Testing a Skill Before You Ship It
Most skills break in two predictable ways: the description doesn't trigger, or the body misfires once invoked. Both are catchable before users…
Category: Guides
In-depth how-to articles on Skills, Prompts, MCP, and Claude Code. The reference material behind the downloadable Skills and Prompts.
Bundling Scripts and Reference Docs in a Skill
A skill is more than a SKILL.md file. The folder around it can carry executable scripts, reusable templates, and deep-dive reference docs…
How Skill Trigger Matching Actually Works
When the agent looks at your installed skills and decides which one — if any — to invoke, what is it actually…
Claude Code Slash Commands: A Working Reference
Every slash command in Claude Code, what it actually does, when to reach for it, and the small handful you'll use 80%…
Build Your First MCP Server in 30 Minutes
A working MCP server, end to end, in 30 minutes. We'll expose two tools, run it locally, and connect it to Claude…
What is MCP? A Practical Introduction
MCP — the Model Context Protocol — is the standard way to connect AI assistants to external tools, data, and systems. This…
System vs User Prompts: When to Use Which
The split between system and user prompts is the single most under-used lever in prompt design. This guide explains the difference, when…
Prompt Engineering 101: 12 Patterns That Consistently Work
A pragmatic, no-buzzwords guide to the prompting patterns that survive contact with real production work — from few-shot to constraint stacking to…
Writing Skill Descriptions That Actually Trigger
Your skill's description is the only thing the model sees at routing time. This guide breaks down what makes a description fire…
Anatomy of a Skill: Field-by-Field Reference for SKILL.md
A skill is a folder with a SKILL.md file at the top. This guide walks every field of the frontmatter, why it…