skill-creator

To create an AI skill, follow a structured development process using the skill anatomy: define the `SKILL.md` frontmatter and body, and bundle resources like scripts, references, and assets to ensure modularity and effectiveness.

Progressive disclosure in AI skill development is a design principle that structures information so the AI agent receives necessary details at the right time, keeping the skill concise and reducing cognitive load.

You should structure AI agent extension documentation using `SKILL.md` for the core logic and anatomy, and provide a separate `README.user.md` to package and distribute the skill for external users.

Best practices for writing `SKILL.md` files include maintaining conciseness, managing degrees of freedom, applying progressive disclosure, and ensuring modular design for the AI extension.

You need to use bundled resources like scripts and references in skill development when your AI skill requires external logic execution or detailed supporting documentation beyond the core `SKILL.md` structure.

Building a modular AI skill does not require external dependencies; it relies on a structured internal design featuring `SKILL.md`, scripts, references, and assets to achieve effective AI agent extensions.