Skip to main content
hello is a preserved example, no longer installed by default: copy it from examples/init-pack/ for the smallest end-to-end workflow. It greets whoever you name via .smithers/prompts/hello.mdx.
With no arguments, name defaults to "world", so workflow run hello works standalone.

Inputs

How It Runs

  1. Reads name (default "world").
  2. Runs one agent <Task> whose prompt is .smithers/prompts/hello.mdx, with name interpolated into the Markdown via {props.name}.
  3. Returns the agent’s greeting.
The instruction lives in a Markdown prompt, so changing the behavior means editing .smithers/prompts/hello.mdx (e.g. ask for a haiku instead of a greeting) and re-running.

Output Shape

hello returns the task’s text output, the greeting; the run log records the invocation and result.

Use it when

  • You are learning Smithers and want the smallest end-to-end run.
  • You are scaffolding a new workflow and want a known-good single-task template.

Use something else when

Resume & retry

Runs are durable and resume with up --resume; since hello is a single task, resuming just re-runs it if incomplete.