The Agent Skills Directory

[SAFE]: The skill operates entirely within the context of a conversation. It instructs the agent to ask questions in 'clusters', wait for user responses, and eventually generate a markdown file based on those responses. There are no automated commands or scripts that interact with the system or network independently of the standard agent tools. The use of $ARGUMENTS is standard for receiving user input in this environment and is used here to identify optional research paths which the agent is instructed to 'read first' if provided, mirroring standard document-processing tasks.

plan-create-prd