The Agent Skills Directory

[Secure External Data Fetching]: The skill instructs the agent to fetch a JSON catalog from academy.claude.com, which is an official domain owned by the vendor (Anthropic). It includes explicit validation rules, such as checking for staleness and ensuring the content is treated as data rather than instructions, which aligns with security best practices for handling external content.
[Strict Hallucination Controls]: The instructions mandate that only URLs and titles fetched directly from the verified catalog be used, preventing the agent from providing incorrect or malicious links from memory.
[Minimalist Integration]: The skill is designed to be a non-intrusive supplement to existing answers, limiting recommendations to two items to maintain relevance and reduce noise.

claude-academy-guide