Tessl • The package manager for agent skills

SkillPublic

splitting-datasets

Split datasets into training, validation, and test partitions with the right stratification and temporal rules. Use as a narrow preprocessing helper once the broader ML workflow is already chosen, not as the main route owner for an end-to-end ML task.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/splitting-datasets/SKILL.md

Quality

Content

40%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.

The body is concise and well-structured as a positioning/routing skill, but it provides no concrete executable guidance and ignores its own bundle files. Adding a minimal workflow with validation and links to the bundled script and config would substantially raise the score.

Suggestions

Add a short worked example or reference scripts/split_data.py with concrete invocation (e.g., ratios, random seed, stratify column) so the guidance is executable rather than descriptive.

Include a brief split-then-validate workflow with an explicit checkpoint (e.g., verify no group/time leakage between partitions before handing off) to satisfy the batch-operation validation requirement.

Link the existing bundle files (split_data_config.yaml, dataset_schema.json, example_dataset.csv) from the relevant sections so progressive disclosure surfaces the bundled resources.

Dimension	Reasoning	Score
Conciseness	The body is lean and sectioned without over-explaining concepts Claude already knows; the only minor trim is the 'Positioning' section, which restates the description's narrow-helper framing.	4 / 5
Actionability	The body offers only high-level descriptions ('Partition strategy with ratios, random seeds, and stratification rules') with no executable code, commands, or concrete steps, and it never points to the bundled split_data.py or config files.	2 / 5
Workflow Clarity	There is no sequenced workflow — only 'When to Use' conditions and abstract output descriptions — and no validation/verification checkpoint for this batch dataset operation, which the rubric caps at 3.	2 / 5
Progressive Disclosure	Although the body has clear sections, it fails to reference the actual bundle files (scripts/split_data.py, assets/split_data_config.yaml, dataset_schema.json) that exist, leaving those resources unlinked and undiscoverable.	2 / 5
	Total	10 / 20 Passed

Description

71%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.

The description is specific, third-person, and clearly distinguishes the skill's narrow niche from neighboring ML skills. Its main weakness is trigger-term coverage, which lacks common synonyms and file extensions users would naturally say.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions — 'split datasets into training, validation, and test partitions', 'stratification', 'temporal rules' — with only minor coverage gaps.	4 / 5
Completeness	Clearly states what the skill does and gives an explicit 'when' clause ('Use as a narrow preprocessing helper once the broader ML workflow is already chosen'), though the 'when' is a positioning statement rather than concrete user trigger phrases.	4 / 5
Trigger Term Quality	Includes relevant keywords like 'datasets', 'training, validation, and test partitions', and 'stratification', but misses common natural variations such as 'train/test split', 'holdout', or file extensions.	3 / 5
Distinctiveness Conflict Risk	The description explicitly carves a narrow niche ('not as the main route owner for an end-to-end ML task') and contrasts against related skills, giving it a clear distinct trigger with minimal conflict risk.	5 / 5
	Total	16 / 20 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: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/splitting-datasets/SKILL.md
Revision: 5ce2258

Reviewed: 28 days ago

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.

splitting-datasets

Table of Contents

Is this your skill?