zenml-io

Author ZenML pipelines: @step/@pipeline decorators, type hints, multi-output steps, dynamic vs static pipelines, artifact data flow, ExternalArtifact, YAML configuration, step caching (enable_cache at pipeline, step, and YAML level), DockerSettings and…

Migrate Apache Airflow DAGs, operators, and workflows to idiomatic ZenML pipelines. Handles concept mapping (DAG→pipeline, operator→step, XCom→artifact), code translation, scheduling, retry config, Docker settings, and flags unsupported patterns (trigger…

Migrate Kedro pipelines and projects to idiomatic ZenML pipelines. Handles concept mapping (node->step, Pipeline->pipeline, Data Catalog->explicit boundary steps plus artifacts, params:->typed parameters), catalog analysis, code translation,…

Migrate Prefect flows, tasks, and deployment patterns to idiomatic ZenML pipelines. Handles concept mapping (`@flow`→`@pipeline`, `@task`→`@step`, result persistence→artifacts), dynamic-execution analysis, code translation, scheduling, retries, Blocks/secrets…

Implements ZenML quick wins to enhance MLOps workflows. Investigates codebase and stack configuration, recommends high-priority improvements, and implements metadata logging, experiment tracking, alerts, scheduling, secrets management, tags, git hooks, HTML…

Migrate Argo Workflows, WorkflowTemplates, ClusterWorkflowTemplates, and CronWorkflows to idiomatic ZenML pipelines. Handles concept mapping, YAML-to-Python translation, scheduling, retries, Kubernetes-native pattern analysis, and flags unsupported patterns…

Migrate Azure Machine Learning SDK v2 pipelines, components, environments, and schedules to idiomatic ZenML pipelines. Handles concept mapping (`@pipeline` -> `@pipeline`, `@command_component` -> `@step`, `Environment(...)` -> `DockerSettings(...)`, AzureML…

Migrate Dagster assets, ops, graphs, jobs, and software-defined asset workflows to idiomatic ZenML pipelines. Handles concept mapping (asset->step output, job->pipeline, IOManager->artifact store/materializer + explicit IO steps), asset-boundary planning,…

Add or change a Kitaru framework adapter that records native agent runs or supports bounded replay. Use for Python adapter distributions under plugins/packages or TypeScript adapter packages under packages, not trace importers or core API work.

Kitaru just recipes, CLI structure and structured-output contract, analytics events, and PR-description conventions. Use when running project commands, adding CLI commands or analytics events, or writing a PR description.

Add or change a separately packaged Kitaru trace importer that normalizes provider exports into imported sessions. Use for importer packages under plugins/packages, not recording adapters or unrelated SDK, API, or server work.

Discover dependencies and prepare or execute Kitaru core and plugin releases, including version proposals, Kitaru UI selection, release PRs, ordered tag commands, artifact verification, and recovery. Use when a user asks what a release depends on or wants to…

Kitaru test layout, CI workflows, and release-workflow behavior. Use when adding or debugging tests on any surface (CLI, server, task, worker, MCP, plugins), changing CI, or explaining what a release tag triggers.

Discover dependencies and prepare or execute Kitaru core and plugin releases, including version proposals, Kitaru UI selection, release PRs, ordered tag commands, artifact verification, and recovery. Use when a user asks what a release depends on or wants to…

Kitaru documentation surfaces, link rules, and accuracy rules. Use when editing docs under docs/book, generated SDK or CLI reference, docs redirects, example READMEs, or docs CI.

Add, reuse, or change a frontend-specific Kitaru REST response under /api/v1/ui and its OpenAPI contract in zenml-frontend-monorepo. Use when a dashboard screen needs a purpose-built data shape, not for ordinary reusable resources or UI bundle releases.

