The Agent Skills Directory

[SAFE]: The skill is a documentation resource providing prompt engineering guidance. It includes reference files on agentic patterns, anti-patterns, context design, and system prompt architecture.
[SAFE]: The skill uses only read-only tools (Read, Grep, Glob) to access its own documentation and provide users with guidance. No file-writing, network communication, or shell execution capabilities are requested or used.
[SAFE]: External links point to reputable sources such as Anthropic, OpenAI, and Vercel documentation. References to 'GPT-5' and other future models appear to be aspirational placeholders or typos in the documentation and do not pose a security risk.

agent-prompt