Explain Skills and Progressive Disclosure in an Agent

Explain what a skill means in an agent architecture, how it differs from an ordinary prompt, and how progressive disclosure can organize the information supplied to the agent. ### Constraints & Assumptions Use a generic architecture: a skill is a reusable task package containing instructions and optional references or tools. Do not assume a specific product's file format or loading implementation. ### Clarifying Questions How are skills discovered and selected? Which information is loaded initially? Who owns permissions and validation? What happens when a referenced document is untrusted or outdated? ### What a Strong Answer Covers Reusable procedure versus per-interaction instruction, staged loading, context and selection tradeoffs, and limits of what a skill can guarantee. ### Follow-up Questions How can too many skill descriptions harm selection? When should detailed references be loaded? Why does packaging a procedure not make every instruction in a retrieved document authoritative?