ml-pipeline
Designs and implements production-grade ML pipeline infrastructure: configures experiment tracking with MLflow or Weights & Biases, creates Kubeflow or Airflow DAGs for training orchestration, builds feature store schemas with Feast, deploys model registries, and automates retraining and validation workflows. Use when building ML pipelines, orchestrating training workflows, automating model lifecycle, implementing feature stores, managing experiment tracking systems, setting up DVC for data versioning, tuning hyperparameters, or configuring MLOps tooling like Kubeflow, Airflow, MLflow, or Prefect.
Install with Tessl CLI
npx tessl i github:jeffallan/claude-skills --skill ml-pipeline93
Does it follow best practices?
Evaluation — 87%
↑ 1.12xAgent success when using this skill
Validation for skill structure
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that excels across all dimensions. It provides comprehensive specific actions with named tools, includes a thorough 'Use when...' clause with natural trigger terms, and carves out a distinct MLOps infrastructure niche that won't conflict with general ML or coding skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'configures experiment tracking with MLflow or Weights & Biases', 'creates Kubeflow or Airflow DAGs', 'builds feature store schemas with Feast', 'deploys model registries', and 'automates retraining and validation workflows'. | 3 / 3 |
Completeness | Clearly answers both what (designs/implements ML pipeline infrastructure with specific tools) AND when (explicit 'Use when...' clause covering multiple trigger scenarios like building pipelines, orchestrating workflows, managing experiment tracking). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'ML pipelines', 'training workflows', 'model lifecycle', 'feature stores', 'experiment tracking', 'DVC', 'hyperparameters', 'MLOps', 'Kubeflow', 'Airflow', 'MLflow', 'Prefect'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused on MLOps infrastructure with specific tool names (MLflow, Kubeflow, Feast, Airflow, Prefect, DVC) that clearly differentiate it from general coding or data science skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality skill that exemplifies best practices: it's concise yet comprehensive, provides executable code templates, includes explicit validation checkpoints throughout the workflow, and uses progressive disclosure effectively with a clear reference table. The constraints section provides clear guardrails without being verbose, and the output format gives Claude specific deliverables to produce.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, avoiding explanations of concepts Claude already knows. Each section serves a clear purpose with no padding or unnecessary context about what ML pipelines are or how libraries work. | 3 / 3 |
Actionability | Provides fully executable, copy-paste ready code examples for MLflow logging, Kubeflow components, and data validation. The templates are complete with imports, error handling, and realistic parameter usage. | 3 / 3 |
Workflow Clarity | The core workflow is clearly sequenced with explicit validation checkpoints (step 2: 'halt and report on failures', step 6: 'run model evaluation gates'). The data validation code example includes explicit failure handling with raised exceptions. | 3 / 3 |
Progressive Disclosure | Excellent structure with a concise overview, clear reference table pointing to one-level-deep topic files, and well-organized sections. The reference guide table clearly signals when to load each detailed document. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.