Select a supported Kitaru adapter or build a project-local one for an unsupported Python or TypeScript agent framework. Use when a user wants to record or replay framework-native agent runs in Kitaru, needs a custom adapter, has no supported Kitaru…

Build and validate a custom Kitaru trace importer when a provider, observability platform, export format, or agent framework has no suitable built-in importer. Use when a user wants to map provider traces into Kitaru sessions and nodes, add bounded provider…

Guide users from their own agent code or recorded traces through Kitaru setup, session import or recording, human review, an accepted behavior, a versioned cohort, and evaluator selection, then hand one bounded change to the replay-experiment skill. Use when…

Guide a human through checking one evaluator against criterion-specific Kitaru investigation verdicts, inspecting disagreements, improving on development cases, and assessing a frozen configuration on held-out cases. Use when a user asks whether an evaluator…

Guide the ZenML Pro hosted Kitaru onboarding tour from preloaded traces through human review, one reusable evaluator, and one bounded replay. Use only inside the controlled hosted onboarding runner. Resume exact durable workspace state, handle existing agents…

Run and interpret one safe, bounded Kitaru replay comparison against an accepted cohort and exact evaluators. Use when a user wants to replay a cohort, test or compare a model, prompt, system prompt, parameter, agent version, or tool policy, supervise an…

Give first-time users a short, value-first Kitaru tour with the PydanticAI returns agent example in the Kitaru repository. Use when someone has no agent or traces of their own, arrives from Kitaru onboarding, asks for a demo, tutorial, quickstart, or guided…

Use when cutting a release of the kitaru-skills repository — pushing develop to main, bumping the kitaru plugin version, tagging a version, or publishing a GitHub Release for the Claude Code marketplace.

Add or import a blog post from Markdown or Notion; prepare content, metadata, and assets, including the cover via the figma-blog-cover skill. External actions require task authorization. Skip ordinary edits to existing posts.

Create a blog post's cover in Figma from the Blog Cover / 16:9 component (or a Kitaru-vs-X comparison card from the VS template), export it, convert to AVIF + JPEG, upload to R2 and print the mainImage / seo.ogImage frontmatter. Can also add a missing…

Use for website route, template, design primitive, or build/runtime changes. Read the relevant architecture and validation reference. Skip prose-only edits.

Add or import a blog post from Markdown or Notion; prepare content, metadata, and assets, including the cover via the figma-blog-cover skill. Skip ordinary edits to existing posts.

Upload content images or assets to R2 when authorized; verify URLs and provide references. Skip UI assets stored in public/images.

Use for website route, template, design primitive, or build/runtime changes. Read the relevant architecture and validation reference. Skip prose-only edits.

Upload images and assets to ZenML's Cloudflare R2 bucket. Use when adding new images to blog posts, content pages, marketing data files, or any content that needs an R2-hosted URL. Handles uploading, key generation, and prints paste-ready frontmatter.…

Use for ZenML tests, PRs, migrations, docs, integrations, models, orchestrators, server, storage, or webhooks. Read only relevant sections.

Write or review Pydantic `Field(description=...)` text for ZenML stack component configs. Use when adding, editing, or reviewing config fields in `src/zenml/integrations/*/flavors/` or any `StackComponentConfig` subclass, or when…

Backport docs/examples changes to a pre-existing ZenML release. Use when changes merged to `develop` need to be reflected in a live release version. Triggers include "backport", "cherry-pick to release", "update release docs", or when docs/examples changes…

Guide for writing Kitaru durable workflows and operational control paths. Use when creating or refactoring Kitaru flows, checkpoints, waits, logging, artifacts, tracked LLM calls, replay/resume/retry flows, KitaruClient usage, CLI commands, MCP operations, or…

Scope and validate whether an agent workflow is well-suited for Kitaru's durable execution model, then design the flow architecture — checkpoint boundaries, wait points, replay anchors, artifact strategy, operator surface, and MVP scope. Runs a structured…

Scope and validate whether an agent workflow is well-suited for Kitaru's durable execution model, then design the flow architecture — checkpoint boundaries, wait points, replay anchors, artifact strategy, operator surface, and MVP scope. Runs a structured…

Review and complete new changelog entries after automated PR creation. Use when there's a new changelog PR with entries that have placeholder URLs or empty fields that need review. Triggers on phrases like "review changelog", "complete changelog entries",…