preprocessing-data-with-automated-pipelines

Process automate data cleaning, transformation, and validation for ML tasks. Use when requesting "preprocess data", "clean data", "ETL pipeline", or "data transformation". Trigger with relevant phrases based on skill purpose.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

20%

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

The body is divided into clear sections but is largely generic prose and template filler with no executable code, and it fails to reference the bundled scripts that contain the real implementation. The workflow is sequenced but missing validation checkpoints for batch data operations.

Suggestions

Replace the prose examples and template-filler sections (Output, Resources, Instructions) with concrete, executable code snippets or direct references to the bundled scripts.

Add explicit links to the bundle — e.g. scripts/pipeline.py, scripts/validate_data.py, scripts/transform_data.py, and assets/example_data.csv — so SKILL.md functions as an overview pointing to the implementation.

Insert an explicit validation checkpoint into the workflow (e.g. validate data after transformation and only load when validation passes) to cover the batch operations the pipeline performs.

Dimension	Reasoning	Score
Conciseness	Template-filler sections ('The skill produces structured output relevant to the task', 'Project documentation', 'Related skills and commands') and a redundant Overview that restates the description pad the body with content Claude does not need.	1 / 3
Actionability	There is no executable code or commands anywhere; examples are described in prose ('Generate a Python script to read the CSV file, remove duplicate entries...') rather than provided, and the bundled scripts are never referenced.	1 / 3
Workflow Clarity	'How It Works' lists a 4-step sequence (analyze, generate, execute, report) but lacks validation checkpoints for batch data operations, which the rubric caps at 2.	2 / 3
Progressive Disclosure	Sections are organized, but the body never signals or links to the bundled scripts (pipeline.py, validate_data.py, transform_data.py, handle_errors.py) or assets/example_data.csv that hold the actual implementation.	2 / 3
	Total	6 / 12 Passed

Description

92%

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 both capability and explicit triggers with good natural keyword coverage, scoring near the top of the scale. Its only weaknesses are the garbled opening verb, a redundant trailing filler sentence, and trigger terms broad enough to risk overlap with related data skills.

Dimension	Reasoning	Score
Specificity	Names three concrete operations — 'data cleaning, transformation, and validation for ML tasks' — matching the multi-action anchor, though the opening 'Process automate' is grammatically garbled.	3 / 3
Completeness	Explicitly answers both what (cleaning/transformation/validation for ML) and when ('Use when requesting preprocess data, clean data, ETL pipeline, or data transformation').	3 / 3
Trigger Term Quality	Includes natural user phrases 'preprocess data', 'clean data', 'ETL pipeline', and 'data transformation', giving good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The ML/ETL framing gives a niche, but 'data cleaning' and 'data transformation' are broad and could still overlap with general data-analysis skills.	2 / 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: 2cafb23

Reviewed: 2 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.