splitting-datasets

Process split datasets into training, validation, and testing sets for ML model development. Use when requesting "split dataset", "train-test split", or "data partitioning". 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

35%

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

The body is organized into sections but is largely generic and non-executable: it describes code that 'will be generated' rather than providing it, omits validation steps, and ignores the available bundle resources. It reads more like a template than skill-specific guidance.

Suggestions

Replace prose descriptions of generated code with actual, executable Python (e.g. a concrete train_test_split snippet) so guidance is copy-paste ready.

Add an explicit validation checkpoint in the workflow (verify split ratios, check for data leakage, confirm stratified class proportions) and a fix-and-retry loop.

Link to the existing bundle files from the body (assets/split_data_config.yaml, assets/dataset_schema.json, scripts/split_data.py) and remove the generic Instructions/Output/Resources filler.

Dimension	Reasoning	Score
Conciseness	It retains section structure but is padded with generic boilerplate ('Output', 'Resources', 'Instructions') and re-explains basic train/validation/test splitting that Claude already knows, so it is not lean.	2 / 3
Actionability	No executable code or specific commands appear; it only says it 'generates Python code utilizing standard ML libraries', describing rather than instructing, which matches the vague/abstract anchor 1.	1 / 3
Workflow Clarity	A three-step sequence is listed (Analyze, Generate, Execute) but it is abstract and lacks validation checkpoints, and dataset splitting is a batch operation that caps clarity at 2 without feedback loops.	2 / 3
Progressive Disclosure	The body is sectioned but never signals the existing bundle files (dataset_schema.json, example_dataset.csv, split_data_config.yaml, split_data.py), keeping material inline that should be referenced one level deep.	2 / 3
	Total	7 / 12 Passed

Description

90%

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 is strong: it states the skill's purpose clearly and pairs it with natural, explicit trigger phrases. The only weakness is that it enumerates a single concrete action rather than several, and the trailing 'Trigger with relevant phrases based on skill purpose' is redundant filler.

Dimension	Reasoning	Score
Specificity	It names the domain and the main action ('Process split datasets into training, validation, and testing sets') but does not list multiple distinct concrete actions, so it falls short of the multi-action anchor 3.	2 / 3
Completeness	It explicitly answers what it does and when to use it via the 'Use when requesting "split dataset"...' clause, matching the what-and-when anchor 3.	3 / 3
Trigger Term Quality	It surfaces natural phrases a user would say ('split dataset', 'train-test split', 'data partitioning'), giving good coverage of common variations.	3 / 3
Distinctiveness Conflict Risk	It carves a clear ML dataset-splitting niche with distinct triggers, making it unlikely to fire for unrelated 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: 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.