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

86%

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

72%

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-structured overview with verified progressive disclosure and concrete v1.x code. Its main weakness is length and duplicated algorithm-selection content, with workflows lacking explicit validation checkpoints.

Suggestions

Collapse the duplicated algorithm-selection content: keep one canonical guide (e.g., in the 'Algorithm Selection Guide' section) and have the per-capability sections reference it instead of restating picks.

Add an explicit validation/verification checkpoint to at least one Common Workflow (e.g., assert accuracy against a baseline or verify array shape (n_cases, n_channels, n_timepoints) after loading) to lift workflow clarity.

Trim the inline architectural and distance catalog lists that are already covered by their reference files, letting references/ carry the enumerations.

Dimension	Reasoning	Score
Conciseness	Mostly efficient — version-specific notes like 'ARIMA uses p/d/q (not order=)' earn their place — but the ~390-line body duplicates algorithm-selection guidance (the per-section 'Algorithm Selection' list and the later 'Algorithm Selection Guide') and could be tightened.	2 / 3
Actionability	Every capability ships executable, copy-paste-ready quick-start code with correct import paths and concrete version-1.x specifics (e.g., 'Set horizon in the constructor; predict passes the series to forecast from'), matching the fully-executable anchor.	3 / 3
Workflow Clarity	The 'Common Workflows' pipelines are sequenced (fit/score), but no explicit validation or error-recovery checkpoints are present; per the anchor, sequence without checkpoints caps this at 2.	2 / 3
Progressive Disclosure	Clear overview with well-signaled one-level-deep references ('See references/classification.md for complete algorithm catalog') plus a 'Reference Documentation' index; all 11 referenced files verified present in ./references/.	3 / 3
	Total	10 / 12 Passed

Description

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.

A strong, well-scoped description that names concrete task types, supplies natural trigger terms, and pairs a clear 'what' with an explicit 'when' clause in third-person voice. No revisions needed.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search' — matching the score-3 anchor that names several specific actions rather than vague language.	3 / 3
Completeness	Explicitly answers what ('time series machine learning tasks including...') and when via an explicit 'Use when working with temporal data, sequential patterns, or time-indexed observations' trigger clause, satisfying both halves.	3 / 3
Trigger Term Quality	Covers natural terms users would say — 'time series', 'forecasting', 'anomaly detection', 'temporal data', 'sequential patterns' — giving good coverage of common variations rather than just technical jargon.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear time-series-ML niche with 'beyond standard ML approaches' and scikit-learn-compatible framing, making it unlikely to trigger for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/aeon/SKILL.md
Commit: 757b63b

Reviewed: about 12 hours 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.