SKILL.md
This is an example skill, showcasing forked contexts. With forked context, the agent will execute in a fresh context, using the system prompt of the agent. It will pass the skill as context, along with arguments at the end, or replacing $ARGUMENTS with the arguments passed when the skill is called.
Use skills like this to make it so that subagents are prompted "perfectly"—there's the prompt from the agent, the system prompt from the agent, and then the pre-made prompt from the skill.
Skills are kinda like one-off agents that don't have to be used frequently. Subagents have fresh context by default anyway, though they can also be used in a way so that they DON"T have fresh context.