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.
34
3%
Does it follow best practices?
Impact
89%
0.92xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./planned-skills/generated/07-ml-training/cross-validation-setup/SKILL.mdQuality
Discovery
7%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is essentially a title repeated as a trigger term with no substantive content. It fails to describe what the skill actually does (e.g., configure k-fold splits, set up stratified sampling, generate validation metrics) and provides no explicit guidance on when Claude should select it. The duplicated trigger term suggests a template was used without customization.
Suggestions
Add concrete actions the skill performs, e.g., 'Configures k-fold cross validation, sets up stratified splits, implements leave-one-out CV, and generates validation metrics for model evaluation.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks about k-fold, cross validation, CV splits, train/test splitting, holdout sets, or model validation strategies.'
Remove the duplicated trigger term and expand with natural variations users would actually say, such as 'k-fold', 'CV', 'validation split', 'stratified sampling', 'LOOCV'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description only names the domain ('cross validation setup' and 'ML Training') but does not describe any concrete actions like splitting data, configuring k-folds, stratified sampling, or evaluating model performance. It is essentially a label, not a capability description. | 1 / 3 |
Completeness | The 'what' is extremely weak (no concrete actions described) and the 'when' is missing entirely—there is no 'Use when...' clause or equivalent explicit trigger guidance. It only states it 'triggers on' the same phrase repeated. | 1 / 3 |
Trigger Term Quality | The only trigger terms listed are 'cross validation setup' repeated twice. It misses natural variations users would say such as 'k-fold', 'CV', 'train/test split', 'holdout validation', 'stratified cross validation', or 'model evaluation'. | 1 / 3 |
Distinctiveness Conflict Risk | The term 'cross validation' is somewhat specific to a particular ML technique, which provides some distinctiveness. However, the vague 'ML Training' category and lack of concrete actions could cause overlap with other ML-related skills. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
0%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is essentially a placeholder or auto-generated template with no actual instructional content. It describes what it would do in theory but never provides any concrete guidance on cross-validation setup — no code examples (e.g., sklearn's KFold, StratifiedKFold), no parameter recommendations, no workflow steps. It fails on every dimension of the rubric.
Suggestions
Replace the meta-description with actual cross-validation code examples using sklearn (e.g., KFold, StratifiedKFold, cross_val_score) with executable, copy-paste-ready snippets.
Add a clear workflow: 1) Choose CV strategy based on data characteristics, 2) Implement the split, 3) Train/evaluate per fold, 4) Aggregate and validate results — with specific validation checkpoints.
Include concrete guidance on when to use different CV strategies (KFold vs StratifiedKFold vs TimeSeriesSplit vs GroupKFold) with brief decision criteria rather than vague 'best practices' claims.
Remove all self-referential content (Purpose, When to Use, Example Triggers, Capabilities) that describes the skill rather than teaching the task.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is entirely filler and meta-description. It explains what the skill does in abstract terms without providing any actual technical content. Phrases like 'Provides step-by-step guidance' and 'Follows industry best practices' are empty padding with zero informational value. | 1 / 3 |
Actionability | There is no concrete code, no executable commands, no specific examples of cross-validation implementation. The entire skill describes rather than instructs — it never actually shows how to set up cross validation. | 1 / 3 |
Workflow Clarity | No workflow steps are provided whatsoever. There is no sequence of actions, no validation checkpoints, and no actual process for setting up cross validation. The skill only describes itself in abstract terms. | 1 / 3 |
Progressive Disclosure | The content is a monolithic block of meta-description with no meaningful structure. There are no references to detailed materials, no links to examples or API references, and the sections present (Purpose, When to Use, Capabilities) contain no actionable content. | 1 / 3 |
Total | 4 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Commit
3076d78
- 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.