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
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 skill description that clearly defines its scope (time series machine learning), lists specific supported tasks, and provides explicit trigger guidance for when to use it. It distinguishes itself well from general ML skills by emphasizing temporal/sequential data and specialized algorithms. The description is concise, uses third person voice, and includes natural trigger terms users would employ.
| 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, forecasting, anomaly detection, segmentation, similarity search) and when ('Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches'). | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'time series', 'forecasting', 'anomaly detection', 'temporal data', 'sequential patterns', 'univariate', 'multivariate', 'scikit-learn'. Good coverage of terms a user working with time series data would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly carves out a distinct niche: time series ML specifically, differentiated from standard ML by the phrase 'beyond standard ML approaches'. The mention of scikit-learn compatible APIs and specific time series tasks makes it unlikely to conflict with general ML or data processing skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%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, highly actionable skill with excellent executable code examples covering all major aeon capabilities. Its main weaknesses are verbosity (the document tries to be both an overview and a detailed guide, resulting in ~300 lines) and lack of validation/error-handling guidance in workflows. The progressive disclosure structure is well-designed in theory but the main file retains too much detail that could be delegated to reference files.
Suggestions
Remove the 'When to Use This Skill' section — this information is redundant with the skill description and Claude can infer applicability from the content itself.
Move the 'Best Practices' and 'Algorithm Selection Guide' sections into a reference file (e.g., references/best_practices.md) and keep only a brief pointer in the main skill.
Add validation checkpoints to workflows, e.g., verifying data shape matches expected (n_samples, n_channels, n_timepoints) format before fitting, and checking for common errors like NaN values in predictions.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some unnecessary content like the 'When to Use This Skill' section (Claude can infer this), repeated algorithm selection guidance in multiple places, and some verbose explanations. The best practices section, while useful, adds significant length with advice Claude likely already knows (e.g., 'use validation', 'compare baselines'). However, the code examples are generally lean. | 2 / 3 |
Actionability | Every capability section includes fully executable, copy-paste ready Python code with proper imports. The examples use real dataset names, concrete parameters, and show complete workflows from data loading to prediction. The algorithm selection guide provides specific class names for different use cases. | 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 models fail, how to verify data format correctness, or feedback loops for debugging. For ML workflows involving data preparation and model training, some validation steps would be expected. | 2 / 3 |
Progressive Disclosure | The skill references 11 separate reference files in a well-organized directory structure with clear signaling throughout the document. However, since no bundle files were provided, we cannot verify these references exist. The main SKILL.md itself is quite long (~300 lines) and could benefit from moving some content (like the full best practices and algorithm selection guide) into reference files to keep the overview leaner. | 2 / 3 |
Total | 9 / 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
cbcae7b
- 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.