alonso-skills/sql-ml-features
Use when preparing data for machine learning from SQL Server — feature engineering in T-SQL, building training/test datasets, statistical aggregations for ML pipelines, sampling strategies, data normalization and encoding in SQL, writing queries that feed pandas or scikit-learn, exporting to Parquet or CSV for model training, or when a data scientist asks for a 'feature table' or 'training set' from a SQL Server database.
100
100%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%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 is a strong description that clearly defines a specific niche — ML data preparation from SQL Server — with rich trigger terms covering both the SQL and data science sides. It includes an explicit 'Use when' clause and lists numerous concrete actions. The only minor weakness is that it lacks a brief 'what this does' summary sentence before the 'Use when' clause, making it read as purely trigger-oriented rather than having a clean what/when structure.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: feature engineering in T-SQL, building training/test datasets, statistical aggregations, sampling strategies, data normalization and encoding, writing queries that feed pandas or scikit-learn, exporting to Parquet or CSV. | 3 / 3 |
Completeness | Opens with an explicit 'Use when' clause that covers both what (feature engineering, building datasets, statistical aggregations, exporting data) and when (preparing data for ML from SQL Server, when a data scientist asks for a 'feature table' or 'training set'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms a data scientist would use: 'feature engineering', 'training/test datasets', 'ML pipelines', 'sampling strategies', 'data normalization', 'pandas', 'scikit-learn', 'Parquet', 'CSV', 'feature table', 'training set', 'SQL Server'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche at the intersection of SQL Server and machine learning data preparation. The combination of T-SQL, ML pipelines, and specific tools like pandas/scikit-learn makes it very unlikely to conflict with general SQL or general ML skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an exceptionally well-crafted skill. It is dense, actionable, and well-structured — the workflow has explicit validation at every step, the reference tables are immediately usable, and the common mistakes section addresses real pitfalls with specific fixes. Content is appropriately split between the overview and reference files with clear navigation.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. No explanations of concepts Claude already knows (no 'what is ML' preamble). Tables are dense and scannable. The 'When NOT to use' section efficiently scopes the skill without padding. | 3 / 3 |
Actionability | The quick reference table provides copy-paste-ready T-SQL patterns for every ML concept. The workflow section includes executable SQL snippets, and the common mistakes table gives specific fixes rather than vague advice. | 3 / 3 |
Workflow Clarity | The 7-step feature table build workflow is clearly sequenced with explicit validation checkpoints at every step (row count checks, NULL checks, type checks, proportion checks). Error recovery is implicit but the validate-then-proceed pattern is consistently enforced. | 3 / 3 |
Progressive Disclosure | The SKILL.md serves as a well-organized overview with concise tables and workflow, then clearly signals five one-level-deep reference files for detailed content (feature engineering, sampling, NULL imputation, export, data leakage). Navigation is straightforward. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
Reviewed
Table of Contents