Guides
Foundational knowledge for understanding, designing, and building AI agent skills. Start here if you're new.
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.
Anatomy of a Well-Designed Skill
A deep dive into the four pillars of skill design: clear descriptions, well-typed parameters, thorough error handling, and predictable output, with annotated code examples and practical guidance.
Skill Design Principles
Foundational principles for designing agent skills that are composable, predictable, and maintainable, including single responsibility, idempotency, progressive disclosure, and when to split versus merge.
Testing and Debugging Skills
A practical guide to testing agent skills at every level: unit tests for logic, integration tests with mock LLM responses, snapshot tests for output stability, and debugging techniques for when things go wrong.
Security Considerations for Agent Skills
A practical guide to securing agent skills, covering input sanitization, least privilege, sandboxing, secrets management, and audit logging to build skills that are safe to deploy in production.
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.