golem-annotate-agent-ts

Name: golem-annotate-agent-ts
Availability: InStock
Author: Soham

Adds prompt and description metadata to TypeScript agent classes and methods.

Updated May 17, 2026

Search Tags:#typescript #prompt engineering #tool calling #decorators #llm discovery #agent annotations #metadata documentation

Ready to run

npx skills add https://github.com/Rust-soham/golem-claw --skill golem-annotate-agent-ts-rust-soham

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: golem-annotate-agent-ts
Source: https://github.com/Rust-soham/golem-claw/tree/main/packages/golem/.agents/skills/golem-annotate-agent-ts
Command: npx skills add https://github.com/Rust-soham/golem-claw --skill golem-annotate-agent-ts-rust-soham

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Writing TypeScript agents without prompt and description annotations makes it harder for LLM-based systems to discover what the agent does and when to call specific methods.

Core Features & Use Cases

Agent-level documentation: Add a class-level description so the agent can be used as a discoverable tool.
Method-level prompting: Attach method prompts that tell an LLM when to call each method.
Method-level behavior descriptions: Add method descriptions that document inputs, outputs, and expected behavior for reliable tool use.
Use Case: You maintain an InventoryAgent with methods like checkStock and restock, and you want an LLM to correctly understand and invoke the right method based on user intent.

Quick Start

Ask the AI to annotate your TypeScript agent class and its methods with the appropriate @agent(), @prompt(), and @description() decorators for tool discovery.

Frequently Asked Questions about golem-annotate-agent-ts

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

FAQPage Schema

How do I add metadata to TypeScript agents for LLM tool discovery?▼

To add metadata to TypeScript agents for LLM tool discovery, you apply class-level @description and method-level @prompt/@description decorators. This annotates agent purpose and method execution guidance for intent matching.

What is the correct way to use decorators for TypeScript agent method prompting?▼

The correct way to use decorators for TypeScript agent method prompting is applying @prompt and @description directly to methods. This provides execution guidance and behavioral documentation, while avoiding invalid agent options like embedding description in @agent().

Why does my LLM fail to select the right method on my TypeScript agent class?▼

An LLM fails to select the right method on a TypeScript agent class when missing method-level @prompt annotations. Without discovery metadata, the system cannot match user intent to specific method execution guidance.

Can I put description text inside the @agent() decorator for TypeScript agents?▼

No, you cannot put description text inside the @agent() decorator for TypeScript agents. Embedding description in @agent() is an invalid agent option; class-level descriptions must use the separate @description decorator.

When do I need to annotate TypeScript agent classes with prompt and description metadata?▼

You need to annotate TypeScript agent classes with prompt and description metadata when maintaining agents with multiple methods, like an InventoryAgent, that an LLM must correctly understand and invoke based on user intent.