Claude Skills.

You will learn how skills turn your repeated tasks into reusable, auto-triggering workflows. End state is one working skill for your most-repeated task, built, evaluated, installed, and trigger-tested. After this module you can build skills with the skill-creator, debug ones that don't fire, set boundaries so they don't hijack, and install pre-built skills from the ecosystem.

• Anthropic, "Agent Skills overview", the progressive-disclosure model, what the description field has to do, and the security guidance on untrusted skills: https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview
• Anthropic, "Skill authoring best practices", how to write the body once the description is right: https://platform.claude.com/docs/en/agents-and-tools/agent-skills/best-practices
• Claude Help Center, "How to create custom Skills", the claude.ai path, the zip layout, and the code-execution requirement: https://support.claude.com/en/articles/12512198-how-to-create-custom-skills
• Claude Help Center, "Provision and manage Skills for your organization", the Team and Enterprise admin route: https://support.claude.com/en/articles/13119606-provision-and-manage-skills-for-your-organization
• Anthropic Academy course "Introduction to Agent Skills": https://anthropic.skilljar.com
• Ruben Hassid, "Claude Skills": https://ruben.substack.com/p/claude-skills
• Community skill collections. Read for ideas, audit before installing (see the third-party skills warning in the lesson): https://github.com/ComposioHQ/awesome-claude-skills and https://github.com/VoltAgent/awesome-agent-skills