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

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/ai-ml/data-preprocessing-pipeline/skills/preprocessing-data-with-automated-pipelines/SKILL.md

Quality

Content

35%Weight 40%Scale 1-3

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

The body is structurally organized but mostly descriptive rather than actionable: it contains no executable code, never references the bundled pipeline/transform/validate scripts that hold the real capability, and is padded with generic filler sections. The workflow has a sequence but lacks the validation checkpoints expected for batch data operations.

Suggestions

Replace the prose examples with executable guidance — show how to invoke scripts/pipeline.py (e.g. `python scripts/pipeline.py --input data.csv`) or include a concrete pandas code snippet, so Claude can act rather than paraphrase.

Link the bundled scripts from the body (e.g. 'Validation: see [scripts/validate_data.py](scripts/validate_data.py)') and drop the empty Output, Resources, and meta Instructions sections that add no value.

Add explicit validation checkpoints to the workflow (run validate_data.py after transform, fix and re-validate before reporting) to turn the abstract 'include validation' advice into a real feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is sectioned but padded with vacuous filler — 'The skill produces structured output relevant to the task', 'Project documentation', and an 'Instructions' section telling Claude to 'Invoke this skill when the trigger conditions are met' — that adds nothing Claude does not already know.	2 / 3
Actionability	No executable code or commands appear anywhere; the examples describe in prose ('Generate a Python script to read the CSV file... and impute missing values') rather than instruct, and the bundled scripts holding the real code are never surfaced.	1 / 3
Workflow Clarity	A four-step sequence exists (Analyze → Generate → Execute → Provide Metrics), but validation is only abstract advice ('Always include data validation steps') with no checkpoints or feedback loops, so per the batch-operation cap it cannot exceed 2.	2 / 3
Progressive Disclosure	The body is organized into clear sections, but the actual bundle (scripts/pipeline.py, validate_data.py, transform_data.py, handle_errors.py, assets/example_data.csv) is never referenced or linked, so the overview fails to route Claude to the detailed materials that exist.	2 / 3
	Total	7 / 12 Passed

Description

92%Weight 40%Scale 1-3

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 description that covers capabilities, natural trigger terms, and an explicit 'Use when...' clause, clearly answering both what and when. It is held back only by moderate overlap risk from generic terms like 'clean data' and a trailing filler sentence ('Trigger with relevant phrases based on skill purpose') plus minor grammatical awkwardness ('Process automate data cleaning').

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'data cleaning, transformation, and validation' — matching the anchor for several specific concrete actions, not just naming a domain.	3 / 3
Completeness	Explicitly answers both what ('data cleaning, transformation, and validation for ML tasks') and when via a 'Use when requesting...' clause, satisfying the anchor for both what AND when.	3 / 3
Trigger Term Quality	Natural user-facing triggers are present: 'preprocess data', 'clean data', 'ETL pipeline', 'data transformation' — phrases a user would actually say rather than technical jargon.	3 / 3
Distinctiveness Conflict Risk	The ML-preprocessing/ETL niche is reasonably clear, but 'clean data' and 'data transformation' are generic terms that overlap with broader data-analysis skills, so some conflict risk remains.	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
Path: plugins/ai-ml/data-preprocessing-pipeline/skills/preprocessing-data-with-automated-pipelines/SKILL.md
Commit: c4eafaf

Reviewed: 5 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.