Llm Agent Reference

---
name: llm-agent-reference
description: >-
  Worked examples for building LLM/agent features in Ruby — prompt construction, tool/
  function calling, structured output, retries/guardrails, token handling, and testing.
  CONSULT when implementing or reviewing agent/LLM code (files matching *agent*/*llm* or
  config/prompts) and you need the idiomatic example. Reference loaded on demand — the
  always-apply rules live in the `llm-agent-practices` rule.
allowed-tools:
  - Read
  - Grep
  - Glob
---

# LLM agent practices — worked examples

Companion to the `llm-agent-practices` rule. For worked examples (prompt patterns, tool use,
structured output, guardrails, token handling, testing), read `references/llm-agent.md` in
this skill's folder.