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.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, actionable skill body with executable templates, a clear sequenced workflow including a validation checkpoint, and excellent progressive disclosure through a reference table pointing to real bundle files. Minor conciseness padding and a few high-level workflow steps keep it just short of perfect.

Suggestions

Trim the opening 'Senior ML pipeline engineer specializing in...' framing and the bare Knowledge Reference tool-name list, which add tokens without new guidance.

Complete the Kubeflow pipeline template beyond the single train step (e.g., add the validate/register/deploy steps) so it is copy-paste ready rather than leaving a 'Chain additional steps here' note.

Tighten Core Workflow steps 4-6 with explicit pass/fail thresholds and retry cues (matching the Great Expectations checkpoint style) to remove implicit validation gaps.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete code and tight lists, but the opening 'Senior ML pipeline engineer specializing in...' line and the Knowledge Reference tool-name dump add minor padding. Falls above the mostly-efficient-but-tightenable anchor but not fully lean.	4 / 5
Actionability	Three concrete, mostly-executable code blocks (MLflow logging, KFP typed component, Great Expectations validation) cover common cases, but the Kubeflow template leaves chaining as a 'Chain additional steps here' note, a minor gap from fully copy-paste ready.	4 / 5
Workflow Clarity	The 6-step Core Workflow is clearly sequenced with an explicit validation checkpoint in step 2 ('halt and report on failures'), reinforced by the Great Expectations example; later steps (orchestrate, validate, deploy) are more high-level with implicit checkpoints, a minor gap.	4 / 5
Progressive Disclosure	A well-structured Reference Guide table routes to five verified one-level-deep reference files, each with a 'Load When' trigger; the body stays a concise overview with bulk detail appropriately split into separate files and easy to navigate.	5 / 5
	Total	17 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that pairs concrete tool-named capabilities with an explicit, comprehensive 'Use when' trigger clause. It is specific, distinctive, and complete with no over-claims or vague fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions with named tools ('configures experiment tracking with MLflow or Weights & Biases', 'creates Kubeflow or Airflow DAGs', 'builds feature store schemas with Feast', 'deploys model registries'), giving comprehensive coverage.	5 / 5
Completeness	Clearly answers both 'what' (designs/implements ML pipeline infrastructure plus concrete actions) and 'when' via an explicit 'Use when...' clause with multiple concrete trigger scenarios.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases including synonyms and tool names ('building ML pipelines', 'orchestrating training workflows', 'tuning hyperparameters', 'MLOps tooling like Kubeflow, Airflow, MLflow, or Prefect') that users would naturally say.	5 / 5
Distinctiveness Conflict Risk	Targets a distinct ML-pipeline/MLOps niche with specific tool triggers (MLflow, Kubeflow, Feast, DVC), giving a clear niche with minimal conflict risk against unrelated skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Jeffallan/claude-skills
Path: skills/ml-pipeline/SKILL.md
Commit: 882ef55

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.