Agent Skills Fundamentals
Learn what AI agent skills are, how to design them, and how they work. Start here if you're new to building or using agent skills.
What are agent skills and why they matter
A beginner-friendly introduction to AI agent skills: what they are, why they're transforming how we work with AI, and how to think about them.
Agent skills glossary: skill, tool, MCP, plugin, agent, prompt
Plain-language definitions for the AI agent vocabulary that gets used loosely everywhere: what's a skill, what's a tool, how MCP fits in, how plugins differ, and what an agent actually is.
Skill design principles
Foundational principles for designing composable, predictable, and maintainable skill files including single responsibility and idempotency.
Testing and debugging agent skills
A practical guide to testing agent skills: unit tests, integration tests with mock LLM responses, snapshot tests, and debugging techniques.
How to design AI agent skills
A deep dive into the four pillars of skill design: clear descriptions, well-typed parameters, error handling, and predictable output.
Security Considerations for Agent Skills
A practical guide to securing agent skills: input sanitization, least privilege, sandboxing, secrets management, and audit logging.
How agents actually work under the hood
The think-act-observe loop, tool calling, and context windows explained without the hype. What's really happening when an AI agent does something for you.
Writing effective skill instructions
The words you use to describe a skill matter more than the code behind it. How to write instructions that agents actually follow.
When NOT to use an agent
Agents are powerful, but they're not the answer to everything. Sometimes a script, a form, or a human is the better choice. Here's how to tell the difference.
The cost of bad tool descriptions
Your agent keeps picking the wrong tool. The problem isn't the code, it's the description. Real examples of tool descriptions that fail and how to fix them.
Prompt engineering vs skill design
They sound similar but they solve different problems. When to write a better prompt and when to build a skill instead.
Agent memory patterns for non-developers
What 'memory' actually means for AI agents, why your assistant forgets things, and how to work with memory instead of fighting it.