Support skill metadata to invoke subagents

### Describe the feature or problem you'd like to solve

An equivalent to claude's `context: fork` metadata in skills

### Proposed solution

https://code.claude.com/docs/en/skills#run-skills-in-a-subagent

I have a main agent file that acts as a workflow that delegates to subagents by explicitly stating in the agent file `"Step 1: Run subagent to follow instructions in prompt file at c:/path"`

My wish is to turn each step into a skill instead of a prompt, and it would be great for those skills to define "this should be run in a subagent", because those skills are effectively instructions to follow

### Example prompts or workflows

_No response_

### Additional context

_No response_

Comece lendo a documentação vinculada do Claude sobre skills executadas em um subagent e, em seguida, inspecione o comportamento existente de invocação de skills e subagents nesta CLI. O trabalho estará concluído quando uma skill puder declarar metadados solicitando a execução em um subagent e o workflow a invocar de acordo.

Escrita pelo modelo de indexação a partir do texto da issue.