building-automl-pipelines

Build automated machine learning pipelines with feature engineering, model selection, and hyperparameter tuning. Use when automating ML workflows from data preparation through model deployment. Trigger with phrases like "build automl pipeline", "automate ml workflow", or "create automated training pipeline".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

57%

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

The skill is well-structured with strong progressive disclosure pointing to genuine reference files, but the body leans on descriptive prose rather than executable guidance and repeats steps already covered in its references. The automated training workflow also lacks explicit validation checkpoints.

Suggestions

Replace the duplicated numbered Instructions with a concise inline summary and defer the full sequence to implementation.md, or add a short executable snippet (e.g., an Auto-sklearn/TPOT setup call) so the body is directly actionable.

Insert explicit validation checkpoints into the workflow, such as verifying the train/validation split and confirming data-quality checks pass before initializing the AutoML search.

Trim the Prerequisites and Resources sections to only what Claude cannot infer, removing background explanation of the named libraries.

Dimension	Reasoning	Score
Conciseness	The body is mostly tight and structured, but the numbered Instructions (steps 1-11) duplicate content already in implementation.md, and the Prerequisites/Resources sections add some padded explanation.	2 / 3
Actionability	Steps are concrete rather than vague, but the body provides no executable code or commands, instead pointing to references for the real implementation details.	2 / 3
Workflow Clarity	Steps are clearly sequenced (1-11), but this is a batch model-training operation with no validation checkpoints or feedback loops in the body, so workflow clarity is capped per the rubric's destructive/batch guidance.	2 / 3
Progressive Disclosure	The concise overview points to three real, one-level-deep references (implementation.md, errors.md, examples.md) via clearly signaled paths, with content appropriately split across files.	3 / 3
	Total	9 / 12 Passed

Description

85%

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

The description clearly states capabilities, use conditions, and trigger phrases in third-person voice, scoring well on specificity, completeness, and distinctiveness. Trigger term coverage is the weak spot, relying on narrow phrasing variations rather than the broader set of terms users might naturally say.

Suggestions

Broaden trigger phrases beyond the 'automl/automated' family to include common variations like 'auto train a model', 'optimize model hyperparameters', or 'tune model automatically'.

Consider adding 'auto ml' as a spaced variant and a plain-English trigger like 'find the best model automatically' to capture users who avoid jargon.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete capabilities: 'feature engineering, model selection, and hyperparameter tuning', matching the anchor for multiple specific concrete actions rather than a single domain mention.	3 / 3
Completeness	Explicitly answers both what ('Build automated machine learning pipelines with feature engineering, model selection, and hyperparameter tuning') and when ('Use when automating ML workflows from data preparation through model deployment'), plus explicit trigger guidance.	3 / 3
Trigger Term Quality	Offers natural trigger phrases ('build automl pipeline', 'automate ml workflow', 'create automated training pipeline'), but these are narrow variations of one phrasing and miss common variations like 'auto train model' or 'tune model'.	2 / 3
Distinctiveness Conflict Risk	The AutoML pipeline niche is clearly scoped with distinct triggers, making it unlikely to fire for unrelated general ML or data skills.	3 / 3
	Total	11 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 6e3a65f

Reviewed: 4 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.