skill-creator

To package modular AgentSkills, use a skill initializer to scaffold a new Skill Unit, customize the SKILL.md frontmatter, define resource patterns like scripts and references, and run safe packaging checks to ensure standardized deployment.

A valid SKILL.md file requires standardized frontmatter to define the skill's metadata. This ensures lifecycle guidance and frontmatter standards are followed, keeping the file lean while enabling rich references when needed.

Yes, PyYAML is required as a dependency to parse and validate the SKILL.md frontmatter during the skill creation workflow, ensuring initialization and packaging checks process the YAML metadata correctly.

Organize self-contained AgentSkills by establishing a reusable skill scaffold that defines clear resource patterns for scripts, references, and assets, reducing boilerplate and enabling consistent deployment across instances.

Yes, progressive disclosure is supported to keep the SKILL.md body lean and practical. This approach allows you to structure essential information upfront while enabling rich references and assets when needed.

Run validation and packaging checks after customizing the SKILL.md file and before deployment. This ensures frontmatter standards and safe packaging checks are followed across Codex instances for reliable modular AgentSkills.