Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add zenml-io/skills --skill prefect-migrationgit clone --depth 1 https://github.com/zenml-io/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zenml-io/skills/prefect-migration)<a href="https://agentmods.dev/skills/zenml-io/skills/prefect-migration"><img src="https://agentmods.dev/badge/skills/zenml-io/skills/prefect-migration/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zenml-io/skills/prefect-migration"><img src="https://agentmods.dev/badge/skills/zenml-io/skills/prefect-migration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00257 | $0.04207 |
| Opus 5 | $0.00129 | $0.02103 |
| Sonnet 5 | $0.00051 | $0.00841 |
| Haiku 4.5 | $0.00026 | $0.00421 |
Grade A, and why
prefect-to-zenml-migration scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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_FASTis supported with caveats around already-running inline steps;CONTINUE_ON_FAILUREis 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:
- map cleanly,
- map with semantic differences, or
- require redesign.
The three mapping types
Every Prefect concept falls into one of these categories:
| Type | Meaning | Action |
|---|---|---|
| Direct | Clean or near-clean mapping exists | Translate automatically |
| Approximate | Similar concept exists, but behavior changes | Translate with caveats in the migration report |
| Absent | No trustworthy ZenML equivalent | Flag for human review with redesign suggestions |
See references/concept-map.md for the full mapping tables.
The Migration Workflow
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 392 lines · 257 tokens per session scan A f69a3aaed0f0
prefect-to-zenml-migration is a skill published in the GitHub repository zenml-io/skills (6 stars, last pushed 2mo ago), licensed MIT. It adds 257 tokens to every session and 4,207 once invoked, about $0.0013 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
mlops-automation
Automate an MLOps project with mise tasks, lefthook hooks, Docker images, GitHub Actions, and MLflow tracking on a SQL backend. Use when adding a task runner, git hooks, CI/CD, or experiment tracking to a working package.
mlops-prototyping
Structure reproducible Jupyter notebooks with a fixed section layout, hoisted configuration, and leakage-free scikit-learn pipelines. Use when exploring a dataset, training a first model, or preparing a notebook for promotion.
mlops-observability
Make an ML system a glass box with reproducible runs, MLflow dataset lineage, drift monitoring, alerting, and SHAP explanations. Use when a deployed model needs traceability, monitoring, alerting, or explanation.
mlops-industrialization
Convert notebook prototypes into a distributable Python package with a src layout, a domain/io/application split, and validated OmegaConf plus Pydantic configuration. Use when moving code out of notebooks or designing entrypoints.
mlops-initialization
Initialize a production-ready Python MLOps project with uv, git, mise, and a shared editor setup. Use when starting a new repository, writing its first pyproject.toml, or repairing an inconsistent project skeleton.
huggingface-hub
HuggingFace hf CLI: search/download/upload models, datasets.