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.
name defaults to "world", so workflow run hello works
standalone.
Inputs
How It Runs
- Reads
name(default"world"). - Runs one agent
<Task>whose prompt is.smithers/prompts/hello.mdx, withnameinterpolated into the Markdown via{props.name}. - Returns the agent’s greeting.
.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
- You need research, planning, and a validated implementation: use
implementorresearch-plan-implement. - You want to author a brand-new workflow interactively: use
create-workflow.
Resume & retry
Runs are durable and resume withup --resume; since hello is a single task,
resuming just re-runs it if incomplete.