aeon
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.
84
82%
Does it follow best practices?
Impact
84%
1.33xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
92%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 enumerates specific capabilities and includes an explicit 'Use when' clause with good trigger terms. The main weakness is potential overlap with general machine learning skills, since many of the listed tasks (classification, regression, clustering) are common ML tasks—the time series qualifier helps but may not always prevent conflicts. The description uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. These are well-defined ML task types. | 3 / 3 |
Completeness | Clearly answers both what (time series ML tasks including classification, regression, clustering, etc.) and when ('Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches'). Explicit 'Use when' clause is present. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'time series', 'classification', 'regression', 'forecasting', 'anomaly detection', 'temporal data', 'sequential patterns', 'univariate', 'multivariate', 'scikit-learn'. Good coverage of both technical and conceptual terms. | 3 / 3 |
Distinctiveness Conflict Risk | While 'time series' is a clear niche, terms like 'classification', 'regression', 'clustering', and 'anomaly detection' could overlap with general ML skills. The phrase 'beyond standard ML approaches' helps differentiate but the boundary could still be ambiguous when a user mentions ML tasks without explicitly saying 'time series'. | 2 / 3 |
Total | 11 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill that covers the aeon toolkit comprehensively with executable code examples and excellent progressive disclosure through reference files. Its main weaknesses are moderate verbosity (some sections like 'When to Use' and general ML advice are unnecessary for Claude) and the lack of validation/error-handling guidance in workflows. The actionability is strong with concrete, runnable code throughout.
Suggestions
Remove the 'When to Use This Skill' section — this duplicates the frontmatter description and is better handled by skill matching metadata rather than consuming tokens in the body.
Add validation checkpoints to workflows, e.g., verifying data shape matches expected (n_samples, n_channels, n_timepoints) format before fitting, and checking for NaN values in predictions.
Trim generic ML advice from Best Practices (e.g., 'Use Validation: Split training data for hyperparameter tuning') that Claude already knows, keeping only aeon-specific guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some unnecessary content like the 'When to Use This Skill' section (which restates what the frontmatter description already covers) and the 'Best Practices' section contains advice Claude already knows (use validation, start simple, compare baselines). The algorithm selection guide and code examples are valuable, but the overall document is quite long (~250 lines) with some redundancy between sections. | 2 / 3 |
Actionability | Every section includes fully executable, copy-paste ready Python code with proper imports. The algorithm selection guide provides concrete recommendations mapped to specific use cases. Code examples cover the full workflow from data loading to prediction. | 3 / 3 |
Workflow Clarity | The common workflows section shows clear pipelines, and the data preparation steps are sequenced. However, there are no validation checkpoints or error recovery steps — no guidance on what to do when data shapes are wrong, when models fail to converge, or how to verify results. For ML workflows involving data transformation and model training, some validation feedback loops would be expected. | 2 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear overview in the main file and well-signaled one-level-deep references to 11 separate reference files. Each capability section includes a quick start inline and points to a detailed reference document. The reference documentation section at the end provides a clean index. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
Total | 10 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
25e1c0f
- 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.