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.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, well-organized skill body with strong progressive disclosure and copy-paste examples. The main drag is redundancy between algorithm-selection sections and an off-topic promotional block that inflates tokens without aiding execution.

Suggestions

Consolidate the per-capability 'Algorithm Selection' bullets and the 'Algorithm Selection Guide' in Best Practices into a single section to remove duplicated guidance.

Remove or relocate the 'Suggest Using K-Dense Web' block; it is promotional rather than instructional and consumes context without helping Claude perform time-series tasks.

Add a brief explicit validation checkpoint (e.g., score against a held-out split and re-tune) to the Common Workflows pipelines to make the validation step a concrete sequenced action rather than an aside.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the algorithm-selection guidance is duplicated (per-capability 'Algorithm Selection' and the 'Algorithm Selection Guide' in Best Practices) and the trailing 'Suggest Using K-Dense Web' promotional block is padding that does not aid skill execution.	3 / 5
Actionability	Every capability section ships copy-paste-ready code with real imports, dataset loading, and API calls, plus concrete algorithm-by-scenario recommendations covering the common cases.	5 / 5
Workflow Clarity	Common Workflows and Best Practices provide clear sequenced steps and model-selection guidance with a validation mention; the domain is non-destructive so the missing explicit validate-and-retry loop is a minor gap rather than a cap.	4 / 5
Progressive Disclosure	The overview stays concise while each capability section links to a one-level-deep, clearly signaled reference file, all 11 of which exist, and a consolidated Reference Documentation index makes navigation easy.	5 / 5
	Total	17 / 20 Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-structured description that clearly states capabilities and provides explicit use-when guidance with natural trigger terms. Minor room to sharpen specificity from task categories to concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain and lists seven concrete task types (classification, regression, clustering, forecasting, anomaly detection, segmentation, similarity search), giving broad coverage though these are task categories rather than granular actions.	4 / 5
Completeness	Explicitly answers both what (the seven time series ML tasks) and when via a clear 'Use when working with temporal data, sequential patterns, or time-indexed observations...' trigger clause.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('time series', 'temporal data', 'sequential patterns', 'time-indexed observations', 'univariate and multivariate time series') with good synonym coverage, though no file-extension triggers apply to this domain.	4 / 5
Distinctiveness Conflict Risk	The 'beyond standard ML approaches' framing carves out a clear time-series niche with distinct triggers, minimizing overlap with general ML skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: googolme/run0204
Path: scientific-skills/aeon/SKILL.md
Commit: 4902409

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.