What problem does it solve? Designing and packaging AI agent skills requires consistent structure, valid frontmatter, and distributable packaging, which is error-prone when done manually. ## Core Features & Use Cases - Skill Scaffolding: Initialize new skill directories with a SKILL.md template and optional scripts, references, and assets folders using init_skill.py. - Validation & Packaging: Validate frontmatter, naming conventions, and structure, then package skills into distributable .skill zip files with symlink protection. - Design Guidance: Apply progressive disclosure principles, naming rules, and resource organization patterns when authoring skills. - Use Case: When you need to build a new skill for PDF processing, run the initializer to scaffold the directory, write the SKILL.md following the guidance, then validate and package it into a shareable .skill file. ## Quick Start Create a new skill named pdf-tools with scripts and references resources, then package it into a distributable .skill file.