Helps you decide when and how to split a Claude skill between SKILL.md and reference files instead of keeping everything in one file. The default advice is stay monolithic until you have real evidence otherwise, usually around 400 lines or when evals show wasted context. Three patterns that actually work: variant branches (one cloud provider per file), workflow versus lookup data (procedures in SKILL.md, tables in references), and common path versus edge cases. Includes specific anti-patterns like topic splits that sound clean but force multiple loads per invocation. Useful when refactoring an existing skill or when you catch yourself splitting just to hit a line count target.
npx -y skills add samber/cc-skills --skill skill-progressive-disclosure-design --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
leonxlnx/taste-skill
supercent-io/skills-template
supercent-io/skills-template