Migrate Prefect to ZenML

This skill translates Prefect flows into idiomatic ZenML pipelines. It handles the full migration workflow: analyzing Prefect code, classifying each pattern, translating what maps cleanly, flagging what needs redesign, and producing a working ZenML project plus a migration report.

How migration works at a high level

Prefect and ZenML look similar at first glance because both are Python-first and both decorate functions. But the execution story is different.

• Prefect runs the flow body like regular Python at runtime. That means the flow can branch on task outputs, inspect states, submit new tasks dynamically, and use pause/suspend semantics while the run is already in progress.
• ZenML static pipelines compile a DAG before steps run. Step outputs are versioned artifacts, not ordinary in-memory values available during pipeline construction.
• ZenML dynamic pipelines recover part of Prefect's runtime flexibility, but they are still an approximation rather than a full state-model match. They default to STOP_ON_FAILURE; FAIL_FAST is supported with caveats around already-running inline steps; CONTINUE_ON_FAILURE is not supported for dynamic pipelines. They also support only a subset of orchestrators.

So migration is never just "rename @flow to @pipeline". The real job is to decide which Prefect behaviors:

1. map cleanly,
2. map with semantic differences, or
3. require redesign.

The three mapping types