cross-validation-setup
Cross Validation Setup - Auto-activating skill for ML Training. Triggers on: cross validation setup, cross validation setup Part of the ML Training skill category.
Overall
score
23%
Does it follow best practices?
Validation for skill structure
Install with Tessl CLI
npx tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill cross-validation-setupActivation
7%This description is essentially a placeholder that names the skill but provides no substantive information about its capabilities. It lacks concrete actions, meaningful trigger terms, and explicit usage guidance. The redundant trigger terms and absence of natural language variations make it difficult for Claude to appropriately select this skill.
Suggestions
Add specific actions the skill performs, e.g., 'Configures k-fold cross validation, stratified splits, and leave-one-out validation for model evaluation'
Include natural trigger term variations users would say: 'k-fold', 'CV', 'train-test split', 'validation strategy', 'holdout set', 'model evaluation'
Add an explicit 'Use when...' clause: 'Use when the user needs to set up cross validation, evaluate model performance, or configure data splitting strategies for ML training'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description only names the domain 'cross validation setup' without describing any concrete actions. It doesn't explain what the skill actually does - no verbs like 'configure', 'split data', 'evaluate models', etc. | 1 / 3 |
Completeness | The description fails to answer 'what does this do' beyond naming itself, and while it mentions triggers, they are just the skill name repeated. There is no explicit 'Use when...' clause with meaningful guidance. | 1 / 3 |
Trigger Term Quality | The trigger terms are redundant ('cross validation setup' listed twice) and miss natural variations users might say like 'k-fold', 'CV', 'train-test split', 'holdout validation', or 'model validation'. | 1 / 3 |
Distinctiveness Conflict Risk | Being part of 'ML Training skill category' provides some context, and 'cross validation' is a specific ML concept. However, without concrete actions described, it could overlap with other ML/model evaluation skills. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
7%This skill is essentially a placeholder template with no actual instructional content. It describes what a cross validation skill should do but provides zero concrete guidance on how to actually implement cross validation. The content would be useless to Claude as it contains no code examples, no specific techniques, and no actionable information.
Suggestions
Add executable code examples showing k-fold, stratified k-fold, and time-series cross validation implementations using sklearn/pytorch
Include specific guidance on choosing the right CV strategy based on data characteristics (imbalanced classes, time series, small datasets)
Provide concrete parameter recommendations (e.g., 'Use 5-10 folds for most cases; use LOOCV only for n<50')
Add validation steps showing how to check for data leakage and interpret CV results
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is padded with generic boilerplate that explains nothing Claude doesn't already know. Phrases like 'provides automated assistance' and 'follows industry best practices' are meaningless filler with no actual information about cross validation. | 1 / 3 |
Actionability | No concrete code, commands, or specific guidance is provided. The skill describes what it claims to do but never actually shows how to implement cross validation - no code examples, no specific techniques (k-fold, stratified, etc.), no parameters. | 1 / 3 |
Workflow Clarity | No workflow is defined. 'Provides step-by-step guidance' is claimed but no actual steps are given. There's no sequence, no validation checkpoints, and no actual process for setting up cross validation. | 1 / 3 |
Progressive Disclosure | The content has some structure with clear section headers, but there's nothing to disclose - no references to detailed documentation, no links to examples, and the sections themselves contain no substantive content to organize. | 2 / 3 |
Total | 5 / 12 Passed |
Validation
69%Validation — 11 / 16 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
metadata_version | 'metadata' field is not a dictionary | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
body_steps | No step-by-step structure detected (no ordered list); consider adding a simple workflow | Warning |
Total | 11 / 16 Passed | |
Reviewed
Table of Contents
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.