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.
Installs into .claude/skills of the current project.
Are you the author of Llm Agent Reference?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/mik2win-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.
