skill-creator

To create and test AI skills, you need to define the skill intent, draft the `SKILL.md` file, generate test cases, and run evaluations against baseline models. This process handles iterative development loops and provides structured feedback mechanisms for performance optimization.

AI skill optimization is the process of enhancing skill discoverability and triggering accuracy through automated prompt testing. It works by analyzing evaluation results using provided tools, refining skill descriptions, and running iterative development loops to improve overall performance.

No specific dependencies are required to build LLM skills as this capability operates independently. It guides you through defining intent, interviewing for requirements, and writing `SKILL.md` files without relying on external frameworks or platforms.

The best way to evaluate AI agent performance against baseline models is by generating specific test cases, running structured evaluations, and analyzing the results using provided tools. This approach facilitates iterative improvement based on performance metrics and user feedback.

AI skill descriptions fail to trigger accurately when they lack optimization through automated prompt testing. To resolve this, you should analyze evaluation results, refine the skill description, and run iterative development loops to improve triggering accuracy.