdk
Command: npx skills add https://github.com/aircrushin/promptMinder --skill agent-sdk-aircrushin

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides comprehensive expertise and documentation for the Claude Agent SDK, helping developers navigate complex APIs, configure agents, implement tools, and manage permissions efficiently.

Core Features & Use Cases

  • API Reference & Examples: Get precise details on core SDK functions like query(), tool(), and createSdkMcpServer() with accurate TypeScript examples.
  • Agent Configuration & Best Practices: Learn how to define subagents, configure various options, and apply best practices for building robust and secure AI agents.
  • Advanced Features: Understand and implement advanced functionalities such as MCP servers, hook events, permission modes, and file checkpointing.
  • Use Case: A developer is building a new AI agent and needs to integrate a custom tool. They can use this skill to get detailed guidance on tool() definition, input schemas, and MCP server configuration, complete with code examples.

Quick Start

Ask the agent-sdk skill for help on configuring a custom MCP tool.

Frequently Asked Questions about agent-sdk

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

FAQPage Schema
How do I configure a custom MCP server using the Claude Agent SDK?

To configure a custom MCP server using the Claude Agent SDK, use the createSdkMcpServer() function. This approach provides precise TypeScript examples and API references for defining tools and managing server integration efficiently.

How do I define a custom tool with TypeScript in the Claude Agent SDK?

Defining a custom tool in the Claude Agent SDK requires using the tool() function. You must provide an input schema and leverage TypeScript code examples to ensure robust agent configuration and accurate execution.

What are the available permission modes for Claude Agent SDK development?

Claude Agent SDK development includes various permission modes and hook events to manage agent security. These advanced functionalities allow developers to apply best practices and control tool execution within their AI agents.

Does the Claude Agent SDK support file checkpointing for AI agents?

Yes, the Claude Agent SDK supports file checkpointing as an advanced feature. This allows developers to implement state recovery and robust execution tracking when building and configuring complex AI agents.

What is the best way to structure subagents in the Claude Agent SDK?

The best way to structure subagents in the Claude Agent SDK is by applying documented configuration options and best practices. This ensures robust and secure AI agents by properly defining tool execution and API usage.