add-tool

Register Python functions as callable tools with JSON schemas from type hints.

12|1|Updated Sep 7, 2025
One-click install
npx skills add https://github.com/jhd3197/Prompture --skill add-tool-jhd3197
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: add-tool
Source: https://github.com/jhd3197/Prompture/tree/main/.claude/skills/add-tool
Command: npx skills add https://github.com/jhd3197/Prompture --skill add-tool-jhd3197

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables the integration of custom functions and external APIs into LLM conversations, allowing them to perform actions and retrieve real-time data.

Core Features & Use Cases

  • Function Calling: Define and register Python functions that LLMs can invoke.
  • Schema Generation: Automatically create JSON schemas for tool parameters from Python type hints.
  • Provider Integration: Seamlessly works with various LLM providers that support tool use.
  • Use Case: An LLM agent needs to check the current weather. This Skill allows you to define a get_weather(city: str) function and register it, so the LLM can call it when a user asks "What's the weather in London?".

Quick Start

Register the get_weather function with the ToolRegistry and use it within a Conversation.

Frequently Asked Questions about add-tool

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

FAQPage Schema
How do I add callable tools to an LLM agent to fetch real-time data?

To add callable tools to an LLM agent, you define Python functions and register them with a tool registry. This allows the agent to invoke the functions dynamically and retrieve real-time external data during conversations.

Can I automatically generate JSON schemas for function calling from Python type hints?

Yes, you can automatically generate JSON schemas for function calling directly from Python type hints. This eliminates manual schema construction and streamlines the integration of external API parameters into LLM conversations.

How does schema generation work for integrating external APIs with multi-provider LLM frameworks?

Schema generation for external APIs works by parsing Python type hints to create callable tool definitions. These schemas are then integrated with multi-provider LLM frameworks to enable seamless function calling and response handling across platforms.

Does this tool support multi-provider LLM frameworks for function calling?

Yes, this tool supports multi-provider LLM frameworks for function calling. It seamlessly integrates with various LLM providers that support tool use, allowing dynamic agent behavior through programmatic tool invocation.

What is the best way to register a custom Python function for an LLM to invoke?

The best way to register a custom Python function for an LLM to invoke is by adding it to a ToolRegistry within a Conversation. This facilitates automatic schema generation and enables the LLM to call the function when needed.

When do I need to define callable tools for an LLM conversation?

You need to define callable tools for an LLM conversation when the agent must interact with external systems to perform actions. This is required when the agent needs to retrieve real-time data or trigger external APIs dynamically.