
If you're building skills for Claude, this is your starting point. It walks through the three-tier loading system (metadata, SKILL.md, bundled resources), explains when to use scripts versus reference docs versus assets, and pushes hard on keeping things concise since skills share context with everything else. The progressive disclosure patterns are especially useful: keep SKILL.md under 500 lines and split variant-specific details into separate files that Claude loads only when needed. It's prescriptive about structure but flexible about content, which feels right. Think of it as the spec for how to write good onboarding docs that don't waste tokens.
$ npx -y skills add anthropics/financial-services-plugins --skill skill-creator --agent claude-codeInstalls into .claude/skills of the current project.
This skill provides guidance for creating effective skills.
Skills are modular, self-contained packages that extend Claude's capabilities by providing specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific domains or tasks—they transform Claude from a general-purpose agent into a specialized agent equipped with procedural knowledge that no model can fully possess.
The context window is a public good. Skills share the context window with everything else Claude needs: system prompt, conversation history, other Skills' metadata, and the actual user request.
Sponsors